--- /dev/null
+#!/usr/local/bin/perl
+#-Description-------------------------------------------
+# Free realtime web server logfile analyzer (in Perl) working as a CGI to show
+# advanced web statistics. For better performances, you should use this script
+# at least once a day (from a scheduler for example).
+# See README.TXT file for setup and benchmark informations
+# See COPYING.TXT file about AWStats GNU General Public License
+#-------------------------------------------------------
+
+#-------------------------------------------------------
+# Setup/Configure section
+#-------------------------------------------------------
+# Warning: If you're under Linux/Unix, don't forget to change first line of this file with path of your perl binary.
+# Warning: With IIS, if your log filename is different each month or day, launch awstats just before the end of month or day.
+# If you forget it, you will also forget statistics for this month or day.
+$LogFile = "/var/log/httpd/mylog.log"; # Web server logfile to analyze, with full path (ie with IIS: "C:/WINNT/system32/LogFiles/W3SVC1/exyymm.log")
+$LogFormat = 1; # 1 = Apache combined log format, 2 = IIS extended W3C log format
+$DirIcons = "/icons"; # Depending on web server, add relative or absolute web URL of all icons subdirectories (Default = "/icons" means you must copy icons directories in "yourwwwroot/icons")
+@HostAliases= ("www.myserver.com","127.0.0.1","x.y.z.w"); # Put here all possible domain names, addresses or virtual hosts someone can use to access your site
+$DefaultFile= "index.html"; # Default page name for your Web server (Default = "index.html")
+$ArchiveLogRecords = 0; # If AWStats can purge log after processing it, it will do so. You can keep an archive file of processed log records by setting this to 1 (Default = 0)
+$Lang = 0; # Default language: 0 = English, 1 = French, 2 = Dutch, 3 = Spanish (Default = 0)
+$WarningMessages=1; # 1 = Show message informations when warning occurs, 0 = Skip message information for warning (Default = 1)
+$Barwidth = 260; # Bar width in pixel, for horizontal graphics bar (Default = 260)
+$Barheight = 220; # Bar height in pixel, for vertical graphics bar (Default = 220)
+$SortDir = -1; # -1 = Sort order from most to less, 1 = reverse order (Default = -1)
+$ShowLinksOnUrl= 1; # 1 = Each URL shown in stats are links you can click. Not available for pages generated from command line (Default = 1)
+$VisitTimeOut = 10000; # Laps of time to consider a page load as a new visit. 10000 = one hour (Default = 10000)
+$DNSLookup = 1; # 1 = Show name instead of IPAddress, 0 is faster (Default = 1)
+$FullHostName = 1; # 1 = Use name.domaine.zone to refer host clients, 0 = all hosts in same domaine.zone are one host (Default = 1)
+$MaxLengthOfURL= 70; # Maximum length of URL shown on stats page. This affects only URL visible text, link still work (Default = 70)
+$SponsorLinkVisible = 0; # 1 = Link to AWStats sponsor, at the bottom, is visible (Default = 0)
+$BenchMark=0; # Set this to 1 to get some benchmark informations
+# Stats by hosts
+$MaxNbOfHostsShown = 25; #
+$MinHitHost = 1; #
+# Stats by pages
+$MaxNbOfPageShown = 25; #
+$MinHitFile = 1; #
+# Stats by referers
+$MaxNbOfRefererShown = 25; #
+$MinHitRefer = 1; #
+# Keywords
+$MaxNbOfKeywordsShown = 20; #
+$MinHitKeyword = 1; #
+# Stats by robots
+$MaxNbOfRobotShown = 25; #
+$MinHitRobot = 1; #
+# Icons and colors
+$Logo="awstats_logo1.png"; # You can put your own logo, must be in awstats "other" directory (Default = "awstats_logo1.png")
+$color_Background="#FFFFFF"; # Background color for main page (Default = #FFFFFF)
+$color_TableBorder="#000000"; # Table border color (Default = #000000)
+$color_TableBG="#DDDDBB"; # Background color for table (Default = #DDDDBB)
+$color_TableTitle="#FFFFFF"; # Table title font color (Default = #FFFFFF)
+$color_TableBGTitle="#666666"; # Background color for table title (Default = #666666)
+$color_TableRowTitle="#FFFFFF"; # Table row title font color (Default = #FFFFFF)
+$color_TableBGRowTitle="#BBBBBB"; # Background color for row title (Default = #BBBBBB)
+$color_link="#4000FF"; # Color of HTML links (Default = #4000FF)
+$color_v="#F3F300"; # Background color for number of visites (Default = #F3F300)
+$color_w="#FF9933"; # Background color for number of unique visitors (Default = #FF9933)
+$color_p="#4477DD"; # Background color for number of pages (Default = #4477DD)
+$color_h="#66F0FF"; # Background color for number of hits (Default = #66F0FF)
+$color_k="#339944"; # Background color for number of bytes (Default = #339944)
+$color_s="#8888DD"; # Background color for number of search (Default = #8888DD)
+$BarImageVertical_v = "barrevv.png";
+$BarImageHorizontal_v = "barrehv.png";
+$BarImageVertical_u = "barrevu.png";
+$BarImageHorizontal_u = "barrehu.png";
+$BarImageVertical_p = "barrevp.png";
+$BarImageHorizontal_p = "barrehp.png";
+$BarImageVertical_h = "barrevh.png";
+$BarImageHorizontal_h = "barrehh.png";
+$BarImageVertical_k = "barrevk.png";
+$BarImageHorizontal_k = "barrehk.png";
+#----- End of Setup/Configure section
+
+
+#-------------------------------------------------------
+# Defines
+#-------------------------------------------------------
+$VERSION="2.22k";
+if ($ENV{"GATEWAY_INTERFACE"} ne "") { $PROG=$0; $PROG =~ s/.*\\//; $PROG =~ s/.*\///; $DIR=$0; $DIR =~ s/$PROG//; $PROG =~ s/\.pl$//; }
+else {
+ $PROG=$0; $PROG =~ s/.*\\//; $PROG =~ s/.*\///; $DIR=$0; $DIR =~ s/$PROG//; $PROG =~ s/\.pl$//;
+ $ShowLinksOnUrl=0;
+ }
+$QueryString = $ENV{"QUERY_STRING"};
+if ($QueryString =~ /lang=0/) { $Lang=0; }
+if ($QueryString =~ /lang=1/) { $Lang=1; }
+if ($QueryString =~ /lang=2/) { $Lang=2; }
+if ($QueryString =~ /lang=3/) { $Lang=3; }
+
+# Do not include access from clients that match following IP address
+@SkipHosts= ("x.y.z.w");
+
+# Do not include access to URLs that match following entries
+@SkipFiles= ("\\.css","\\.js","\\.class","robots\\.txt",
+ # If you don't want to include users homepage in your stats, uncomment the following line
+ # "/~"
+ # You can also, if you want, add list of not important frames page (like menus, etc...) to exclude them from statistics.
+ );
+
+# URL with such end signature are not HTML pages
+@NotPageList= (
+ "\\.gif","\\.jpg","\\.png","\\.bmp",
+ "\\.zip","\\.arj","\\.gz","\\.z",
+ "\\.pdf","\\.doc","\\.ppt",
+ "\\.mp3","\\.wma"
+ );
+
+# Those addresses are shown with those lib (First column is full relative URL, Second column is text to show instead of URL)
+%Aliases = (
+ "/", "<b>HOME PAGE</b>",
+ "/cgi-bin/awstats.pl", "<b>AWStats stats page</b>",
+ "/cgi-bin/awstats/awstats.pl", "<b>AWStats stats page</b>",
+ # Put here HTML text you want to see in links instead of URL text.
+ "/cgi-bin/htsearchlaunch", "<b>Recherche sur le site</b>",
+ "/cgi-bin/awmess/SendMess", "<b>Envoi de mails-formulaire via le Web</b>",
+ "/cgi-bin/awmess/GetMess", "<b>Lecture de mails-formulaire via le Web</b>"
+ );
+
+# ---------- Search URL --------------------
+@WordsToCleanSearchUrl= ("act=","annuaire=","btng=","categoria=","cou=","dd=","domain=","dt=","dw=","geo=","hc=","height=","hl=","hs=","kl=","lang=","loc=","lr=","medor=","message=","meta=","mode=","order=","page=","par=","pays=","pg=","pos=","prg=","qc=","refer=","sa=","safe=","sc=","sort=","src=","start=","stype=","tag=","temp=","theme=","url=","user=","width=","what=","\\.x=","\\.y=");
+# Never put the following exclusion ("Claus=","kw=","keyword=","MT","p=","q=","qr=","qt=","query=","s=","search=","searchText=") because they are strings that contain keywords we're looking for.
+# yahoo.com p=
+# altavista.com q=
+# google.com q=
+# eureka.com q=
+# lycos.com query=
+# hotbot.com MT=
+# msn.com MT=
+# infoseek.com qt=
+# webcrawler searchText=
+# excite search=
+# netscape.com search=
+# mamma.com query=
+# alltheweb.com query=
+# northernlight.com qr=
+
+
+# ---------- HTTP Code with tooltip --------
+%httpcode = (
+"201", "Partial Content", "202", "Request recorded, will be executed later", "204", "Request executed", "206", "Partial Content",
+"301", "Moved Permanently", "302", "Found",
+"400", "Bad Request", "401", "Unauthorized", "403", "Forbidden", "404", "Not Found", "408", "Request Timeout",
+"500", "Internal Error", "501", "Not implemented", "502", "Received bad response from real server", "503", "Server busy", "504", "Gateway Time-Out", "505", "HTTP version not supported",
+
+"200", "OK", "304", "Not Modified" # 200 and 304 are not errors
+);
+
+%monthlib = ( "01","Jan","02","Feb","03","Mar","04","Apr","05","May","06","Jun","07","Jul","08","Aug","09","Sep","10","Oct","11","Nov","12","Dec" );
+%monthnum = ( "Jan","01","Feb","02","Mar","03","Apr","04","May","05","Jun","06","Jul","07","Aug","08","Sep","09","Oct","10","Nov","11","Dec","12" );
+
+# ---------- Language translation messages --------
+$message[0][0]="Unknown"; $message[0][1]="Inconnus"; $message[0][2]="Onbekend"; $message[0][3]="Desconocido";
+$message[1][0]="Unknown (unresolved ip)"; $message[1][1]="Inconnu (IP non résolue)"; $message[1][2]="Onbekend (Onbekend ip)"; $message[1][3]="Dirección IP desconocida";
+$message[2][0]="Other visitors"; $message[2][1]="Autres visiteurs"; $message[2][2]="Andere bezoekers"; $message[2][3]="Otros visitantes";
+$message[3][0]="View details"; $message[3][1]="Voir détails"; $message[3][2]="Bekijk details"; $message[3][3]="Vea detalles";
+$message[4][0]="Day"; $message[4][1]="Jour"; $message[4][2]="Dag"; $message[4][3]="Día";
+$message[5][0]="Month"; $message[5][1]="Mois"; $message[5][2]="Maand"; $message[5][3]="Mes";
+$message[6][0]="Year"; $message[6][1]="Année"; $message[6][2]="Jaar"; $message[6][3]="Año";
+$message[7][0]="Statistics of"; $message[7][1]="Statistiques du site"; $message[7][2]="Statistieken van"; $message[7][3]="Estadísticas del sitio";
+$message[8][0]="First visit"; $message[8][1]="Première visite"; $message[8][2]="Eerste bezoek"; $message[8][3]="Primera visita";
+$message[9][0]="Last visit"; $message[9][1]="Dernière visite"; $message[9][2]="Laatste bezoek"; $message[9][3]="Última visita";
+$message[10][0]="Number of visits"; $message[10][1]="Nbre visites"; $message[10][2]="Aantal boezoeken"; $message[10][3]="Número de visitas";
+$message[11][0]="Unique visitors"; $message[11][1]="Nbre visiteurs différents"; $message[11][2]="Unieke bezoekers"; $message[11][3]="No. de visitantes distintos";
+$message[12][0]="visit"; $message[12][1]="visite"; $message[12][2]="bezoek"; $message[12][3]="visita";
+$message[13][0]="Keyword"; $message[13][1]="Mot clé"; $message[13][2]="Trefwoord"; $message[13][3]="Palabra clave (keyword)";
+$message[14][0]="Search"; $message[14][1]="Recherche"; $message[14][2]="Zoek"; $message[14][3]="Búsqueda";
+$message[15][0]="Percent"; $message[15][1]="Pourcentage"; $message[15][2]="Procent"; $message[15][3]="Porciento";
+$message[16][0]="Traffic Summary"; $message[16][1]="Résumé"; $message[16][2]="Opsomming"; $message[16][3]="Resumen de tráfico";
+$message[17][0]="Domains/Countries"; $message[17][1]="Domaines/Pays"; $message[17][2]="Domeinen/Landen"; $message[17][3]="Dominios/Países";
+$message[18][0]="Visitors"; $message[18][1]="Visiteurs"; $message[18][2]="Bezoekers"; $message[18][3]="Visitantes";
+$message[19][0]="Pages/URL"; $message[19][1]="Pages/URL"; $message[19][2]="Pagina's/URL"; $message[19][3]="Páginas/URLs";
+$message[20][0]="Hours"; $message[20][1]="Heures"; $message[20][2]="Uren"; $message[20][3]="Horas";
+$message[21][0]="Browsers"; $message[21][1]="Navigateurs"; $message[21][2]="Browsers"; $message[21][3]="Navegadores";
+$message[22][0]="HTTP Errors"; $message[22][1]="Erreurs HTTP"; $message[22][2]="HTTP Foutmeldingen"; $message[22][3]="Errores de protocolo HTTP";
+$message[23][0]="Referrers"; $message[23][1]="Origine/Referrer"; $message[23][2]="Verwijzing"; $message[23][3]="Referencia de origen";
+$message[24][0]="Search Keywords"; $message[24][1]="Mots clés de recherche"; $message[24][2]="Zoek trefwoorden"; $message[24][3]="Palabra clave de búsqueda";
+$message[25][0]="Visitors domains/countries"; $message[25][1]="Domaines/pays visiteurs"; $message[25][2]="Bezoekers domeinen/landen"; $message[25][3]="Dominios/País de visitantes";
+$message[26][0]="hosts"; $message[26][1]="des hôtes"; $message[26][2]="hosts"; $message[26][3]="servidor";
+$message[27][0]="pages"; $message[27][1]="des pages"; $message[27][2]="pagina's"; $message[27][3]="páginas";
+$message[28][0]="different pages"; $message[28][1]="pages différentes"; $message[28][2]="verschillende pagina's"; $message[28][3]="páginas diferentes";
+$message[29][0]="Access"; $message[29][1]="Accès"; $message[29][2]="Toegang"; $message[29][3]="Acceso";
+$message[30][0]="Other words"; $message[30][1]="Autres mots"; $message[30][2]="Andere woorden"; $message[30][3]="Otras palabras";
+$message[31][0]="Used browsers"; $message[31][1]="Navigateurs utilisés"; $message[31][2]="Gebruikte browsers"; $message[31][3]="Navegadores utilizados";
+$message[32][0]="HTTP Error codes"; $message[32][1]="Codes Erreurs HTTP"; $message[32][2]="HTTP foutmelding codes"; $message[32][3]="Códigos de Errores de Protocolo HTPP";
+$message[33][0]="Netscape versions<br><img src=\"$DirIcons/browser/netscape.png\">"; $message[33][1]="Versions de Netscape<br><img src=\"$DirIcons/browser/netscape.png\">"; $message[33][2]="Netscape versies<br><img src=\"$DirIcons/browser/netscape.png\">"; $message[33][3]="Versiones de Netscape<br><img src=\"$DirIcons/browser/netscape.png\">";
+$message[34][0]="MS Internet Explorer versions<br><img src=\"$DirIcons/browser/msie.png\">"; $message[34][1]="Versions de MS Internet Explorer<br><img src=\"$DirIcons/browser/msie.png\">"; $message[34][2]="MS Internet Explorer versies<br><img src=\"$DirIcons/browser/msie.png\">"; $message[34][3]="Versiones de MS Internet Explorer<br><img src=\"$DirIcons/browser/msie.png\">";
+$message[35][0]="Used OS"; $message[35][1]="Systèmes d'exploitation utilisés"; $message[35][2]="Gebruikt OS"; $message[35][3]="Sistemas Operativos utilizados";
+$message[36][0]="Connect to site from"; $message[36][1]="Connexions au site par"; $message[36][2]="Verbinding naar site vanaf"; $message[36][3]="Enlazado al sitio desde";
+$message[37][0]="Origin"; $message[37][1]="Origine de la connexion"; $message[37][2]="Herkomst"; $message[37][3]="Origen de enlace";
+$message[38][0]="Direct address / Bookmarks"; $message[38][1]="Adresse directe / Bookmarks"; $message[38][2]="Direkt adres / Bookmarks"; $message[38][3]="Dirección directa / Favoritos";
+$message[39][0]="Link from a Newsgroup"; $message[39][1]="Lien depuis un Newsgroup"; $message[39][2]="Link vanuit een nieuwsgroep"; $message[39][3]="Enlace desde Newsgroup";
+$message[40][0]="Link from an Internet Search Engine"; $message[40][1]="Lien depuis un moteur de recherche Internet"; $message[40][2]="Link vanuit een Internet Zoek Machine"; $message[40][3]="Enlace desde algún motor de búsqueda";
+$message[41][0]="Link from an external page (other web sites except search engines)"; $message[41][1]="Lien depuis une page externe (autres sites, hors moteurs de recherche)"; $message[41][2]="Link vanuit een externe pagina (andere web sites behalve zoek machines)"; $message[41][3]="Enlace desde página externa (exeptuando motores de búsqueda)";
+$message[42][0]="Link from an internal page (other page on same site)"; $message[42][1]="Lien depuis une page interne (autre page du site)"; $message[42][2]="Link vanuit een interne pagina (andere pagina van dezelfde site)"; $message[42][3]="Enlace desde página interna (otra página del sitio)";
+$message[43][0]="keywords used on search engines"; $message[43][1]="des critères de recherches utilisés"; $message[43][2]="gebruikte trefwoorden bij zoek machines"; $message[43][3]="Palabras clave utilizada por el motor de búsqueda";
+$message[44][0]="Kb"; $message[44][1]="Ko"; $message[44][2]="Kb"; $message[44][3]="Kb";
+$message[45][0]="Unresolved IP Address"; $message[45][1]="Adresses IP des visiteurs non identifiables (IP non résolue)"; $message[45][2]="niet vertaald IP Adres"; $message[45][3]="Dirección IP no identificada";
+$message[46][0]="Unknown OS (Referer field)"; $message[46][1]="OS non reconnus (champ referer brut)"; $message[46][2]="Onbekend OS (Referer veld)"; $message[46][3]="Sistema Operativo desconocido (campo de referencia)";
+$message[47][0]="Required but not found URLs (HTTP code 404)"; $message[47][1]="URLs du site demandées non trouvées (Code HTTP 404)"; $message[47][2]="Verplicht maar niet gvonden URLs (HTTP code 404)"; $message[47][3]="URLs necesarios pero no encontados (código 404 de protocolo HTTP)";
+$message[48][0]="IP Address"; $message[48][1]="Adresse IP"; $message[48][2]="IP Adres"; $message[48][3]="Dirección IP";
+$message[49][0]="Error Hits"; $message[49][1]="Hits en échec"; $message[49][2]="Fout Hits"; $message[49][3]="Hits erróneos";
+$message[50][0]="Unknown browsers (Referer field)"; $message[50][1]="Navigateurs non reconnus (champ referer brut)"; $message[50][2]="Onbekende browsers (Referer veld)"; $message[50][3]="Navegadores desconocidos (campo de referencia)";
+$message[51][0]="Visiting robots"; $message[51][1]="Robots visiteurs"; $message[51][2]="Bezoekende robots"; $message[51][3]="Visitas de Robots";
+$message[52][0]="visits/visitor"; $message[52][1]="visite/visiteur"; $message[52][2]="bezoeken/bezoeker"; $message[52][3]="Visitas/Visitantes";
+$message[53][0]="Robots/Spiders visitors"; $message[53][1]="Visiteurs Robots/Spiders"; $message[53][2]="Robots/Spiders bezoekers"; $message[53][3]="Visitas de Robots/Spiders (arañas de indexación)";
+$message[54][0]="Free realtime logfile analyzer for advanced web statistics"; $message[54][1]="Analyseur de log gratuit pour statistiques Web avancées"; $message[54][2]="Gratis realtime logbestand analyzer voor geavanceerde web statistieken"; $message[54][3]="Analizador gratuito de 'log' para estadísticas Web avanzadas";
+$message[55][0]="of"; $message[55][1]="sur"; $message[55][2]="van"; $message[55][3]="de";
+
+
+# ---------- Browser lists ----------------
+# ("browser id in lower case", "browser text")
+%BrowsersHash = (
+"netscape","<font color=blue>Netscape</font> <a href=\"$PROG.pl?action=browserdetail&lang=$Lang\">(Versions)</a>",
+"msie","<font color=blue>MS Internet Explorer</font> <a href=\"$PROG.pl?action=browserdetail&lang=$Lang\">(Versions)</a>",
+
+"libwww","LibWWW",
+"wget","Wget",
+"lynx","Lynx",
+"opera","Opera",
+"22acidownload","22AciDownload",
+"aol\\-iweng","AOL-Iweng",
+"amigavoyager","AmigaVoyager",
+"antfresco","ANT Fresco",
+"bpftp","BPFTP",
+"cyberdog","Cyberdog",
+"downloadagent","DownloadAgent",
+"ecatch", "eCatch",
+"emailsiphon","EmailSiphon",
+"friendlyspider","FriendlySpider",
+"getright","GetRight",
+"headdump","HeadDump",
+"hotjava","Sun HotJava",
+"ibrowse","IBrowse",
+"intergo","InterGO",
+"konqueror","Konqueror",
+"linemodebrowser","W3C Line Mode Browser",
+"lotus-notes","Lotus Notes web client",
+"macweb","MacWeb",
+"ncsa_mosaic","NCSA Mosaic",
+"nutscrape", "Nutscrape",
+"mspie","MS Pocket Internet Explorer",
+"msfrontpageexpress","MS FrontPage Express",
+"real","RealAudio or compatible player",
+"teleportpro","TelePortPro",
+"tzgeturl","TZGETURL",
+"viking","Viking",
+"webcapture","Aspirateur Acrobat",
+"webfetcher","WebFetcher",
+"webtv","WebTV browser",
+"webexplorer","IBM-WebExplorer",
+"webmirror","WebMirror",
+"webvcr","WebVCR",
+"webzip","WebZIP"
+);
+
+# ---------- OS lists --------------------
+
+# ("os id in lower case","os text")
+%OSHash = (
+"win16","Windows 3.xx",
+"win95","Windows 95",
+"win98","Windows 98",
+"winnt","Windows NT / Windows 2000",
+"wince","Windows CE",
+"cp/m","CPM",
+"sunos","Sun Solaris",
+"irix","Irix",
+"macintosh","MacOS",
+"unix","Unknown Unix system",
+"linux","Linux",
+"os/2","Warp OS/2",
+"osf","OSF Unix",
+"crayos","CrayOS",
+"amigaos","AmigaOS",
+"hp-ux","HP Unix",
+"riscos","Acorn RISC OS",
+"aix","Aix",
+"netbsd","NetBSD",
+"bsdi","BSDi",
+"freebsd","FreeBSD",
+"webtv","WebTV"
+);
+
+# ("text that match in log after changing space and plus into underscore","osid")
+%OSAlias = (
+"windows_98","win98",
+"windows_nt","winnt",
+"win32","winnt",
+"windows_95","win95",
+"windows_31","win16",
+"windows;i;16","win16",
+"windowsce","wince",
+"mac_powerpc","macintosh",
+"mac_ppc","macintosh",
+"mac_68000","macintosh",
+"macweb","macintosh"
+);
+
+
+# ---------- Robot lists ------------
+# List can be found at http://info.webcrawler.com/mak/projects/robots/active.html and the next command show how to generate tab list from this file:
+# cat robotslist.txt | sed 's/:/ /' | awk ' /robot-id/ { name=tolower($2); } /robot-name/ { print "\""name"\", \""$0"\"," } ' | sed 's/robot-name *//g' > file
+# Rem: To avoid bad detection, some robots id were removed from this list:
+# - Robots with ID of 2 letters only
+# - Robot called webs
+# Rem: directhit is renamed in direct_hit
+%RobotHash = (
+"acme.spider", "Acme.Spider",
+"ahoythehomepagefinder", "Ahoy! The Homepage Finder",
+"alkaline", "Alkaline",
+"appie", "Walhello appie",
+"arachnophilia", "Arachnophilia",
+"architext", "ArchitextSpider",
+"aretha", "Aretha",
+"ariadne", "ARIADNE",
+"aspider", "ASpider (Associative Spider)",
+"atn.txt", "ATN Worldwide",
+"atomz", "Atomz.com Search Robot",
+"auresys", "AURESYS",
+"backrub", "BackRub",
+"bigbrother", "Big Brother",
+"bjaaland", "Bjaaland",
+"blackwidow", "BlackWidow",
+"blindekuh", "Die Blinde Kuh",
+"bloodhound", "Bloodhound",
+"brightnet", "bright.net caching robot",
+"bspider", "BSpider",
+"cactvschemistryspider", "CACTVS Chemistry Spider",
+"calif", "Calif",
+"cassandra", "Cassandra",
+"cgireader", "Digimarc Marcspider/CGI",
+"checkbot", "Checkbot",
+"churl", "churl",
+"cmc", "CMC/0.01",
+"collective", "Collective",
+"combine", "Combine System",
+"conceptbot", "Conceptbot",
+"core", "Web Core / Roots",
+"cshkust", "CS-HKUST WISE: WWW Index and Search Engine",
+"cusco", "Cusco",
+"cyberspyder", "CyberSpyder Link Test",
+"deweb", "DeWeb(c) Katalog/Index",
+"dienstspider", "DienstSpider",
+"diibot", "Digital Integrity Robot",
+"direct_hit", "Direct Hit Grabber",
+"dnabot", "DNAbot",
+"download_express", "DownLoad Express",
+"dragonbot", "DragonBot",
+"dwcp", "DWCP (Dridus' Web Cataloging Project)",
+"ebiness", "EbiNess",
+"eit", "EIT Link Verifier Robot",
+"emacs", "Emacs-w3 Search Engine",
+"emcspider", "ananzi",
+"esther", "Esther",
+"evliyacelebi", "Evliya Celebi",
+"nzexplorer", "nzexplorer",
+"fdse", "Fluid Dynamics Search Engine robot",
+"felix", " Felix IDE",
+"ferret", "Wild Ferret Web Hopper #1, #2, #3",
+"fetchrover", "FetchRover",
+"fido", "fido",
+"finnish", "Hämähäkki",
+"fireball", "KIT-Fireball",
+"fish", "Fish search",
+"fouineur", "Fouineur",
+"francoroute", "Robot Francoroute",
+"freecrawl", "Freecrawl",
+"funnelweb", "FunnelWeb",
+"gazz", "gazz",
+"gcreep", "GCreep",
+"getbot", "GetBot",
+"geturl", "GetURL",
+"golem", "Golem",
+"googlebot", "Googlebot",
+"grapnel", "Grapnel/0.01 Experiment",
+"griffon", "Griffon ",
+"gromit", "Gromit",
+"gulliver", "Northern Light Gulliver",
+"hambot", "HamBot",
+"harvest", "Harvest",
+"havindex", "havIndex",
+"hometown", "Hometown Spider Pro",
+"wired-digital", "Wired Digital",
+"htdig", "ht://Dig",
+"htmlgobble", "HTMLgobble",
+"hyperdecontextualizer", "Hyper-Decontextualizer",
+"ibm", "IBM_Planetwide",
+"iconoclast", "Popular Iconoclast",
+"ilse", "Ingrid",
+"imagelock", "Imagelock ",
+"incywincy", "IncyWincy",
+"informant", "Informant",
+"infoseek", "InfoSeek Robot 1.0",
+"infoseeksidewinder", "Infoseek Sidewinder",
+"infospider", "InfoSpiders",
+"inspectorwww", "Inspector Web",
+"intelliagent", "IntelliAgent",
+"iron33", "Iron33",
+"israelisearch", "Israeli-search",
+"javabee", "JavaBee",
+"jcrawler", "JCrawler",
+"jeeves", "Jeeves",
+"jobot", "Jobot",
+"joebot", "JoeBot",
+"jubii", "The Jubii Indexing Robot",
+"jumpstation", "JumpStation",
+"katipo", "Katipo",
+"kdd", "KDD-Explorer",
+"kilroy", "Kilroy",
+"ko_yappo_robot", "KO_Yappo_Robot",
+"labelgrabber.txt", "LabelGrabber",
+"larbin", "larbin",
+"legs", "legs",
+"linkscan", "LinkScan",
+"linkwalker", "LinkWalker",
+"lockon", "Lockon",
+"logo_gif", "logo.gif Crawler",
+"lycos", "Lycos",
+"macworm", "Mac WWWWorm",
+"magpie", "Magpie",
+"mediafox", "MediaFox",
+"merzscope", "MerzScope",
+"meshexplorer", " NEC-MeshExplorer",
+"mindcrawler", "MindCrawler",
+"moget", "moget",
+"momspider", "MOMspider",
+"monster", "Monster",
+"motor", "Motor",
+"muscatferret", "Muscat Ferret",
+"mwdsearch", "Mwd.Search",
+"myweb", "Internet Shinchakubin",
+"netcarta", "NetCarta WebMap Engine",
+"netmechanic", "NetMechanic",
+"netscoop", "NetScoop",
+"newscan-online", "newscan-online",
+"nhse", "NHSE Web Forager",
+"nomad", "Nomad",
+"northstar", "The NorthStar Robot",
+"occam", "Occam",
+"octopus", "HKU WWW Octopus",
+"orb_search", "Orb Search",
+"packrat", "Pack Rat",
+"pageboy", "PageBoy",
+"parasite", "ParaSite",
+"patric", "Patric",
+"perignator", "The Peregrinator",
+"perlcrawler", "PerlCrawler 1.0",
+"phantom", "Phantom",
+"piltdownman", "PiltdownMan",
+"pioneer", "Pioneer",
+"pitkow", "html_analyzer",
+"pjspider", "Portal Juice Spider",
+"pka", "PGP Key Agent",
+"plumtreewebaccessor", "PlumtreeWebAccessor ",
+"poppi", "Poppi",
+"portalb", "PortalB Spider",
+"puu", "GetterroboPlus Puu",
+"python", "The Python Robot",
+"raven", "Raven Search",
+"rbse", "RBSE Spider",
+"resumerobot", "Resume Robot",
+"rhcs", "RoadHouse Crawling System",
+"roadrunner", "Road Runner: The ImageScape Robot",
+"robbie", "Robbie the Robot",
+"robi", "ComputingSite Robi/1.0",
+"roverbot", "Roverbot",
+"safetynetrobot", "SafetyNet Robot",
+"scooter", "Scooter",
+"search_au", "Search.Aus-AU.COM",
+"searchprocess", "SearchProcess",
+"senrigan", "Senrigan",
+"sgscout", "SG-Scout",
+"shaggy", "ShagSeeker",
+"shaihulud", "Shai'Hulud",
+"sift", "Sift",
+"simbot", "Simmany Robot Ver1.0",
+"site-valet", "Site Valet",
+"sitegrabber", "Open Text Index Robot",
+"sitetech", "SiteTech-Rover",
+"slurp", "Inktomi Slurp",
+"smartspider", "Smart Spider",
+"snooper", "Snooper",
+"solbot", "Solbot",
+"spanner", "Spanner",
+"speedy", "Speedy Spider",
+"spider_monkey", "spider_monkey",
+"spiderbot", "SpiderBot",
+"spiderman", "SpiderMan",
+"spry", "Spry Wizard Robot",
+"ssearcher", "Site Searcher",
+"suke", "Suke",
+"sven", "Sven",
+"tach_bw", "TACH Black Widow",
+"tarantula", "Tarantula",
+"tarspider", "tarspider",
+"tcl", "Tcl W3 Robot",
+"techbot", "TechBOT",
+"templeton", "Templeton",
+"titin", "TitIn",
+"titan", "TITAN",
+"tkwww", "The TkWWW Robot",
+"tlspider", "TLSpider",
+"ucsd", "UCSD Crawl",
+"udmsearch", "UdmSearch",
+"urlck", "URL Check",
+"valkyrie", "Valkyrie",
+"victoria", "Victoria",
+"visionsearch", "vision-search",
+"voyager", "Voyager",
+"vwbot", "VWbot",
+"w3index", "The NWI Robot",
+"w3m2", "W3M2",
+"wanderer", "the World Wide Web Wanderer",
+"webbandit", "WebBandit Web Spider",
+"webcatcher", "WebCatcher",
+"webcopy", "WebCopy",
+"webfetcher", "webfetcher",
+"webfoot", "The Webfoot Robot",
+"weblayers", "weblayers",
+"weblinker", "WebLinker",
+"webmirror", "WebMirror",
+"webmoose", "The Web Moose",
+"webquest", "WebQuest",
+"webreader", "Digimarc MarcSpider",
+"webreaper", "WebReaper",
+"websnarf", "Websnarf",
+"webspider", "WebSpider",
+"webvac", "WebVac",
+"webwalk", "webwalk",
+"webwalker", "WebWalker",
+"webwatch", "WebWatch",
+"wget", "Wget",
+"whowhere", "WhoWhere Robot",
+"wmir", "w3mir",
+"wolp", "WebStolperer",
+"wombat", "The Web Wombat ",
+"worm", "The World Wide Web Worm",
+"wwwc", "WWWC Ver 0.2.5",
+"wz101", "WebZinger",
+"xget", "XGET",
+"nederland.zoek", "Nederland.zoek",
+
+# Not declared robots
+"ezresult", "Ezresult (Not referenced robot)",
+"fast-webcrawler", "Fast-Webcrawler (Not referenced robot)",
+"perman surfer", "Perman surfer (Not referenced robot)",
+"mercator", "Mercator (Not referenced robot)",
+"antibot", "Antibot (Not referenced robot)",
+"daviesbot", "DaviesBot (Not referenced robot)",
+"unlost_web_crawler", "Unlost_Web_Crawler (Not referenced robot)",
+"justview", "JustView (Not referenced robot)",
+# Supposed to be robots
+"webcompass", "webcompass (Not referenced robot)",
+"digout4u", "digout4u (Not referenced robot)",
+"echo", "EchO! (Not referenced robot)",
+"voila", "Voila (Not referenced robot)",
+"boris", "Boris (Not referenced robot)",
+"ultraseek", "Ultraseek (Not referenced robot)",
+"ia_archiver", "ia_archiver (Not referenced robot)",
+# Generic detect ID
+"robot", "Unknown robot (Not referenced robot)"
+);
+
+# ---------- Search engine lists --------------------
+%SearchEnginesHash=(
+"excite\.","Excite", "yahoo\.","Yahoo", "altavista\.","AltaVista",
+"lycos\.","Lycos", "voila\.", "Voila", "infoseek\.","Infoseek", "google\.","Google",
+"webcrawler\.","WebCrawler", "lokace\.", "Lokace", "northernlight\.","NorthernLight", "hotbot\.","Hotbot",
+"metacrawler\.","MetaCrawler", "go2net\.com","Go2Net (Metamoteur)", "askjeeves\.","Ask Jeeves", "ctrouve\.","C'est trouvé",
+"euroseek\.","Euroseek", "francite\.","Francité", "\.lbb\.org", "LBB",
+"netscape\.","Netscape", "nomade\.fr/","Nomade",
+"msn\.dk/","MSN (dk)", "msn\.fr/","MSN (fr)", "msn\.","MSN", "nbci\.com/search","NBCI",
+"mamma\.","Mamma", "dejanews\.","DejaNews",
+"search\.terra\.","Terra", "snap\.","Snap",
+"netfind\.aol\.com","AOL", "recherche\.aol\.fr","AOL", "rechercher\.libertysurf\.fr","Libertysurf",
+"search\.com","Other search engines"
+);
+
+# ---------- Domains --------------------
+%DomainsHash = (
+"localhost","localhost",
+
+"ad","Andorra","ae","United Arab Emirates","af","Afghanistan","ag",
+"Antigua and Barbuda","ai","Anguilla","al","Albania","am",
+"Armenia","an","Netherlands Antilles","ao","Angola","aq",
+"Antarctica","ar","Argentina","arpa","Old style Arpanet","as",
+"American Samoa","at","Austria","au","Australia","aw","Aruba","az",
+"Azerbaidjan","ba","Bosnia-Herzegovina","bb","Barbados","bd",
+"Bangladesh","be","Belgium","bf","Burkina Faso","bg","Bulgaria",
+"bh","Bahrain","bi","Burundi","bj","Benin","bm","Bermuda","bn",
+"Brunei Darussalam","bo","Bolivia","br","Brazil","bs","Bahamas",
+"bt","Bhutan","bv","Bouvet Island","bw","Botswana","by","Belarus",
+"bz","Belize","ca","Canada","cc","Cocos (Keeling) Islands","cf",
+"Central African Republic","cg","Congo","ch","Switzerland","ci",
+"Ivory Coast (Cote D'Ivoire)","ck","Cook Islands","cl","Chile","cm","Cameroon",
+"cn","China","co","Colombia","com","Commercial","cr","Costa Rica",
+"cs","Former Czechoslovakia","cu","Cuba","cv","Cape Verde","cx",
+"Christmas Island","cy","Cyprus","cz","Czech Republic","de","Germany",
+"dj","Djibouti","dk","Denmark","dm","Dominica","do","Dominican Republic",
+"dz","Algeria","ec","Ecuador","edu","USA Educational","ee","Estonia",
+"eg","Egypt","eh","Western Sahara","es","Spain","et","Ethiopia","fi","Finland","fj","Fiji","fk",
+"Falkland Islands","fm","Micronesia","fo","Faroe Islands",
+"fr","France","fx","France (European Territory)","ga","Gabon","gb",
+"Great Britain","gd","Grenada","ge","Georgia","gf","French Guyana","gh","Ghana","gi","Gibraltar",
+"gl","Greenland","gm","Gambia","gn","Guinea","gov","USA Government","gp","Guadeloupe (French)","gq",
+"Equatorial Guinea","gr","Greece","gs","S. Georgia & S. Sandwich Isls.",
+"gt","Guatemala","gu","Guam (USA)","gw","Guinea Bissau","gy","Guyana",
+"hk","Hong Kong","hm","Heard and McDonald Islands","hn","Honduras","hr",
+"Croatia","ht","Haiti","hu","Hungary","id","Indonesia","ie","Ireland","il","Israel",
+"in","India","int","International","io","British Indian Ocean Territory",
+"iq","Iraq","ir","Iran","is","Iceland","it","Italy","jm",
+"Jamaica","jo","Jordan","jp","Japan","ke","Kenya","kg","Kyrgyzstan",
+"kh","Cambodia","ki","Kiribati","km","Comoros","kn","Saint Kitts & Nevis Anguilla",
+"kp","North Korea","kr","South Korea","kw","Kuwait","ky",
+"Cayman Islands","kz","Kazakhstan","la","Laos","lb","Lebanon","lc","Saint Lucia",
+"li","Liechtenstein","lk","Sri Lanka","lr","Liberia","ls","Lesotho","lt","Lithuania",
+"lu","Luxembourg","lv","Latvia","ly","Libya","ma","Morocco","mc","Monaco",
+"md","Moldavia","mg","Madagascar","mh","Marshall Islands","mil","USA Military","mk",
+"Macedonia","ml","Mali","mm","Myanmar","mn","Mongolia","mo","Macau",
+"mp","Northern Mariana Islands","mq","Martinique (French)","mr","Mauritania",
+"ms","Montserrat","mt","Malta","mu","Mauritius","mv","Maldives","mw",
+"Malawi","mx","Mexico","my","Malaysia","mz","Mozambique","na","Namibia","nato","NATO",
+"nc","New Caledonia (French)","ne","Niger","net","Network","nf","Norfolk Island",
+"ng","Nigeria","ni","Nicaragua","nl","Netherlands","no","Norway",
+"np","Nepal","nr","Nauru","nt","Neutral Zone","nu","Niue","nz","New Zealand","om","Oman","org",
+"Non-Profit Organizations","pa","Panama","pe","Peru","pf","Polynesia (French)",
+"pg","Papua New Guinea","ph","Philippines","pk","Pakistan","pl","Poland",
+"pm","Saint Pierre and Miquelon","pn","Pitcairn Island","pr",
+"Puerto Rico","pt","Portugal","pw","Palau","py","Paraguay","qa","Qatar",
+"re","Reunion (French)","ro","Romania","ru","Russian Federation","rw","Rwanda",
+"sa","Saudi Arabia","sb","Solomon Islands","sc","Seychelles","sd",
+"Sudan","se","Sweden","sg","Singapore","sh","Saint Helena","si","Slovenia",
+"sj","Svalbard and Jan Mayen Islands","sk","Slovak Republic","sl","Sierra Leone",
+"sm","San Marino","sn","Senegal","so","Somalia","sr","Suriname","st",
+"Saint Tome and Principe","su","Former USSR","sv","El Salvador","sy","Syria","sz","Swaziland","tc",
+"Turks and Caicos Islands","td","Chad","tf","French Southern Territories","tg","Togo",
+"th","Thailand","tj","Tadjikistan","tk","Tokelau","tm","Turkmenistan","tn","Tunisia",
+"to","Tonga","tp","East Timor","tr","Turkey","tt","Trinidad and Tobago","tv","Tuvalu",
+"tw","Taiwan","tz","Tanzania","ua","Ukraine","ug","Uganda","uk",
+"United Kingdom","um","USA Minor Outlying Islands","us","United States",
+"uy","Uruguay","uz","Uzbekistan","va","Vatican City State","vc",
+"Saint Vincent & Grenadines","ve","Venezuela","vg","Virgin Islands (British)",
+"vi","Virgin Islands (USA)","vn","Vietnam","vu","Vanuatu","wf","Wallis and Futuna Islands",
+"ws","Samoa","ye","Yemen","yt","Mayotte","yu","Yugoslavia","za","South Africa",
+"zm","Zambia","zr","Zaire","zw","Zimbabwe"
+);
+
+
+#-------------------------------------------------------
+# Functions
+#-------------------------------------------------------
+sub html_end {
+ $date=localtime();
+ print "<br><font size=1>$date - <b>Advanced Web Statistics $VERSION</b> - <a href=\"http://perso.wanadoo.fr/l.destailleur/awstats.html\" target=_newawstats>Visit $PROG official web page</a></font>\n";
+ if ($SponsorLinkVisible) {
+ print " - <a href=\"http://www.commission-junction.com/track/track.dll?AID=348418&PID=531902&URL=http%3A%2F%2Fwww%2Ecj%2Ecom\">";
+ print "Visit $PROG sponsor";
+ print "</a><img src=\"http://www.commission-junction.com/banners/tracker.exe?AID=348418&PID=531902&banner=0.gif\" height=1 width=1 border=0>";
+ }
+ print "<br><br>";
+ print "</body>";
+ print "</html>";
+ exit(0);
+}
+
+sub tab_head {
+ print "
+ <TABLE CLASS=TABLEBORDER BORDER=0 CELLPADDING=1 CELLSPACING=0 WIDTH=700>
+ <TR><TD>
+ <TABLE CLASS=TABLEFRAME BORDER=0 CELLPADDING=3 CELLSPACING=0 WIDTH=100%>
+ <TR><TH COLSPAN=2 CLASS=TABLETITLE>$tab_titre</TH></TR>
+ <TR><TD COLSPAN=2>
+ <TABLE CLASS=TABLEDATA BORDER=1 CELLPADDING=2 CELLSPACING=0 WIDTH=100%>
+ ";
+}
+
+sub tab_end {
+ print "</TABLE></TD></TR></TABLE>";
+ print "</TD></TR></TABLE>";
+}
+
+sub UnescapeURL {
+ $_[0] =~ s/\+/ /gi;
+ $_[0] =~ s/%20/ /gi; #
+ $_[0] =~ s/%22//gi; #"
+ $_[0] =~ s/%26/ /gi; #&
+ $_[0] =~ s/%27/ /gi; #'
+ $_[0] =~ s/%28//gi; #(
+ $_[0] =~ s/%29//gi; #)
+ $_[0] =~ s/%2b/ /gi; #+
+ $_[0] =~ s/%2c/ /gi; #,
+ $_[0] =~ s/%2d//gi; #-
+ $_[0] =~ s/%2f/ /gi; #/
+ $_[0] =~ s/%3c/ /gi; #<
+ $_[0] =~ s/%3d/ /gi; #=
+ $_[0] =~ s/%3e/ /gi; #>
+ $_[0] =~ s/%c9/é/gi; #é maj
+ $_[0] =~ s/%e8/è/gi; #è
+ $_[0] =~ s/%e9/é/gi; #é
+ $_[0] =~ s/%ea/ê/gi; #ê
+ $_[0] =~ s/%eb/ë/gi; #ë
+ $_[0] =~ s/%f1/ñ/gi; #ñ
+ $_[0] =~ s/%f2/ò/gi; #ò
+ $_[0] =~ s/%f3/ó/gi; #ó
+ $_[0] =~ s/[0-9]//gi; # $_[0] =~ s/^[0-9]*//gi; should be better but not tested yet
+ $_[0] =~ s/\"//gi;
+}
+
+sub error {
+ print "$_[0].<br><br>\n";
+ print "<font color=#880000><b>Setup ($PROG, web server or logfile permissions) may be wrong.</b></font><br>";
+ print "See README.TXT for informations on how to install $PROG.\n";
+ print "</BODY>\n";
+ print "</HTML>\n";
+ die;
+}
+
+sub warning {
+ if ($WarningMessages == 1) {
+ print "$_[0]<br>\n";
+ print "You can now suppress this warning by changing <b>\$WarningMessage=1</b> parameter into <b>\$WarningMessage=0</b> in <b>$PROG.pl</b> file.<br><br>\n";
+ }
+}
+
+sub SkipHost {
+ foreach $Skip (@SkipHosts) { if ($_[0] =~ m/$Skip/) { return 1; } }
+ 0; # Not in @SkipHosts
+}
+
+sub SkipFile {
+ foreach $Skip (@SkipFiles) { if ($_[0] =~ m/$Skip/i) { return 1; } }
+ 0; # Not inside @SkipFiles
+}
+
+sub Read_History_File {
+if (open(HISTORY,$fic)) {
+ $readdomain=0;$readvisitor=0;$readunknownip=0;$readsider=0;$readtime=0;$readbrowser=0;$readnsver=0;$readmsiever=0;
+ $reados=0;$readrobot=0;$readunknownreferer=0;$readunknownrefererbrowser=0;$readpagerefs=0;$readse=0;
+ $readsearchwords=0;$readerrors=0;$readerrors404=0;
+ $indic1{$_[0]}=0; $indic2{$_[0]}=0; $indic3{$_[0]}=0; $indic4{$_[0]}=0; $indic5{$_[0]}=0;
+ while (<HISTORY>) {
+ $_ =~ s/\n//; $saveline=$_;
+ @felter=split(/ /,$_);
+ if ($felter[0] eq "FirstTime") { $FirstTime=$felter[1]; next; }
+ if (($felter[0] eq "LastTime") && ($LastTime eq 0)) { $LastTime=$felter[1]; next; }
+ if ($felter[0] eq "TotalVisits") { $TotalVisits+=$felter[1]; $indic1{$_[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_DOMAIN") { $readdomain=1; next; }
+ if ($felter[0] eq "END_DOMAIN") { $readdomain=0; next; }
+ if ($readdomain) {
+ $domener_p{$felter[0]}+=$felter[1];
+ $domener_h{$felter[0]}+=$felter[2];
+ $domener_k{$felter[0]}+=$felter[3];
+ next; }
+
+ if ($felter[0] eq "BEGIN_VISITOR") { $readvisitor=1; next; }
+ if ($felter[0] eq "END_VISITOR") { $readvisitor=0; next; }
+ if ($readvisitor) {
+ $hostmachine_p{$felter[0]}+=$felter[1];
+ $hostmachine_h{$felter[0]}+=$felter[2];
+ $hostmachine_k{$felter[0]}+=$felter[3];
+ $hostmachine_l{$felter[0]}=$felter[4];
+ if (($felter[0] ne "Unknown") && ($hostmachine_p{$felter[0]} > 0)) { $indic2{$_[0]}++; }
+ next; }
+ if ($felter[0] eq "BEGIN_UNKNOWNIP") { $readunknownip=1; next; }
+ if ($felter[0] eq "END_UNKNOWNIP") { $readunknownip=0; next; }
+ if ($readunknownip) {
+ if ($unknownip_l{$felter[0]} eq "") { $unknownip_l{$felter[0]}=$felter[1]; }
+ $indic2{$_[0]}++;
+ next; }
+
+ if ($felter[0] eq "BEGIN_SIDER") { $readsider=1; next; }
+ if ($felter[0] eq "END_SIDER") { $readsider=0; next; }
+ if ($readsider) { $sider_p{$felter[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_TIME") { $readtime=1; next; }
+ if ($felter[0] eq "END_TIME") { $readtime=0; next; }
+ if ($readtime) {
+ $time_p[$felter[0]]+=$felter[1]; $time_h[$felter[0]]+=$felter[2]; $time_k[$felter[0]]+=$felter[3];
+ $indic3{$_[0]}+=$felter[1]; $indic4{$_[0]}+=$felter[2]; $indic5{$_[0]}+=$felter[3];
+ next; }
+
+ if ($felter[0] eq "BEGIN_BROWSER") { $readbrowser=1; next; }
+ if ($felter[0] eq "END_BROWSER") { $readbrowser=0; next; }
+ if ($readbrowser) { $browser{$felter[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_NSVER") { $readnsver=1; next; }
+ if ($felter[0] eq "END_NSVER") { $readnsver=0; next; }
+ if ($readnsver) { $nsver[$felter[0]]+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_MSIEVER") { $readmsiever=1; next; }
+ if ($felter[0] eq "END_MSIEVER") { $readmsiever=0; next; }
+ if ($readmsiever) { $msiever[$felter[0]]+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_OS") { $reados=1; next; }
+ if ($felter[0] eq "END_OS") { $reados=0; next; }
+ if ($reados) { $OS{$felter[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_ROBOT") { $readrobot=1; next; }
+ if ($felter[0] eq "END_ROBOT") { $readrobot=0; next; }
+ if ($readrobot) {
+ if ($robot_l{$felter[0]} eq "") { $robot_l{$felter[0]}=$felter[2]; }
+ $robot{$felter[0]}+=$felter[1];
+ next; }
+
+ if ($felter[0] eq "BEGIN_UNKNOWNREFERER") { $readunknownreferer=1; next; }
+ if ($felter[0] eq "END_UNKNOWNREFERER") { $readunknownreferer=0; next; }
+ if ($readunknownreferer) {
+ if ($unknownreferer_l{$felter[0]} eq "") { $unknownreferer_l{$felter[0]}=$felter[1]; }
+ next; }
+ if ($felter[0] eq "BEGIN_UNKNOWNREFERERBROWSER") { $readunknownrefererbrowser=1; next; }
+ if ($felter[0] eq "END_UNKNOWNREFERERBROWSER") { $readunknownrefererbrowser=0; next; }
+ if ($readunknownrefererbrowser) {
+ if ($unknownrefererbrowser_l{$felter[0]} eq "") { $unknownrefererbrowser_l{$felter[0]}=$felter[1]; }
+ next; }
+
+ if ($felter[0] eq "HitFrom0") { $HitFrom[0]+=$felter[1]; next; }
+ if ($felter[0] eq "HitFrom1") { $HitFrom[1]+=$felter[1]; next; }
+ if ($felter[0] eq "HitFrom2") { $HitFrom[2]+=$felter[1]; next; }
+ if ($felter[0] eq "HitFrom3") { $HitFrom[3]+=$felter[1]; next; }
+ if ($felter[0] eq "HitFrom4") { $HitFrom[4]+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_PAGEREFS") { $readpagerefs=1; next; }
+ if ($felter[0] eq "END_PAGEREFS") { $readpagerefs=0; next; }
+ if ($readpagerefs) { $PageRefs{$felter[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_SEREFERRALS") { $readse=1; next; }
+ if ($felter[0] eq "END_SEREFERRALS") { $readse=0; next; }
+ if ($readse) { $SEReferrals{$felter[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_SEARCHWORDS") { $readsearchwords=1; next; }
+ if ($felter[0] eq "END_SEARCHWORDS") { $readsearchwords=0; next; }
+ if ($readsearchwords) { $searchwords{$felter[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_ERRORS") { $readerrors=1; next; }
+ if ($felter[0] eq "END_ERRORS") { $readerrors=0; next; }
+ if ($readerrors) { $errors{$felter[0]}+=$felter[1]; next; }
+
+ if ($felter[0] eq "BEGIN_SIDER_404") { $readerrors404=1; next; }
+ if ($felter[0] eq "END_SIDER_404") { $readerrors404=0; next; }
+ if ($readerrors404) { $sider404{$felter[0]}+=$felter[1]; next; }
+ }
+ }
+close HISTORY;
+}
+
+
+# For my own test
+if ($ENV{"SERVER_NAME"} eq "athena" || $ARGV[0] eq "athena") {
+$LogFile = "C:\\WINNT\\system32\\LogFiles\\W3SVC1\\ex";
+#$LogFile = "C:\\TEMP\\test.log";
+$LogFormat = 2; }
+if ($ENV{"SERVER_NAME"} eq "chiensderace.com" || $ARGV[0] eq "chiensderace.com") {
+$ArchiveLogRecords = 1;
+@SkipFiles= ("\\.css","\\.js","\\.class","robots\\.txt","/~","accueil\\.htm","sommaire\\.htm","barre\\.htm","menu\\.shtml","menu_","onglet_");
+@HostAliases= ("chiensderaces.com","www.chiensderaces.com");
+$LogFile = "/export/home/wwwroot/nicoboy/logs/chiensderace_access_log";
+$DirIcons="/icon"; }
+if ($ENV{"SERVER_NAME"} eq "reference" || $ARGV[0] eq "reference") {
+@HostAliases= ("163.84.167.24","163.84.92.240","refoptimia","referenc");
+$LogFile = "/usr/local/apache/logs/reference.access_log"; }
+if ($ENV{"SERVER_NAME"} eq "www.partenor.com" || $ARGV[0] eq "www.partenor.com") {
+$ArchiveLogRecords = 1;
+@SkipHosts= ("10.0.0.");
+@SkipFiles= ("\\.css","\\.js","\\.class","robots\\.txt","/~","sommaire\\.htm","barre\\.htm","menu_","onglet_");
+@HostAliases= ("ftp.partenor.com");
+$LogFile = "/var/log/httpd/www.partenor.com-access_log"; }
+
+
+#-------------------------------------------------------
+# MAIN
+#-------------------------------------------------------
+if ($DNSLookup) { use Socket; }
+
+$LocalSite = $ENV{"SERVER_NAME"};if ($LocalSite eq "") { $LocalSite=$ARGV[0] }; $LocalSite =~ tr/A-Z/a-z/;
+$LocalSiteWithoutwww = $LocalSite; $LocalSiteWithoutwww =~ s/www\.//;
+if ($ARGV[0] eq "-h" || $ARGV[0] eq "-?" || $ARGV[0] eq "--help") {
+ print "----- $PROG $VERSION (c) laurent.destailleur\@wanadoo.fr -----\n";
+ print "$PROG is a free Web server logfile analyzer (in Perl) working as CGI to show\n";
+ print "advanced web statistics. Now supports/detects :\n";
+ print " Visits and unique visitors\n";
+ print " Rush hours\n";
+ print " Most often viewed pages\n";
+ @DomainsArray=keys %DomainsHash;
+ print " ".(@DomainsArray)." domains/countries\n";
+ @BrowserArray=keys %BrowsersHash;
+ print " ".(@BrowserArray)." browsers\n";
+ @OSArray=keys %OSHash;
+ print " ".(@OSArray)." Operating Systems\n";
+ @RobotArray=keys %RobotHash;
+ print " ".(@RobotArray)." robots\n";
+ @SearchEnginesArray=keys %SearchEnginesHash;
+ print " ".(@SearchEnginesArray)." search engines to detect referrer\n";
+ print " ".(@SearchEnginesArray)." search engines to detect keywords\n";
+ print "See README.TXT for setup.\n";
+ print "New versions and support at http://perso.wanadoo.fr/l.destailleur/awstats.html\n";
+ exit 0
+ }
+if ($LocalSite eq "") {
+ print "----- $PROG $VERSION (c) laurent.destailleur\@wanadoo.fr -----\n";
+ print "Syntax: $PROG.pl www.myservername Run $PROG from command line, not as CGI\n";
+ print " $PROG.pl -h Quick features (Read README.TXT for help)\n";
+ print "New versions and support at http://perso.wanadoo.fr/l.destailleur/awstats.html\n";
+ exit 0
+ }
+
+# Send HTTP/HTML Header
+if ($ENV{"GATEWAY_INTERFACE"} ne "") { print("Content-type: text/html\n\n\n"); }
+print "<html>\n";
+print "<head>\n";
+print "<meta http-equiv=\"description\" content=\"$PROG - Advanced Web Statistics of $LocalSite\">\n";
+print "<meta http-equiv=\"keywords\" content=\"$LocalSite, free, advanced, realtime, web, server, logfile, log, analyzer, analysis, statistics, stats, perl, analyse, performance, hits, visits\">\n";
+print "<meta name=\"robots\" content=\"index,follow\">\n";
+print "<title>$message[7][$Lang] $LocalSite</title>\n";
+print "</head>\n";
+print "<body>\n";
+
+print "<center><br>\n";
+print "<font size=2><b>AWStats</b></font><br>";
+print "<a href=\"http://perso.wanadoo.fr/l.destailleur/awstats.html\" target=_newawstats><img src=$DirIcons/other/$Logo border=0 alt=\"$PROG Official Web Site\"></a><br>\n";
+print "<a href=\"$PROG.pl?lang=0\"><img src=\"$DirIcons\/flags\/us.png\" height=14 border=0></a> <a href=\"$PROG.pl?lang=1\"><img src=\"$DirIcons\/flags\/fr.png\" height=14 border=0></a> <a href=\"$PROG.pl?lang=2\"><img src=\"$DirIcons\/flags\/nl.png\" height=14 border=0></a> <a href=\"$PROG.pl?lang=3\"><img src=\"$DirIcons\/flags\/es.png\" height=14 border=0></a><br>\n";
+print "<font size=1>$message[54][$Lang]</font><br>\n";
+print "<font name=Arial size=-2>\n";
+print "<BR><BR>\n";
+print "<STYLE TYPE=text/css>\n
+<!--
+ BODY { font-align: font-family: arial, verdana, helvetica, sans-serif; font-size: 10px; background-color:$color_Background; }
+ TD,TH { font-family: arial, verdana, helvetica, sans-serif; font-size: 10px; }
+ A { font-family: arial, verdana helvetica, sans-serif; font-size: 10px; font-style: normal; color: $color_link; }
+ DIV { text-align: justify; }
+ .TABLEBORDER { background-color:$color_TableBorder; }
+ .TABLEFRAME { background-color:$color_TableBG; }
+ .TABLEDATA { background-color:$color_Background; }
+ .TABLETITLE { font-family: verdana, arial, helvetica, sans-serif; font-size: 14px; font-weight:bold; color: $color_TableTitle; background-color:$color_TableBGTitle; }
+ .classTooltip { position:absolute; top:0px; left:0px; z-index:2; width: 280; visibility:hidden; font: 8pt MS Comic Sans,arial,sans-serif; background-color:#FFFFE6; padding:10px 10px; border: 1px solid black; }
+//-->
+</STYLE>\n
+";
+
+# INIT
+#------------------------------------------
+($sec,$min,$hour,$day,$month,$year,$wday,$yday,$isdst) = localtime(time);
+if ($year < 100) { $year+=2000; } else { $year+=1900; }
+$smallyear=$year;$smallyear =~ s/^..//;
+$month++;if ($month < 10) { $month = "0$month"; }
+foreach $Host (@SkipHosts) { if ($Host eq "") { die "Error: undefined SkipHosts. Put a value.\n"; } }
+foreach $Host (@SkipFiles) { if ($Host eq "") { die "Error: undefined SkipFiles. Put a value.\n"; } }
+foreach $HostAlias (@HostAliases) { if ($HostAlias eq "") { die "Error: undefined HostAliases. Put a value.\n"; } }
+$FirstTime=0;$LastTime=0;$TotalVisits=0;$TotalUnique=0;$TotalDifferentPages=0;$TotalDifferentKeywords=0;$TotalKeywords=0;
+for ($ix=0; $ix<5; $ix++) { $HitFrom[$ix]=0; }
+
+
+#------------------------------------------
+# READING CURRENT MONTH HISTORY FILE
+#------------------------------------------
+$fic="$DIR$PROG$month$year.txt";
+&Read_History_File($month);
+
+
+#------------------------------------------
+# PROCESSING CURRENT LOG
+#------------------------------------------
+if ($BenchMark == 1) {
+ ($secbench,$minbench,$hourbench,$daybench,$monthbench,$yearbench,$wdaybench,$ydaybench,$isdstbench) = localtime(time);
+ print "Start of processing log file: $hourbench:$minbench:$secbench<br>";
+ }
+# Try with $LogFile (If not found try $LogFile$smallyear$month.log and then $LogFile$smallyear$month$day.log)
+$OpenFileError=1; if (open(LOG,"$LogFile")) { $OpenFileError=0; }
+if ($OpenFileError) { if (open(LOG,"$LogFile$smallyear$month.log")) { $LogFile="$LogFile$smallyear$month.log"; $OpenFileError=0; } }
+if ($OpenFileError) { if (open(LOG,"$LogFile$smallyear$month$day.log")) { $LogFile="$LogFile$smallyear$month$day.log"; $OpenFileError=0; } }
+if ($OpenFileError) { error("Error: Couldn't open server log file <b>$LogFile</b>: $!"); }
+while (<LOG>)
+{
+ # Get log line
+ #-------------
+ $line=$_;
+ $_ =~ s/\n//; # Needed because IIS log file end with CRLF and perl read lines until LF
+ $_ =~ s/\" / /g; $_ =~ s/ \"/ /g; $_ =~ s/\"$//; # Suppress "
+ if ($LogFormat == 2) {
+ if (/^#/) { next; } # ISS writes such comments, we forget line
+ @felter=split(/ /,$_);
+ # Change order of ISS parameters to be like Apache
+ $savedate=$felter[0];$savetime=$felter[1];
+ $felter[0]=$felter[2];
+ $felter[1]="-";
+ $felter[2]=$felter[3];
+ @datep=split(/-/,$savedate); #Day:MM:YY:Hour:Min:Sec
+ $felter[3]="[$datep[2]/$datep[1]/$datep[0]:$savetime";
+ $felter[11]=$felter[9];
+ $felter[9]=$felter[7];
+ $felter[7]=$felter[8];
+ $felter[8]=$felter[6];
+ $felter[6]=$felter[5];
+ $felter[5]=$felter[4];
+ $felter[4]="+0000]";
+ #print "$felter[0] $felter[1] $felter[2] $felter[3] $felter[4] $felter[5] $felter[6] $felter[7] $felter[8] $felter[9] $felter[10] $felter[11]<br>";
+ }
+ else {
+ $_ =~ s/ GET .* .* HTTP\// GET BAD_URL HTTP\//; # Change ' GET x y z HTTP/' into ' GET x%20y%20z HTTP/'
+ @felter=split(/ /,$_);
+ }
+
+ # Check filters (here, log is in apache combined format, even with IIS)
+ #----------------------------------------------------------------------
+ if ($felter[5] eq 'HEAD') { next; } # Keep only GET, POST, OPTIONS but not HEAD
+ if ($felter[11] eq "") { next; } # Apache sometines forget some fields, ISS sometimes write blank lines
+ if ($felter[6] =~ /^RC=/) { next; } # A strange log record we need to forget
+
+ $felter[3] =~ s/\//:/g;
+ $felter[3] =~ s/\[//;
+ @dateparts=split(/:/,$felter[3]); # Split DD:Month:YYYY:HH:MM:SS
+ if ( $monthnum{$dateparts[1]} ) { $dateparts[1]=$monthnum{$dateparts[1]}; } # Change lib month in num month if necessary
+ $timeconnexion=$dateparts[2].$dateparts[1].$dateparts[0].$dateparts[3].$dateparts[4].$dateparts[5]; # YYYYMMDDHHMMSS
+ if ($timeconnexion <= $LastTime) { next; } # Skip if not a new line
+
+ if (&SkipHost($felter[0])) { next; } # Skip with some client host IP address
+ if (&SkipFile($felter[6])) { next; } # Skip with some URL
+ if (($felter[8] != 200) && ($felter[8] != 304)) { # Stop if HTTP server return code != 200 and 304
+ if ($felter[8] =~ /^[\d][\d][\d]$/) { # Keep error code
+ $errors{$felter[8]}++;
+ if ($felter[8] == 404) { $sider404{$felter[6]}++; }
+ next;
+ }
+ print "Log file <b>$LogFile</b> doesn't seem to have good format. Suspect line is<br>";
+ print "<font color=#888888><i>$line</i></font><br>";
+ print "<br><b>LogFormat</b> parameter is <b>$LogFormat</b>, this means each line in your log file need to have ";
+ if ($LogFormat == 2) {
+ print "<b>\"MSIE Extended W3C log format\"</b> like this:<br>";
+ print "<font color=#888888><i>date time c-ip c-username cs-method cs-uri-sterm cs-status cs-bytes cs-version cs(User-Agent) cs(Referer)</i></font><br>"
+ }
+ else {
+ print "<b>\"combined log format\"</b> like this:<br>";
+ print "<font color=#888888><i>62.161.78.73 - - [19/Jul/2000:02:14:14 +0200] \"GET / HTTP/1.1\" 200 1234 \"http://www.fromserver.com/from.htm\" \"Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)\"</i></font><br>";
+ }
+ error("<br>");
+ }
+
+ # Record is approved. Start of line process
+ if ($LogFormat == 1) {
+ # To correct bad format of some old apache log (field 10 is twice in line)
+# if ($felter[10] =~ /^$felter[11],/) {
+# for ($ix=12; $ix<=$#felter; $ix++) { $felter[$ix-1] = $felter[$ix]; }
+# }
+ # Define $UserAgent in one string (no ' ') like "Mozilla/4.0_(compatible;_MSIE_4.01;_Windows_98)"
+ for ($ix=12; $ix<=$#felter; $ix++) {
+ $felter[11] .= "_"; $felter[11] .= $felter[$ix];
+ }
+ }
+
+ $felter[11] =~ s/\+/_/g;
+ $UserAgent = $felter[11];
+ $UserAgent =~ tr/A-Z/a-z/;
+
+ # Robot ? If yes, we stop here
+ #-----------------------------
+ $foundrobot=0;
+ if (!$TmpHashNotRobot{$UserAgent}) { # TmpHashNotRobot is a temporary hash table to increase speed
+ foreach $bot (keys %RobotHash) { if ($UserAgent =~ /$bot/) { $robot{$bot}++; $robot_l{$bot}=$timeconnexion ; $foundrobot=1; last; } }
+ if ($foundrobot == 1) { next; }
+ $TmpHashNotRobot{$UserAgent}=1; # Last time, we won't search if robot or not. We know it's not.
+ }
+
+ # Canonize and clean target URL and referrer URL
+ $felter[6] =~ s/\/$DefaultFile$/\//; # Replace default page name with / only
+ $felter[6] =~ s/\?.*//; # Trunc CGI parameters in URL get
+ $felter[6] =~ s/\/\//\//g; # Because some targeted url were taped with 2 / (Ex: //rep//file.htm)
+
+ # Check if page or not
+ $PageBool=1;
+ foreach $cursor (@NotPageList) { if ($felter[6] =~ /$cursor$/) { $PageBool=0; last; } }
+
+ # Analyze: Date - Hour - Pages - Hits - Kilo
+ #-------------------------------------------
+ if ($FirstTime eq 0) { $FirstTime=$dateparts[2].$dateparts[1].$dateparts[0].$dateparts[3].$dateparts[4].$dateparts[5]; }
+ if ($PageBool) {
+ $time_p[$dateparts[3]]++; $indic3{$month}++; #Count accesses per hour (page)
+ $sider_p{$felter[6]}++; #Count accesses per page (page)
+ }
+ $time_h[$dateparts[3]]++; $indic4{$month}++; #Count accesses per hour (hit)
+ $time_k[$dateparts[3]]+=$felter[9]; $indic5{$month}++; #Count accesses per hour (kb)
+ $sider_h{$felter[6]}++; #Count accesses per page (hit)
+ $sider_k{$felter[6]}+=$felter[9]; #Count accesses per page (kb)
+
+ # Analyze: IP-address
+ #--------------------
+ $found=0;
+ $Host=$felter[0];
+ if ($Host =~ /^[\d]+\.[\d]+\.[\d]+\.[\d]+$/) {
+ # Doing DNS lookup
+ if ($DNSLookup) {
+ $new=$TmpHashDNSLookup{$Host}; # TmpHashDNSLookup is a temporary hash table to increase speed
+ if (!$new) { # if $new undefined, $Host not yet resolved
+ $new=gethostbyaddr(pack("C4",split(/\./,$Host)),AF_INET); # This is very slow may took 20 seconds
+ if ($new eq "") { $new="ip"; }
+ $TmpHashDNSLookup{$Host}=$new;
+ }
+
+ # Here $Host is still xxx.xxx.xxx.xxx and $new is name or "ip" if reverse failed)
+ if ($new ne "ip") { $Host=$new; }
+ }
+ # If we're not doing lookup or if it failed, we still have an IP address in $Host
+ if (!$DNSLookup || $new eq "ip") {
+ if ($PageBool) {
+ if (int($timeconnexion) > int($unknownip_l{$Host}+$VisitTimeOut)) { $TotalVisits++; $indic1{$month}++; }
+ if ($unknownip_l{$Host} eq "") { $indic2{$month}++; }
+ $unknownip_l{$Host}=$timeconnexion; # Table of (all IP if !DNSLookup) or (all unknown IP) else
+ $hostmachine_p{"Unknown"}++;
+ $domener_p{"ip"}++;
+ }
+ $hostmachine_h{"Unknown"}++;
+ $domener_h{"ip"}++;
+ $hostmachine_k{"Unknown"}+=$felter[9];
+ $domener_k{"ip"}+=$felter[9];
+ $found=1;
+ }
+ }
+
+ # Here, $Host = hostname or xxx.xxx.xxx.xxx
+ if (!$found) { # If not processed yet ($Host = hostname)
+ $Host =~ tr/A-Z/a-z/;
+ $_ = $Host;
+
+ # Count hostmachine
+ if (!$FullHostName) { s/^[\w\-]+\.//; };
+ if ($PageBool) {
+ if (int($timeconnexion) > int($hostmachine_l{$_}+$VisitTimeOut)) { $TotalVisits++; $indic1{$month}++; }
+ if ($hostmachine_l{$_} eq "") { $indic2{$month}++; }
+ $hostmachine_p{$_}++;
+ $hostmachine_l{$_}=$timeconnexion;
+ }
+ $hostmachine_h{$_}++;
+ $hostmachine_k{$_}+=$felter[9];
+
+ # Count top-level domain
+ if (/\./) { /\.([\w]+)$/; $_=$1; };
+ if ($DomainsHash{$_}) {
+ if ($PageBool) { $domener_p{$_}++; }
+ $domener_h{$_}++;
+ $domener_k{$_}+=$felter[9];
+ }
+ else {
+ if ($PageBool) { $domener_p{"ip"}++; }
+ $domener_h{"ip"}++;
+ $domener_k{"ip"}+=$felter[9];
+ }
+ }
+
+ # Analyze: Browser
+ #-----------------
+ $found=0;
+
+ # IE ? (For higher speed, we start whith IE, the most often used. This avoid other tests if found)
+ if ($UserAgent =~ /msie/ && !($UserAgent =~ /webtv/)) {
+ $browser{"msie"}++;
+ $UserAgent =~ /msie_(\d)\./; # $1 now contains major version no
+ $msiever[$1]++;
+ $found=1;
+ }
+
+ # Netscape ?
+ if (!$found) {
+ if ($UserAgent =~ /mozilla/ && !($UserAgent =~ /compatible/)) {
+ $browser{"netscape"}++;
+ $UserAgent =~ /\/(\d)\./; # $1 now contains major version no
+ $nsver[$1]++;
+ $found=1;
+ }
+ }
+
+ # Other ?
+ if (!$found) {
+ foreach $key (keys %BrowsersHash) {
+ if ($UserAgent =~ /$key/) { $browser{$key}++; $found=1; last; }
+ }
+ }
+
+ # Unknown browser ?
+ if (!$found) { $browser{"Unknown"}++; $unknownrefererbrowser_l{$felter[11]}=$timeconnexion; }
+
+ # Analyze: OS
+ #------------
+ $found=0;
+ if (!$TmpHashOS{$UserAgent}) {
+ # OSHash list ?
+ foreach $key (keys %OSHash) {
+ if ($UserAgent =~ /$key/) { $OS{$key}++; $found=1; $TmpHashOS{$UserAgent}=$key; last; }
+ }
+ # OSAlias list ?
+ if (!$found) {
+ foreach $key (keys %OSAlias) {
+ if ($UserAgent =~ /$key/) { $OS{$OSAlias{$key}}++; $found=1; $TmpHashOS{$UserAgent}=$OSAlias{$key}; last; }
+ }
+ }
+ # Unknown OS ?
+ if (!$found) { $OS{"Unknown"}++; $unknownreferer_l{$felter[11]}=$timeconnexion; }
+ }
+ else {
+ $OS{$TmpHashOS{$UserAgent}}++;
+ }
+
+ # Analyze: Referrer
+ #------------------
+ $found=0;
+
+ # Direct ?
+ if ($felter[10] eq "-") { $HitFrom[0]++; $found=1; }
+
+ # HTML link ?
+ if (!$found) {
+ if ($felter[10] =~ /^http/) {
+ $internal_link=0;
+ if (($felter[10] =~ /^http:\/\/www.$LocalSiteWithoutwww/i) || ($felter[10] =~ /^http:\/\/$LocalSiteWithoutwww/i)) { $internal_link=1; }
+ else {
+ foreach $HostAlias (@HostAliases) {
+ if ($felter[10] =~ /^http:\/\/$HostAlias/) { $internal_link=1; last; }
+ }
+ }
+
+ if ($internal_link) {
+ # Intern (This hit came from another page of the site)
+ $HitFrom[4]++;
+ $found=1;
+ }
+ else {
+ # Extern (This hit came from an external web site)
+ @refurl=split(/\?/,$felter[10]);
+ $refurl[0] =~ tr/A-Z/a-z/;
+ foreach $key (keys %SearchEnginesHash) {
+ if ($refurl[0] =~ /$key/) {
+ # This hit came from a search engine
+ $HitFrom[2]++;
+ $SEReferrals{$key}++;
+ # Extract keywords
+ $refurl[1] =~ tr/A-Z/a-z/;
+ @paramlist=split(/&/,$refurl[1]);
+ foreach $param (@paramlist) {
+ $keep=1;
+ &UnescapeURL($param); # Change xxx=aaa+bbb/ccc+ddd%20eee'fff into xxx=aaa bbb ccc ddd eee fff
+ foreach $paramtoexclude (@WordsToCleanSearchUrl) {
+ if ($param =~ /.*$paramtoexclude.*/i) { $keep=0; last; } # Not the param with search criteria
+ }
+ if ($keep == 0) { next; } # Do not keep this URL parameter because is in exclude list
+ # Ok. xxx=aaa bbb ccc ddd eee fff is a search parameter line
+ $param =~ s/.*=//g; # Cut chars xxx=
+ @wordlist=split(/ /,$param); # Split aaa bbb ccc ddd eee fff into a wordlist array
+ foreach $word (@wordlist) {
+ if ((length $word) > 2) { $searchwords{$word}++; } # Keep word only if word length is 3 or more
+ }
+ }
+ $found=1;
+ last;
+ }
+ }
+ if (!$found) {
+ # This hit came from a site other than a search engine
+ $HitFrom[3]++;
+ $PageRefs{$felter[10]}++;
+ $found=1;
+ }
+ }
+ }
+ }
+
+ # News link ?
+ if (!$found) {
+ if ($felter[10] =~ /^news/) {
+ $HitFrom[1]++;
+ $found=1;
+ }
+ }
+
+}
+close LOG;
+if ($BenchMark == 1) {
+ ($secbench,$minbench,$hourbench,$daybench,$monthbench,$yearbench,$wdaybench,$ydaybench,$isdstbench) = localtime(time);
+ print "End of processing log file: $hourbench:$minbench:$secbench<br>";
+ }
+if ($dateparts[0]) { $LastTime = $dateparts[2].$dateparts[1].$dateparts[0].$dateparts[3].$dateparts[4].$dateparts[5]; }
+
+
+#---------------------------
+# SAVING NEW CURRENT MONTH
+#---------------------------
+
+open(HISTORYTMP,">$DIR$PROG$month$year.tmp.$$") || error("Couldn't open file $DIR$PROG$month$year.tmp.$$: $!");
+
+print HISTORYTMP "FirstTime $FirstTime\n";
+print HISTORYTMP "LastTime $LastTime\n";
+
+print HISTORYTMP "TotalVisits $TotalVisits\n";
+
+print HISTORYTMP "BEGIN_DOMAIN\n";
+foreach $key (keys %domener_h) {
+ $page=$domener_p{$key};$kilo=$domener_k{$key};
+ if ($page == "") {$page=0;}
+ if ($kilo == "") {$kilo=0;}
+ print HISTORYTMP "$key $page $domener_h{$key} $kilo\n"; next;
+ }
+print HISTORYTMP "END_DOMAIN\n";
+
+print HISTORYTMP "BEGIN_VISITOR\n";
+foreach $key (keys %hostmachine_h) {
+ $page=$hostmachine_p{$key};$kilo=$hostmachine_k{$key};
+ if ($page == "") {$page=0;}
+ if ($kilo == "") {$kilo=0;}
+ print HISTORYTMP "$key $page $hostmachine_h{$key} $kilo $hostmachine_l{$key}\n"; next;
+ }
+print HISTORYTMP "END_VISITOR\n";
+
+print HISTORYTMP "BEGIN_UNKNOWNIP\n";
+foreach $key (keys %unknownip_l) { print HISTORYTMP "$key $unknownip_l{$key}\n"; next; }
+print HISTORYTMP "END_UNKNOWNIP\n";
+
+print HISTORYTMP "BEGIN_SIDER\n";
+foreach $key (keys %sider_p) { print HISTORYTMP "$key $sider_p{$key}\n"; next; }
+print HISTORYTMP "END_SIDER\n";
+
+print HISTORYTMP "BEGIN_TIME\n";
+for ($ix=0; $ix<=23; $ix++) { print HISTORYTMP "$ix $time_p[$ix] $time_h[$ix] $time_k[$ix]\n"; next; }
+print HISTORYTMP "END_TIME\n";
+
+print HISTORYTMP "BEGIN_BROWSER\n";
+foreach $key (keys %browser) { print HISTORYTMP "$key $browser{$key}\n"; next; }
+print HISTORYTMP "END_BROWSER\n";
+print HISTORYTMP "BEGIN_NSVER\n";
+for ($i=1; $i<=$#nsver; $i++) { print HISTORYTMP "$i $nsver[$i]\n"; next; }
+print HISTORYTMP "END_NSVER\n";
+print HISTORYTMP "BEGIN_MSIEVER\n";
+for ($i=1; $i<=$#msiever; $i++) { print HISTORYTMP "$i $msiever[$i]\n"; next; }
+print HISTORYTMP "END_MSIEVER\n";
+print HISTORYTMP "BEGIN_OS\n";
+foreach $key (keys %OS) { print HISTORYTMP "$key $OS{$key}\n"; next; }
+print HISTORYTMP "END_OS\n";
+
+print HISTORYTMP "BEGIN_ROBOT\n";
+foreach $key (keys %robot) { print HISTORYTMP "$key $robot{$key} $robot_l{$key}\n"; next; }
+print HISTORYTMP "END_ROBOT\n";
+
+print HISTORYTMP "BEGIN_UNKNOWNREFERER\n";
+foreach $key (keys %unknownreferer_l) { print HISTORYTMP "$key $unknownreferer_l{$key}\n"; next; }
+print HISTORYTMP "END_UNKNOWNREFERER\n";
+print HISTORYTMP "BEGIN_UNKNOWNREFERERBROWSER\n";
+foreach $key (keys %unknownrefererbrowser_l) { print HISTORYTMP "$key $unknownrefererbrowser_l{$key}\n"; next; }
+print HISTORYTMP "END_UNKNOWNREFERERBROWSER\n";
+
+print HISTORYTMP "HitFrom0 $HitFrom[0]\n";
+print HISTORYTMP "HitFrom1 $HitFrom[1]\n";
+print HISTORYTMP "HitFrom2 $HitFrom[2]\n";
+print HISTORYTMP "HitFrom3 $HitFrom[3]\n";
+print HISTORYTMP "HitFrom4 $HitFrom[4]\n";
+
+print HISTORYTMP "BEGIN_SEREFERRALS\n";
+foreach $key (keys %SEReferrals) { print HISTORYTMP "$key $SEReferrals{$key}\n"; next; }
+print HISTORYTMP "END_SEREFERRALS\n";
+
+print HISTORYTMP "BEGIN_PAGEREFS\n";
+foreach $key (keys %PageRefs) { print HISTORYTMP "$key $PageRefs{$key}\n"; next; }
+print HISTORYTMP "END_PAGEREFS\n";
+
+print HISTORYTMP "BEGIN_SEARCHWORDS\n";
+foreach $key (keys %searchwords) { print HISTORYTMP "$key $searchwords{$key}\n"; next; }
+print HISTORYTMP "END_SEARCHWORDS\n";
+
+print HISTORYTMP "BEGIN_ERRORS\n";
+foreach $key (keys %errors) { print HISTORYTMP "$key $errors{$key}\n"; next; }
+print HISTORYTMP "END_ERRORS\n";
+
+print HISTORYTMP "BEGIN_SIDER_404\n";
+foreach $key (keys %sider404) { print HISTORYTMP "$key $sider404{$key}\n"; next; }
+print HISTORYTMP "END_SIDER_404\n";
+
+close(HISTORYTMP);
+
+
+# Archive LOG file into ARCHIVELOG
+if ($ArchiveLogRecords == 1) {
+ if ($BenchMark == 1) { print "Start of archiving log records: ";print localtime(); print "<br>"; }
+ open(LOG,"+<$LogFile") || error("Error: Enable to archive log records of $LogFile into $DIR$PROG$month$year.log because source can't be opened for read and write: $!<br>\n");
+ open(ARCHIVELOG,">>$DIR$PROG$month$year.log") || error("Error: Couldn't open file $DIR$PROG$month$year.log to archive current log: $!");
+ while (<LOG>) { print ARCHIVELOG $_; }
+ close(ARCHIVELOG);
+ if ($BenchMark == 1) { print "End of archiving log records: ";print localtime(); print "<br>"; }
+ }
+else {
+ open(LOG,"+<$LogFile");
+}
+# Rename HISTORYTMP file into HISTORYTXT and purge LOG if ok
+if (rename "$DIR$PROG$month$year.tmp.$$", "$DIR$PROG$month$year.txt") {
+ truncate(LOG,0) || warning("Warning: $PROG couldn't purge logfile <b>$LogFile</b>.<br>\nBe aware of purging this file sometimes to keep good performances. Think to launch $PROG just before this to save in AWStats history text file all informations logfile contains.");
+ }
+close(LOG);
+chmod 438,"$DIR$PROG$month$year.txt"; chmod 438,"$DIR$PROG$month$year.log";
+
+
+#----------------------------------
+# READING OLD HISTORY FILES TO ADD
+#----------------------------------
+
+# Loop on each old month files
+for ($ix=($month-1); $ix>=1; $ix--) {
+ $monthix=$ix;if ($monthix < 10) { $monthix = "0$monthix"; }
+ $fic="$DIR$PROG$monthix$year.txt";
+ &Read_History_File($monthix);
+}
+
+
+#---------------------------------------------------------------------
+# SHOW STATISTICS
+#---------------------------------------------------------------------
+
+if ($QueryString =~ /unknownip/) {
+ print "<a name=\"UNKOWNIP\"></a>";
+ $tab_titre=$message[45][$Lang];
+ &tab_head;
+ print "<TR BGCOLOR=$color_TableBGRowTitle><TH align=left>$message[48][$Lang]</TH><TH align=center>$message[9][$Lang]</TH>\n";
+ @sortunknownip=sort { $SortDir*$unknownip_l{$a} <=> $SortDir*$unknownip_l{$b} } keys (%unknownip_l);
+ foreach $key (@sortunknownip) {
+ $yearcon=substr($unknownip_l{$key},0,4);
+ $monthcon=substr($unknownip_l{$key},4,2);
+ $daycon=substr($unknownip_l{$key},6,2);
+ $hourcon=substr($unknownip_l{$key},8,2);
+ $mincon=substr($unknownip_l{$key},10,2);
+ if ($Lang == 1) { print "<tr align=left><td>$key</td><td align=center>$daycon/$monthcon/$yearcon - $hourcon:$mincon</td></tr>"; }
+ else { print "<tr align=left><td>$key</td><td align=center>$daycon $monthlib{$monthcon} $yearcon - $hourcon:$mincon</td></tr>"; }
+ }
+ &tab_end;
+ &html_end;
+ exit(0);
+ }
+if ($QueryString =~ /unknownrefererbrowser/) {
+ print "<a name=\"UNKOWNREFERERBROWSER\"></a>";
+ $tab_titre=$message[50][$Lang];
+ &tab_head;
+ print "<TR BGCOLOR=$color_TableBGRowTitle><TH align=left>Referer</TH><TH align=center>$message[9][$Lang]</TH></TR>\n";
+ @sortunknownrefererbrowser=sort { $SortDir*$unknownrefererbrowser_l{$a} <=> $SortDir*$unknownrefererbrowser_l{$b} } keys (%unknownrefererbrowser_l);
+ foreach $key (@sortunknownrefererbrowser) {
+ $yearcon=substr($unknownrefererbrowser_l{$key},0,4);
+ $monthcon=substr($unknownrefererbrowser_l{$key},4,2);
+ $daycon=substr($unknownrefererbrowser_l{$key},6,2);
+ $hourcon=substr($unknownrefererbrowser_l{$key},8,2);
+ $mincon=substr($unknownrefererbrowser_l{$key},10,2);
+ if ($Lang == 1) { print "<tr align=left><td>$key</td><td align=center>$daycon/$monthcon/$yearcon - $hourcon:$mincon</td></tr>"; }
+ else { print "<tr align=left><td>$key</td><td align=center>$daycon $monthlib{$monthcon} $yearcon - $hourcon:$mincon</td></tr>"; }
+ }
+ &tab_end;
+ &html_end;
+ exit(0);
+ }
+if ($QueryString =~ /unknownreferer/) {
+ print "<a name=\"UNKOWNREFERER\"></a>";
+ $tab_titre=$message[46][$Lang];
+ &tab_head;
+ print "<TR BGCOLOR=$color_TableBGRowTitle><TH align=left>Referer</TH><TH align=center>$message[9][$Lang]</TH></TR>\n";
+ @sortunknownreferer=sort { $SortDir*$unknownreferer_l{$a} <=> $SortDir*$unknownreferer_l{$b} } keys (%unknownreferer_l);
+ foreach $key (@sortunknownreferer) {
+ $yearcon=substr($unknownreferer_l{$key},0,4);
+ $monthcon=substr($unknownreferer_l{$key},4,2);
+ $daycon=substr($unknownreferer_l{$key},6,2);
+ $hourcon=substr($unknownreferer_l{$key},8,2);
+ $mincon=substr($unknownreferer_l{$key},10,2);
+ if ($Lang == 1) { print "<tr align=left><td>$key</td><td align=center>$daycon/$monthcon/$yearcon - $hourcon:$mincon</td></tr>"; }
+ else { print "<tr align=left><td>$key</td><td align=center>$daycon $monthlib{$monthcon} $yearcon - $hourcon:$mincon</td></tr>"; }
+ }
+ &tab_end;
+ &html_end;
+ exit(0);
+ }
+if ($QueryString =~ /notfounderror/) {
+ print "<a name=\"NOTFOUNDERROR\"></a>";
+ $tab_titre=$message[47][$Lang];
+ &tab_head;
+ print "<TR bgcolor=$color_TableBGRowTitle align=center><TH align=left>URL</TH><TH bgcolor=$color_h>$message[49][$Lang]</TH></TR>\n";
+ @sortsider404=sort { $SortDir*$sider404{$a} <=> $SortDir*$sider404{$b} } keys (%sider404);
+ foreach $key (@sortsider404) {
+ print "<tr align=center><td align=left>$key</td><td>$sider404{$key}</td></tr>";
+ }
+ &tab_end;
+ &html_end;
+ exit(0);
+ }
+if ($QueryString =~ /browserdetail/) {
+ print "<a name=\"BROWSERDETAIL\"></a>";
+
+ print "<a name=\"NETSCAPE\"></a><BR>";
+ $tab_titre=$message[33][$Lang];
+ &tab_head;
+ print "<TR BGCOLOR=$color_TableBGRowTitle align=center><TH align=left>Version</TH><TH bgcolor=$color_h width=40>Hits</TH><TH bgcolor=$color_h width=40>$message[15][$Lang]</TH></TR>\n";
+ for ($i=1; $i<=$#nsver; $i++) {
+ if ($nsver[$i] gt 0) {
+ $h=$nsver[$i]; $p=int($nsver[$i]/$browser{"netscape"}*1000)/10; $p="$p %";
+ }
+ else {
+ $h=" "; $p=" ";
+ }
+ print "<TR align=center><TD align=left>Mozilla/$i.xx</TD><TD>$h</TD><TD>$p</TD></TR>\n";
+ }
+ &tab_end;
+
+ print "<a name=\"MSIE\"></a><BR>";
+ $tab_titre=$message[34][$Lang];
+ &tab_head;
+ print "<TR BGCOLOR=$color_TableBGRowTitle align=center><TH align=left>Version</TH><TH bgcolor=$color_h width=40>Hits</TH><TH bgcolor=$color_h width=40>$message[15][$Lang]</TH></TR>\n";
+ for ($i=1; $i<=$#msiever; $i++) {
+ if ($msiever[$i] gt 0) {
+ $h=$msiever[$i]; $p=int($msiever[$i]/$browser{"msie"}*1000)/10; $p="$p %";
+ }
+ else {
+ $h=" "; $p=" ";
+ }
+ print "<TR align=center><TD align=left>MSIE/$i.xx</TD><TD>$h</TD><TD>$p</TD></TR>\n";
+ }
+ &tab_end;
+
+ &html_end;
+ exit(0);
+ }
+
+
+if ($BenchMark == 1) { print "Start of sorting: ";print localtime();print "<br>"; }
+@RobotArray=keys %RobotHash;
+@SearchEnginesArray=keys %SearchEnginesHash;
+@sortdomains_h=sort { $SortDir*$domener_h{$a} <=> $SortDir*$domener_h{$b} } keys (%domener_h);
+@sortdomains_k=sort { $SortDir*$domener_k{$a} <=> $SortDir*$domener_k{$b} } keys (%domener_k);
+@sorthosts_h=sort { $SortDir*$hostmachine_h{$a} <=> $SortDir*$hostmachine_h{$b} } keys (%hostmachine_h);
+@sortsiders=sort { $SortDir*$sider_p{$a} <=> $SortDir*$sider_p{$b} } keys (%sider_p);
+@sortbrowsers=sort { $SortDir*$browser{$a} <=> $SortDir*$browser{$b} } keys (%browser);
+@sortos=sort { $SortDir*$OS{$a} <=> $SortDir*$OS{$b} } keys (%OS);
+@sortsereferrals=sort { $SortDir*$SEReferrals{$a} <=> $SortDir*$SEReferrals{$b} } keys (%SEReferrals);
+@sortpagerefs=sort { $SortDir*$PageRefs{$a} <=> $SortDir*$PageRefs{$b} } keys (%PageRefs);
+@sortsearchwords=sort { $SortDir*$searchwords{$a} <=> $SortDir*$searchwords{$b} } keys (%searchwords);
+@sorterrors=sort { $SortDir*$errors{$a} <=> $SortDir*$errors{$b} } keys (%errors);
+if ($BenchMark == 1) { print "End of sorting: ";print localtime(); print "<br>"; }
+
+# English tooltips
+if (($Lang == 0) || ($Lang == 2)) {
+ print "
+ <DIV CLASS=\"classTooltip\" ID=\"tt1\">
+ We count a new visits for each new <b>incoming visitor</b> viewing a page and who was not connected during last <b>".($VisitTimeOut/10000*60)." mn</b>.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt2\">
+ Number of client hosts (<b>IP address</b>) who came to visit the site (and to see at list one <b>page</b>).<br>
+ This number is about the number of <b>different physical persons</b> who had reached the site one day.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt3\">
+ Number of time a <b>page</b> of the site is <b>viewed</b> (Sum for all visitors, all visits).<br>
+ This counter differs from \"hits\" because it counts only HTML pages and not images and other files.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt4\">
+ Number of time a <b>page, image, file</b> of the site is <b>viewed</b> or <b>downloaded</b> by someone.<br>
+ This counter is given for indication, \"pages\" counter is often prefered.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt5\">
+ Number of <b>kilobytes</b> downloaded by visitors.<br>
+ It\'s the amount of data caused by download of all <b>pages</b>, <b>images</b> and <b>files</b>.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt13\">
+ $PROG is able to recognize access to the site after a <b>search</b> from the <b>".(@SearchEnginesArray)." most popular Internet Search Engines</b> (Yahoo, Altavista, Lycos, Google, Voila, etc...).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt14\">
+ List of all <b>external pages</b> that own a link followed to access the site (Only the <b>$MaxNbOfRefererShown</b> most often used external pages are shown.\n
+ Links used from the result of a search engine are not included here because they are included on line above this one.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt15\">
+ This tab shows list of most often used <b>keywords</b> to find your site from Internet Search Engines web sites
+ (Search from <b>".(@SearchEnginesArray)."</b> search engines among the most popular are recognized, like Yahoo, Altavista, Lycos, Google, Voila, etc...).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt16\">
+ Robots are <b>automatic computer visitors</b> scanning your web site to index it, to collect statistics on Internet Web sites or to see if your site is online.<br>
+ $PROG is able to recognize <b>".(@RobotArray)."</b> robots</b>.
+ </DIV>";
+
+ print "
+ <DIV CLASS=\"classTooltip\" ID=\"tt201\">
+ No description for this error.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt202\">
+ Request was understood by server but will be processed later.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt204\">
+ Server has processed the request but there is no document to send.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt206\">
+ Partial content.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt301\">
+ Requested document was moved and is now at another address given in awnswer.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt302\">
+ No description for this error.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt400\">
+ Syntax error, server didn\'t understand request.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt401\">
+ Try to reach an <b>URL where identification with login/password was required</b>.<br>
+ A too important number can show you someone making brute cracking of your site (hoping to enter a secured area by trying different logins/password).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt403\">
+ Try to reach an <b>URL not configured to be reachable, even with an identification</b> (for example, an URL of a directory not defined as \"browsable\".).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt404\">
+ Try to reach a <b>non existing URL</b>. So it means an invalid link somewhere or a typing error made by visitor who tape a direct URL.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt408\">
+ Server has taken a <b>too long time</b> to respond to request. It might be a CGI script so slow that server need to kill this job or a overcharged web server.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt500\">
+ Internal error. This error is often caused by a CGI program that had finished abnormally (coredump for example).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt501\">
+ Unknown requested action.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt502\">
+ Code returned by a HTTP server that works as a proxy or gateway when real targeted server doesn\'t answer successfully to the client request.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt503\">
+ Internal server error.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt504\">
+ Gateway Time-out.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt505\">
+ HTTP Version Not Supported.
+ </DIV>
+ ";
+}
+
+# French tooltips
+if ($Lang == 1) {
+ print "
+ <DIV CLASS=\"classTooltip\" ID=\"tt1\">
+ On considère une nouvelle visite pour <b>chaque arrivée</b> d un visiteur consultant une page et ne s étant pas connecté dans les dernières <b>".($VisitTimeOut/10000*60)." mn</b>.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt2\">
+ Nombre de hotes (<b>adresse IP</b>) utilisés pour accéder au site (et voir au moins une <b>page</b>).<br>
+ Ce chiffre reflète le nombre de <b>personnes physiques</b> différentes ayant un jour accédé au site.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt3\">
+ Nombre de fois qu une <b>page</b> du site est <b>vue</b> (Cumul de tout visiteur, toute visite).<br>
+ Ce compteur différe des \"hits\" car il ne comptabilise que les pages HTML et non les images ou autres fichiers.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt4\">
+ Nombre de fois qu une <b>page, image, fichier</b> du site est <b>vu</b> ou <b>téléchargé</b> par un visiteur.<br>
+ Ce compteur est donné à titre indicatif, le compteur \"pages\" etant préféré.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt5\">
+ Nombre de <b>kilo octets</b> téléchargé lors des visites du site.<br>
+ Il s agit aussi bien du volume de données du au chargement des <b>pages</b> et <b>images</b> que des <b>fichiers</b> téléchargés.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt13\">
+ $PROG est capable de reconnaitre l acces au site issu d une <b>recherche</b> depuis les <b>".(@SearchEnginesArray)." moteurs de recherche Internet</b> les plus connus (Yahoo, Altavista, Lycos, Google, Voila, etc...).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt14\">
+ Liste des <b>pages de sites externes</b> contenant un lien suivi pour accéder à ce site (Seules les <b>$MaxNbOfRefererShown</b> pages externes les plus utilisées sont affichées).\n
+ Les liens issus du résultat d un moteur de recherche connu n apparaissent pas ici, car comptabilisés à part sur la ligne juste au-dessus.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt15\">
+ Ce tableau offre la liste des <b>mots</b> les plus souvent utilisés pour retrouver et accéder au site depuis
+ un moteur de recherche Internet (Les recherches depuis <b>".(@SearchEnginesArray)."</b> moteurs de recherche parmi les pluspopulaires sont reconnues, comme Yahoo, Altavista, Lycos, Google, Voila, etc...).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt16\">
+ Les robots sont des <b>automates visiteurs</b> scannant le site dans le but de l indexer, d obtenir des statistiques sur les sites Web Internet ou de vérifier sa disponibilié.<br>
+ $PROG reconnait <b>".(@RobotArray)."</b> robots</b>.
+ </DIV>";
+
+ print "
+ <DIV CLASS=\"classTooltip\" ID=\"tt201\">
+ Contenu partiel renvoyé.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt202\">
+ La requête a été enregistrée par le serveur mais sera exécutée plus tard.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt204\">
+ Le serveur a traité la demande mais il n existe aucun document à renvoyer.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt206\">
+ Contenu partiel renvoyé.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt301\">
+ Le document réclamé a été déplacé et se trouve maintenant à une autre adresse mentionnée dans la réponse.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt302\">
+ Aucun descriptif pour cette erreur.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt400\">
+ Erreur de syntaxe, le serveur n a pas compris la requête.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt401\">
+ Tentatives d accès à une <b>URL nécessitant identification avec un login/mot de passe invalide</b>.<br>
+ Un nombre trop élévé peut mettre en évidence une tentative de crackage brute du site (par accès répété de différents logins/mots de passe).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt403\">
+ Tentatives d accès à une <b>URL non configurée pour etre accessible, même avec une identification</b> (par exemple, une URL d un répertoire non défini comme étant \"listable\").
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt404\">
+ Tentatives d accès à une <b>URL inexistante</b>. Il s agit donc d un lien invalide sur le site ou d une faute de frappe d un visiteur qui a saisie une mauvaise URL directement.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt408\">
+ Le serveur mis un <b>temps trop important</b> pour répondre à la requête. Il peut s agir d un script CGI trop lent sur le serveur forcé d abandonner le traitement ou d une saturation du site.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt500\">
+ Erreur interne au serveur. Cette erreur est le plus souvant renvoyé lors de l arrêt anormal d un script CGI (par exemple suite à un coredump du CGI).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt501\">
+ Le serveur ne prend pas en charge l action demandée.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt502\">
+ Code renvoyé par un serveur HTTP qui fonctionne comme proxy ou gateway lorsque le serveur réel consulté ne réagit pas avec succès à la demande du client.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt503\">
+ Erreur interne au serveur.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt504\">
+ Gateway Time-out.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt505\">
+ Version HTTP non supporté.
+ </DIV>
+ ";
+}
+
+# Spannish tooltips
+if ($Lang == 3) {
+ print "
+ <DIV CLASS=\"classTooltip\" ID=\"tt1\">
+ Se considera un nueva vista por <b>cada nuevo visitante</b> que consulte una página y que no haya accesado el sitio en los últimos <b>".($VisitTimeOut/10000*60)." mins.</b>.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt2\">
+ Número de Servidores (<b>direcciones IP</b>) que entran a un sitio (y que por lo menos visitan una <b>página</b>).<br>
+ Esta cifra refleja el número de <b>personas físicas diferentes</b> que hayan accesado al sitio en un día.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt3\">
+ Número de ocasiones que una <b>página</b> del sitio ha sido <b>vista</b> (La suma de todos los visitantes incluyendo múltiples visitas).<br>
+ Este contador se distingue de \"hits\" porque cuenta sólo las páginas HTML y no los gráficos u otros archivos o ficheros.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt4\">
+ El número de ocasiones que una <b>página, imagen, archivo o fichero</b> de un sitio es <b>visto</b> o <b>descargado</b> por un visitante.<br>
+ Este contador sirve de referencia, pero el contador de \"páginas\" representa un dato mercadotécnico generalmente más útil y por lo tanto se recomienda.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt5\">
+ El número de <b>kilo bytes</b> descargados por los visitantes del sitio.<br>
+ Se refiere al volumen de datos descargados por todas las <b>páginas</b>, <b>imágenes</b> y <b>archivos o ficheros</b> medidos en kilo bytes.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt13\">
+ El programa $PROG es capaz de reconocer una visita a su sitio luego de cada <b>búsqueda</b> desde cualquiera de los <b>".(@SearchEnginesArray)." motores de búsqueda y directorios Internet</b> más populares (Yahoo, Altavista, Lycos, Google, Terra, etc...).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt14\">
+ Lista de <b>páginas de sitios externos</b> utilizadas para acceder o enlazarse con su sitio (Sólo las <b>$MaxNbOfRefererShown</b> páginas más utilizadas se encuentras enumeradas).\n
+ Los enlaces utilizados por los motores de búsqueda o directorios son excluidos porque ya han sido contabilizados en el rubro anterior.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt15\">
+ Esta tabla muestra la lista de las <b>palabras clave</b> más utilizadas en los motores de búsqueda y directorios Internet para encontrar su sitio.
+ (El programa $PROG reconoce palabras clave usadas en los <b>".(@SearchEnginesArray)."</b> motores de búsqueda más populares, tales como Yahoo, Altavista, Lycos, Google, Voila, Terra etc...).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt16\">
+ Los Robots son <b>visitantes automáticos</b> que escanean o viajan por su sitio para indexarlo, o jerarquizarlo, para recopilar estadísticas de sitios Web, o para verificar si su sitio se encuentra conectado a la Red.<br>
+ El programa $PROG reconoce hasta <b>".(@RobotArray)."</b> Robots</b>.
+ </DIV>";
+
+ print "
+ <DIV CLASS=\"classTooltip\" ID=\"tt201\">
+ Error sin descripción.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt202\">
+ La solicitud ha sido computada pero el servidor la procesará más tarde.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt204\">
+ El servidor ha procesado la solicitud pero no existen documentos para enviar.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt206\">
+ Contenido parcial.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt301\">
+ El documento solicitado ha sido reubicado y se encuentra en un URL proporcionado en la misma respuesta.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt302\">
+ Error sin descripción.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt400\">
+ Error de sintaxis, el servidor no ha comprendido su solicitud.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt401\">
+ Número de intentos por acceder un <b>URL que exige una combinación usuario/contraseña que ha sido invalida.</b>.<br>
+ Un número de intentos muy elevado pudiera sugerir la posibilidad de que un hacker (o pirata) ha intentado entrar a una zona restringida del sitio (p.e., intentando múltiples combinaciones de usuario/contraseña).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt403\">
+ Número de intentos por acceder un <b>URL configurado para no ser accesible, aún con una combinación usuario/contraseña</b> (p.e., un URL previamente definido como \"no navegable\").
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt404\">
+ Número de intentos por acceder un <b>URL inexistente</b>. Frecuentemente, éstos se refieren ya sea a un enlace (link) inválido o a un error mecanográfico cuando el visitante tecleó el URL equivocado.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt408\">
+ El servidor ha tomado <b>demasiado tiempo</b> para responder a una solicitud. Frecuentemente se debe ya sea a un programa CGI muy lento, el cual tuvo que ser abandonado por el servidor, o bien por un servidor sobre-saturado.
+ </DIV>
+
+ <DIV CLASS=\"classTooltip\" ID=\"tt500\">
+ Error interno. Este error generalmente es causado por una terminación anormal o prematura de un programa CGI (p.e., un CGI corrompido o dañado).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt501\">
+ Solicitud desconocida por el servidor.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt502\">
+ Código retornado por un servidor de protocolo HTTP el cual funge como proxy o puente (gateway) cuando el servidor objetivo no funciona o no interpreta adecuadamente la solicitud del cliente (o visitante).
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt503\">
+ Error interno del servidor.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt504\">
+ Gateway time-out.
+ </DIV>
+ <DIV CLASS=\"classTooltip\" ID=\"tt505\">
+ Versión de protocolo HTTP no soportada.
+ </DIV>
+ ";
+}
+
+print "
+<SCRIPT JavaScript>
+ function ShowTooltip(fArg)
+ {
+ var tooltipOBJ = eval(\"document.all['tt\" + fArg + \"']\");
+ var tooltipOffsetTop = tooltipOBJ.scrollHeight + 35;
+ var testTop = (document.body.scrollTop + event.clientY) - tooltipOffsetTop;
+ var testLeft = event.clientX - 310;
+ var tooltipAbsLft = (testLeft < 0) ? 10 : testLeft;
+ var tooltipAbsTop = (testTop < document.body.scrollTop) ? document.body.scrollTop + 10 : testTop;
+ tooltipOBJ.style.posLeft = tooltipAbsLft; tooltipOBJ.style.posTop = tooltipAbsTop;
+ tooltipOBJ.style.visibility = \"visible\";
+ }
+ function HideTooltip(fArg)
+ {
+ var tooltipOBJ = eval(\"document.all['tt\" + fArg + \"']\");
+ tooltipOBJ.style.visibility = \"hidden\";
+ }
+</SCRIPT>
+
+";
+
+
+# SUMMARY
+#---------------------------------------------------------------------
+$tab_titre="$message[7][$Lang] $LocalSite";
+&tab_head;
+
+# TotalUnique
+foreach $key (keys %hostmachine_p) { if (($key ne "Unknown") && ($hostmachine_p{$key} > 0)) { $TotalUnique++; } }
+foreach $key (keys %unknownip_l) { $TotalUnique++; }
+# TotalDifferentPages
+$TotalDifferentPages=@sortsiders;
+# TotalPages TotalHits TotalBytes
+for ($ix=0; $ix<=23; $ix++) { $TotalPages+=$time_p[$ix]; $TotalHits+=$time_h[$ix]; $TotalBytes+=$time_k[$ix]; }
+# TotalDifferentKeywords
+$TotalDifferentKeywords=@sortsearchwords;
+# TotalKeywords
+foreach $key (keys %searchwords) { $TotalKeywords+=$searchwords{$key}; }
+# TotalErrors
+foreach $key (keys %errors) { $TotalErrors+=$errors{$key}; }
+# Ratio
+if ($TotalUnique > 0) { $RatioHosts=int($TotalVisits/$TotalUnique*100)/100; }
+if ($TotalVisits > 0) { $RatioPages=int($TotalPages/$TotalVisits*100)/100; }
+if ($TotalVisits > 0) { $RatioHits=int($TotalHits/$TotalVisits*100)/100; }
+if ($TotalVisits > 0) { $RatioBytes=int(($TotalBytes/1024/$TotalVisits)*100)/100; }
+
+print "<TR align=center><TD><b>$message[8][$Lang]</b></TD><TD colspan=3 rowspan=2>$message[6][$Lang] $year</TD><TD><b>$message[9][$Lang]</b></TD></TR>";
+$yearcon=substr($FirstTime,0,4);$monthcon=substr($FirstTime,4,2);$daycon=substr($FirstTime,6,2);$hourcon=substr($FirstTime,8,2);$mincon=substr($FirstTime,10,2);
+print "<TR align=center><TD>$daycon $monthlib{$monthcon} $yearcon - $hourcon:$mincon</TD>";
+$yearcon=substr($LastTime,0,4);$monthcon=substr($LastTime,4,2);$daycon=substr($LastTime,6,2);$hourcon=substr($LastTime,8,2);$mincon=substr($LastTime,10,2);
+print "<TD>$daycon $monthlib{$monthcon} $yearcon - $hourcon:$mincon</TD></TR>";
+print "<TR align=center>";
+print "<TD width=20% bgcolor=$color_v onmouseover=\"ShowTooltip(1);\" onmouseout=\"HideTooltip(1);\">$message[10][$Lang]</TD>";
+print "<TD width=20% bgcolor=$color_w onmouseover=\"ShowTooltip(2);\" onmouseout=\"HideTooltip(2);\">$message[11][$Lang]</TD>";
+print "<TD width=20% bgcolor=$color_p onmouseover=\"ShowTooltip(3);\" onmouseout=\"HideTooltip(3);\">Pages</TD>";
+print "<TD width=20% bgcolor=$color_h onmouseover=\"ShowTooltip(4);\" onmouseout=\"HideTooltip(4);\">Hits</TD>";
+print "<TD width=20% bgcolor=$color_k onmouseover=\"ShowTooltip(5);\" onmouseout=\"HideTooltip(5);\">$message[44][$Lang]</TD></TR>";
+$kilo=int($TotalBytes/1024*100)/100;
+print "<TR align=center><TD><b>$TotalVisits</b><br> </TD><TD><b>$TotalUnique</b><br>($RatioHosts $message[52][$Lang])</TD><TD><b>$TotalPages</b><br>($RatioPages pages/$message[12][$Lang])</TD><TD><b>$TotalHits</b><br>($RatioHits hits/$message[12][$Lang])</TD><TD><b>$kilo $message[44][$Lang]</b><br>($RatioBytes $message[44][$Lang]/$message[12][$Lang])</TD></TR>\n";
+print "<TR valign=bottom><TD colspan=5 align=center>";
+print "<TABLE>";
+print "<TR valign=bottom>";
+$max_v=1;$max_u=1;$max_p=1;$max_h=1;$max_k=1;
+for ($ix=1; $ix<=12; $ix++) {
+ $monthix=$ix; if ($monthix < 10) { $monthix="0$monthix"; }
+ if ($indic1{$monthix} > $max_v) { $max_v=$indic1{$monthix}; }
+ if ($indic2{$monthix} > $max_v) { $max_v=$indic2{$monthix}; }
+ if ($indic3{$monthix} > $max_p) { $max_p=$indic3{$monthix}; }
+ if ($indic4{$monthix} > $max_h) { $max_h=$indic4{$monthix}; }
+ if ($indic5{$monthix} > $max_k) { $max_k=$indic5{$monthix}; }
+}
+for ($ix=1; $ix<=12; $ix++) {
+ $monthix=$ix; if ($monthix < 10) { $monthix="0$monthix"; }
+ $bredde_v=$indic1{$monthix}/$max_v*$Barheight/2;
+ $bredde_u=$indic2{$monthix}/$max_v*$Barheight/2;
+ $bredde_p=$indic3{$monthix}/$max_h*$Barheight/2;
+ $bredde_h=$indic4{$monthix}/$max_h*$Barheight/2;
+ $bredde_k=$indic5{$monthix}/$max_k*$Barheight/2;
+ $kilo=int(($indic5{$monthix}/1024)*100)/100;
+ print "<TD align=center>";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_v\" HEIGHT=$bredde_v WIDTH=8 ALT=\"Visits: $indic1{$monthix}\">";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_u\" HEIGHT=$bredde_u WIDTH=8 ALT=\"Visitors: $indic2{$monthix}\">";
+ print " ";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_p\" HEIGHT=$bredde_p WIDTH=8 ALT=\"Pages: $indic3{$monthix}\">";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_h\" HEIGHT=$bredde_h WIDTH=8 ALT=\"Hits: $indic4{$monthix}\">";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_k\" HEIGHT=$bredde_k WIDTH=8 ALT=\"$message[44][$Lang]: $kilo\">";
+ print "</TD>\n";
+}
+print "</TR><TR>";
+for ($ix=1; $ix<=12; $ix++) {
+ $monthix=$ix; if ($monthix < 10) { $monthix="0$monthix"; }
+ print "<TD align=center>$monthlib{$monthix}</TD>";
+}
+print "</TR></TABLE>";
+print "</TD></TR>";
+&tab_end;
+
+
+# MENU
+#---------------------------------------------------------------------
+print "<br>";
+
+print "<table width=100%><tr align=center><td>";
+print " <a href=\"#DOMAINS\"><font size=1>[$message[17][$Lang]]</font></a> ";
+print " <a href=\"#VISITOR\"><font size=1>[$message[18][$Lang]]</font></a> ";
+print " <a href=\"#ROBOTS\"><font size=1>[$message[53][$Lang]]</font></a> ";
+print " <a href=\"#PAGE\"><font size=1>[$message[19][$Lang]]</font></a> ";
+print " <a href=\"#HOUR\"><font size=1>[$message[20][$Lang]]</font></a> ";
+print " <a href=\"#BROWSER\"><font size=1>[$message[21][$Lang]]</font></a> ";
+print " <a href=\"#REFERER\"><font size=1>[$message[23][$Lang]]</font></a> ";
+print " <a href=\"#SEARCHWORDS\"><font size=1>[$message[24][$Lang]]</font></a> ";
+print " <a href=\"#ERRORS\"><font size=1>[$message[22][$Lang]]</font></a> ";
+print "</td></tr></table>";
+
+print "<br><hr width=96%>";
+
+
+# BY COUNTRY/DOMAIN
+#---------------------------
+print "<a name=\"DOMAINS\"></a><BR>";
+$tab_titre="$message[25][$Lang]";
+&tab_head;
+print "<TR align=center BGCOLOR=$color_TableBGRowTitle><TH colspan=2>$message[17][$Lang]</TH><TH>Code</TH><TH bgcolor=$color_p>Pages</TH><TH bgcolor=$color_h>Hits</TH><TH bgcolor=$color_k>$message[44][$Lang]</TH><TH> </TH></TR>\n";
+if ($SortDir<0) { $max_h=$domener_h{$sortdomains_h[0]}; }
+else { $max_h=$domener_h{$sortdomains_h[$#sortdomains_h]}; }
+if ($SortDir<0) { $max_k=$domener_k{$sortdomains_k[0]}; }
+else { $max_k=$domener_k{$sortdomains_k[$#sortdomains_k]}; }
+foreach $key (@sortdomains_h) {
+ if ($max_h > 0) { $bredde_p=$Barwidth*$domener_p{$key}/$max_h+1; } # use max_h to enable to compare pages with hits
+ if ($max_h > 0) { $bredde_h=$Barwidth*$domener_h{$key}/$max_h+1; }
+ if ($max_k > 0) { $bredde_k=$Barwidth*$domener_k{$key}/$max_k+1; }
+ $page=$domener_p{$key};if ($page eq "") { $page=0; }
+ $kilo=int(($domener_k{$key}/1024)*100)/100;
+ if ($key eq "ip") {
+ print "<TR align=center><TD><IMG SRC=\"$DirIcons\/flags\/$key.png\" height=14></TD><TD align=left>$message[0][$Lang]</TD><TD align=center>$key</TD>";
+ }
+ else {
+ print "<TR align=center><TD><IMG SRC=\"$DirIcons\/flags\/$key.png\" height=14></TD><TD align=left>$DomainsHash{$key}</TD><TD align=center>$key</TD>";
+ }
+ print "<TD>$page</TD><TD>$domener_h{$key}</TD><TD>$kilo</TD>";
+ print "<TD align=left>";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageHorizontal_p\" WIDTH=$bredde_p HEIGHT=6 ALT=\"Pages: $domener_p{$key}\"><br>\n";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageHorizontal_h\" WIDTH=$bredde_h HEIGHT=6 ALT=\"Hits: $domener_h{$key}\"><br>\n";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageHorizontal_k\" WIDTH=$bredde_k HEIGHT=6 ALT=\"$message[44][$Lang]: $kilo\">";
+ print "</TD></TR>\n";
+}
+&tab_end;
+
+
+# BY HOST/VISITOR
+#--------------------------
+print "<a name=\"VISITOR\"></a>";
+$tab_titre="TOP $MaxNbOfHostsShown $message[55][$Lang] ".(@sorthosts_h)." $message[26][$Lang] ($TotalUnique $message[11][$Lang])";
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle><TH align=left>$message[18][$Lang]</TH><TH bgcolor=$color_p>Pages</TH><TH bgcolor=$color_h>Hits</TH><TH bgcolor=$color_k>$message[44][$Lang]</TH><TH>$message[9][$Lang]</TH></TR>\n";
+$count=0;$total_p=0;$total_h=0;$total_k=0;
+foreach $key (@sorthosts_h)
+{
+ if ($hostmachine_h{$key}>=$MinHitHost) {
+ $page=$hostmachine_p{$key};if ($page eq "") { $page=0; }
+ $kilo=int(($hostmachine_k{$key}/1024)*100)/100;
+ if ($key eq "Unknown") {
+ print "<TR align=center><TD align=left><a href=\"$PROG.pl?action=unknownip&lang=$Lang\">$message[1][$Lang]</a></TD><TD>$page</TD><TD>$hostmachine_h{$key}</TD><TD>$kilo</TD><TD><a href=\"$PROG.pl?action=unknownip&lang=$Lang\">$message[3][$Lang]</a></TD></TR>\n";
+ }
+ else {
+ $yearcon=substr($hostmachine_l{$key},0,4);
+ $monthcon=substr($hostmachine_l{$key},4,2);
+ $daycon=substr($hostmachine_l{$key},6,2);
+ $hourcon=substr($hostmachine_l{$key},8,2);
+ $mincon=substr($hostmachine_l{$key},10,2);
+ print "<tr align=center><td align=left>$key</td><TD>$page</TD><TD>$hostmachine_h{$key}</TD><TD>$kilo</TD>";
+ if ($Lang != 0) { print "<td align=center>$daycon/$monthcon/$yearcon - $hourcon:$mincon</td></tr>"; }
+ else { print "<td align=center>$daycon $monthlib{$monthcon} $yearcon - $hourcon:$mincon</td></tr>"; }
+ }
+
+ $total_p += $hostmachine_p{$key};
+ $total_h += $hostmachine_h{$key};
+ $total_k += $hostmachine_k{$key};
+ }
+ $count++;
+ if (!(($SortDir<0 && $count<$MaxNbOfHostsShown) || ($SortDir>0 && $#sorthosts_h-$MaxNbOfHostsShown < $count))) { last; }
+}
+$rest_p=$TotalPages-$total_p;
+$rest_h=$TotalHits-$total_h;
+$rest_k=int((($TotalBytes-$total_k)/1024)*100)/100;
+if ($rest_p > 0) { print "<TR align=center><TD align=left><font color=blue>$message[2][$Lang]</font></TD><TD>$rest_p</TD><TD>$rest_h</TD><TD>$rest_k</TD><TD> </TD></TR>\n"; } # All other visitors (known or not)
+&tab_end;
+
+
+# BY ROBOTS
+#----------------------------
+print "<a name=\"ROBOTS\"></a><BR>";
+$tab_titre=$message[53][$Lang];
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle onmouseover=\"ShowTooltip(16);\" onmouseout=\"HideTooltip(16);\"><TH align=left>Robot</TH><TH align=center bgcolor=$color_h width=80>Hits</TH><TH>$message[9][$Lang]</TH></TR>\n";
+@sortrobot=sort { $SortDir*$robot{$a} <=> $SortDir*$robot{$b} } keys (%robot);
+foreach $key (@sortrobot) {
+ $yearcon=substr($robot_l{$key},0,4);
+ $monthcon=substr($robot_l{$key},4,2);
+ $daycon=substr($robot_l{$key},6,2);
+ $hourcon=substr($robot_l{$key},8,2);
+ $mincon=substr($robot_l{$key},10,2);
+ if ($Lang != 0) { print "<tr align=left><td>$RobotHash{$key}</td><td align=center>$robot{$key}</td><td align=center>$daycon/$monthcon/$yearcon - $hourcon:$mincon</td></tr>"; }
+ else { print "<tr align=left><td>$RobotHash{$key}</td><td align=center>$robot{$key}</td><td align=center>$daycon $monthlib{$monthcon} $yearcon - $hourcon:$mincon</td></tr>"; }
+}
+&tab_end;
+
+
+# BY PAGE
+#-------------------------
+print "<a name=\"PAGE\"></a><BR>";
+$tab_titre="TOP $MaxNbOfPageShown $message[55][$Lang] $TotalDifferentPages $message[27][$Lang]";
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle><TH>Page-URL</TH><TH bgcolor=$color_p align=center> $message[29][$Lang] </TH><TH> </TH></TR>\n";
+if ($SortDir<0) { $max=$sider_p{$sortsiders[0]}; }
+else { $max=$sider_p{$sortsiders[$#sortsiders]}; }
+$count=0;
+foreach $key (@sortsiders) {
+ if ((($SortDir<0 && $count<$MaxNbOfPageShown) || ($SortDir>0 && $#sortsiders-$MaxNbOfPageShown<$count)) && $sider_p{$key}>=$MinHitFile) {
+ print "<TR><TD>";
+ $nompage=$Aliases{$key};
+ if ($nompage eq "") { $nompage=$key; }
+ $nompage=substr($nompage,0,$MaxLengthOfURL);
+ if ($ShowLinksOnUrl) { print "<A HREF=\"$key\">$nompage</A>"; }
+ else { print "$nompage"; }
+ $bredde=$Barwidth*$sider_p{$key}/$max+1;
+ print "</TD><TD align=center>$sider_p{$key}</TD><TD><IMG SRC=\"$DirIcons\/other\/$BarImageHorizontal_p\" WIDTH=$bredde HEIGHT=8 ALT=\"Pages: $sider_p{$key}\"></TD></TR>\n";
+ }
+ $count++;
+}
+&tab_end;
+
+
+# BY HOUR
+#----------------------------
+print "<a name=\"HOUR\"></a><BR>";
+$tab_titre="$message[20][$Lang]";
+&tab_head;
+
+print "<TR><TD align=center><TABLE><TR>\n";
+$max_p=0;$max_h=0;$max_k=0;
+for ($ix=0; $ix<=23; $ix++) {
+ print "<TH width=16>$ix</TH>";
+ if ($time_p[$ix]>$max_p) { $max_p=$time_p[$ix]; }
+ if ($time_h[$ix]>$max_h) { $max_h=$time_h[$ix]; }
+ if ($time_k[$ix]>$max_k) { $max_k=$time_k[$ix]; }
+}
+print "</TR>\n";
+
+print "<TR>\n";
+for ($ix=0; $ix<=23; $ix++) {
+ $hr=$ix+1;
+ if ($ix>11) { $hr=$ix-11; }
+ print "<TH><IMG SRC=\"$DirIcons\/clock\/hr$hr.png\" width=10></TH>";
+}
+print "</TR>\n";
+
+print "\n<TR VALIGN=BOTTOM>\n";
+for ($ix=0; $ix<=23; $ix++) {
+ if ($max_h > 0) { $bredde_p=$Barheight*$time_p[$ix]/$max_h+1; }
+ if ($max_h > 0) { $bredde_h=$Barheight*$time_h[$ix]/$max_h+1; }
+ if ($max_k > 0) { $bredde_k=$Barheight*$time_k[$ix]/$max_k+1; }
+ $kilo=int(($time_k[$ix]/1024)*100)/100;
+ print "<TD>";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_p\" HEIGHT=$bredde_p WIDTH=6 ALT=\"Pages: $time_p[$ix]\">";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_h\" HEIGHT=$bredde_h WIDTH=6 ALT=\"Hits: $time_h[$ix]\">";
+ print "<IMG SRC=\"$DirIcons\/other\/$BarImageVertical_k\" HEIGHT=$bredde_k WIDTH=6 ALT=\"$message[44][$Lang]: $kilo\">";
+ print "</TD>\n";
+}
+print "</TR></TABLE></TD></TR>\n";
+
+&tab_end;
+
+
+# BY BROWSER
+#----------------------------
+print "<a name=\"BROWSER\"></a><BR>";
+$tab_titre="$message[31][$Lang]";
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle align=center><TH align=left>Browser</TH><TH bgcolor=$color_h width=40>Hits</TH><TH bgcolor=$color_h width=40>$message[15][$Lang]</TH></TR>\n";
+foreach $key (@sortbrowsers) {
+ $p=int($browser{$key}/$TotalHits*1000)/10;
+ if ($key eq "Unknown") {
+ print "<TR align=center><TD align=left><a href=\"$PROG.pl?action=unknownrefererbrowser&lang=$Lang\">$message[0][$Lang]</a></TD><TD>$browser{$key}</TD><TD>$p %</TD></TR>\n";
+ }
+ else {
+ print "<TR align=center><TD align=left>$BrowsersHash{$key}</TD><TD>$browser{$key}</TD><TD>$p %</TD></TR>\n";
+ }
+}
+&tab_end;
+
+
+# BY OS
+#----------------------------
+print "<a name=\"OS\"></a><BR>";
+$tab_titre=$message[35][$Lang];
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle align=center><TH align=left colspan=2>OS</TH><TH bgcolor=$color_h width=40>Hits</TH><TH bgcolor=$color_h width=40>$message[15][$Lang]</TH></TR>\n";
+foreach $key (@sortos) {
+ $p=int($OS{$key}/$TotalHits*1000)/10;
+ if ($key eq "Unknown") {
+ print "<TR align=center><TD><IMG SRC=\"$DirIcons\/os\/unknown.png\"></TD><TD align=left><a href=\"$PROG.pl?action=unknownreferer&lang=$Lang\">$message[0][$Lang]</a></TD><TD>$OS{$key} </TD>";
+ print "<TD>$p %</TD></TR>\n";
+ }
+ else {
+ $nameicon = $OSHash{$key}; $nameicon =~ s/\ .*//; $nameicon =~ tr/A-Z/a-z/;
+ print "<TR align=center><TD><IMG SRC=\"$DirIcons\/os\/$nameicon.png\"></TD><TD align=left>$OSHash{$key}</TD><TD>$OS{$key}</TD>";
+ print "<TD>$p %</TD></TR>\n";
+ }
+}
+&tab_end;
+
+
+# BY REFERENCE
+#---------------------------
+print "<a name=\"REFERER\"></a><BR>";
+$tab_titre="$message[36][$Lang]";
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle align=center><TH align=left>$message[37][$Lang]</TH><TH bgcolor=$color_h width=40>Hits</TH><TH bgcolor=$color_h width=40>$message[15][$Lang]</TH></TR>\n";
+if ($TotalHits > 0) { $_=int($HitFrom[0]/$TotalHits*1000)/10; }
+print "<TR align=center><TD align=left><b>$message[38][$Lang]:</b></TD><TD>$HitFrom[0]</TD><TD>$_ %</TD></TR>\n";
+if ($TotalHits > 0) { $_=int($HitFrom[1]/$TotalHits*1000)/10; }
+print "<TR align=center><TD align=left><b>$message[39][$Lang]:</b></TD><TD>$HitFrom[1]</TD><TD>$_ %</TD></TR>\n";
+#------- Referrals by search engine
+if ($TotalHits > 0) { $_=int($HitFrom[2]/$TotalHits*1000)/10; }
+print "<TR align=center onmouseover=\"ShowTooltip(13);\" onmouseout=\"HideTooltip(13);\"><TD align=left><b>$message[40][$Lang] :</b><br>";
+print "<TABLE>\n";
+foreach $SE (@sortsereferrals) {
+ print "<TR><TD align=left>- $SearchEnginesHash{$SE} </TD><TD align=right>$SEReferrals{\"$SE\"}</TD></TR>\n";
+}
+print "</TABLE></TD>\n";
+print "<TD valign=top>$HitFrom[2]</TD><TD valign=top>$_ %</TD></TR>\n";
+#------- Referrals by external HTML link
+if ($TotalHits > 0) { $_=(int($HitFrom[3]/$TotalHits*1000)/10); }
+print "<TR align=center onmouseover=\"ShowTooltip(14);\" onmouseout=\"HideTooltip(14);\"><TD align=left><b>$message[41][$Lang] :</b><br>";
+print "<TABLE>\n";
+$count=0;
+foreach $from (@sortpagerefs) {
+ if (!(($SortDir<0 && $count<$MaxNbOfRefererShown) || ($SortDir>0 && $#sortpagerefs-$MaxNbOfRefererShown < $count))) { last; }
+ if ($PageRefs{$from}>=$MinHitRefer) {
+
+ # Show source
+ $lien=$from;
+ $lien =~ s/\"//g;
+ $lien=substr($lien,0,$MaxLengthOfURL);
+ if ($ShowLinksOnUrl && ($lien =~ /(ftp|http):\/\//)) {
+ print "<TR align=center><TD align=left>- <A HREF=$from>$lien</A></TD> <TD>$PageRefs{$from}</TD></TR>\n";
+ } else {
+ print "<TR align=center><TD align=left>- $lien </TD><TD>$PageRefs{$from}</TD></TR>\n";
+ }
+
+ $count++;
+ }
+}
+print "</TABLE></TD>\n";
+print "<TD valign=top>$HitFrom[3]</TD><TD valign=top>$_ %</TD></TR>\n";
+
+if ($TotalHits > 0) { $_=(int($HitFrom[4]/$TotalHits*1000)/10); }
+print "<TR align=center><TD align=left><b>$message[42][$Lang] :</b></TD><TD>$HitFrom[4]</TD><TD>$_ %</TD></TR>\n";
+&tab_end;
+
+
+# BY SEARCHWORDS
+#----------------------------
+print "<a name=\"SEARCHWORDS\"></a><BR>";
+$tab_titre="TOP $MaxNbOfKeywordsShown $message[55][$Lang] $TotalDifferentKeywords $message[43][$Lang]";
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle align=center onmouseover=\"ShowTooltip(15);\" onmouseout=\"HideTooltip(15);\"><TH align=left>$message[13][$Lang]</TH><TH bgcolor=$color_s width=40>$message[14][$Lang]</TH><TH bgcolor=$color_s width=40>$message[15][$Lang]</TH></TR>\n";
+$count=0;
+foreach $key (@sortsearchwords) {
+ if ( $count>=$MaxNbOfKeywordsShown ) { last; }
+ $p=int($searchwords{$key}/$TotalKeywords*1000)/10;
+ print "<TR align=center><TD align=left>$key</TD><TD>$searchwords{$key}</TD>";
+ print "<TD>$p %</TD></TR>\n";
+ $count++;
+}
+$count=0;$rest=0;
+foreach $key (@sortsearchwords) {
+ if ( $count<$MaxNbOfKeywordsShown ) { $count++; next; }
+ $rest=$rest+$searchwords{$key};
+}
+if ($rest >0) {
+ if ($TotalKeywords > 0) { $p=int($rest/$TotalKeywords*1000)/10; }
+ print "<TR align=center><TD align=left><font color=blue>$message[30][$Lang]</TD><TD>$rest</TD>";
+ print "<TD>$p %</TD></TR>\n";
+ }
+&tab_end;
+
+
+# BY ERRORS
+#----------------------------
+print "<a name=\"ERRORS\"></a><BR>";
+$tab_titre=$message[32][$Lang];
+&tab_head;
+print "<TR BGCOLOR=$color_TableBGRowTitle align=center><TH align=left colspan=2>$message[32][$Lang]</TH><TH bgcolor=$color_h width=40>Hits</TH><TH bgcolor=$color_h width=40>$message[15][$Lang]</TH></TR>\n";
+foreach $key (@sorterrors) {
+ $p=int($errors{$key}/$TotalErrors*1000)/10;
+ if ($httpcode{$key}) { print "<TR align=center onmouseover=\"ShowTooltip($key);\" onmouseout=\"HideTooltip($key);\">"; }
+ else { print "<TR align=center>"; }
+ if ($key == 404) { print "<TD><a href=\"$PROG.pl?action=notfounderror&lang=$Lang\">$key</a></TD>"; }
+ else { print "<TD>$key</TD>"; }
+ if ($httpcode{$key}) { print "<TD align=left>$httpcode{$key}</TD><TD>$errors{$key}</TD><TD>$p %</TD></TR>\n"; }
+ else { print "<TD align=left>Unknown error</TD><TD>$errors{$key}</TD><TD>$p %</TD></TR>\n"; }
+}
+&tab_end;
+
+
+&html_end;
--- /dev/null
+robot-id: Acme.Spider\r
+robot-name: Acme.Spider\r
+robot-cover-url: http://www.acme.com/java/software/Acme.Spider.html\r
+robot-details-url: http://www.acme.com/java/software/Acme.Spider.html\r
+robot-owner-name: Jef Poskanzer - ACME Laboratories\r
+robot-owner-url: http://www.acme.com/\r
+robot-owner-email: jef@acme.com\r
+robot-status: active\r
+robot-purpose: indexing maintenance statistics\r
+robot-type: standalone\r
+robot-platform: java\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Due to a deficiency in Java it's not currently possible to set the User-Agent.\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: Due to a deficiency in Java it's not currently possible to set the User-Agent.\r
+robot-language: java\r
+robot-description: A Java utility class for writing your own robots.\r
+robot-history: \r
+robot-environment: \r
+modified-date: Wed, 04 Dec 1996 21:30:11 GMT\r
+modified-by: Jef Poskanzer\r
+\r
+robot-id: ahoythehomepagefinder\r
+robot-name: Ahoy! The Homepage Finder\r
+robot-cover-url: http://www.cs.washington.edu/research/ahoy/\r
+robot-details-url: http://www.cs.washington.edu/research/ahoy/doc/home.html\r
+robot-owner-name: Marc Langheinrich\r
+robot-owner-url: http://www.cs.washington.edu/homes/marclang\r
+robot-owner-email: marclang@cs.washington.edu\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: ahoy\r
+robot-noindex: no\r
+robot-host: cs.washington.edu\r
+robot-from: no\r
+robot-useragent: 'Ahoy! The Homepage Finder'\r
+robot-language: Perl 5 \r
+robot-description: Ahoy! is an ongoing research project at the\r
+ University of Washington for finding personal Homepages.\r
+robot-history: Research project at the University of Washington in \r
+ 1995/1996 \r
+robot-environment: research\r
+modified-date: Fri June 28 14:00:00 1996\r
+modified-by: Marc Langheinrich\r
+\r
+robot-id: Alkaline\r
+robot-name: Alkaline\r
+robot-cover-url: http://www.vestris.com/alkaline\r
+robot-details-url: http://www.vestris.com/alkaline\r
+robot-owner-name: Daniel Doubrovkine\r
+robot-owner-url: http://cuiwww.unige.ch/~doubrov5 \r
+robot-owner-email: dblock@vestris.com\r
+robot-status: development active\r
+robot-purpose: indexing\r
+robot-type: standalone \r
+robot-platform: unix windows95 windowsNT\r
+robot-availability: binary \r
+robot-exclusion: yes\r
+robot-exclusion-useragent: AlkalineBOT \r
+robot-noindex: yes\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: AlkalineBOT\r
+robot-language: c++\r
+robot-description: Unix/NT internet/intranet search engine\r
+robot-history: Vestris Inc. search engine designed at the University of\r
+ Geneva \r
+robot-environment: commercial research \r
+modified-date: Thu Dec 10 14:01:13 MET 1998\r
+modified-by: Daniel Doubrovkine <dblock@vestris.com>\r
+\r
+robot-id: appie\r
+robot-name: Walhello appie\r
+robot-cover-url: www.walhello.com\r
+robot-details-url: www.walhello.com/aboutgl.html\r
+robot-owner-name: Aimo Pieterse\r
+robot-owner-url: www.walhello.com\r
+robot-owner-email: aimo@walhello.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: windows98\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: appie\r
+robot-noindex: yes\r
+robot-host: 213.10.10.116, 213.10.10.117, 213.10.10.118\r
+robot-from: yes\r
+robot-useragent: appie/1.1\r
+robot-language: Visual C++\r
+robot-description: The appie-spider is used to collect and index web pages for\r
+ the Walhello search engine\r
+robot-history: The spider was built in march/april 2000\r
+robot-environment: commercial\r
+modified-date: Thu, 20 Jul 2000 22:38:00 GMT\r
+modified-by: Aimo Pieterse\r
+\r
+robot-id: arachnophilia\r
+robot-name: Arachnophilia\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Vince Taluskie\r
+robot-owner-url: http://www.ph.utexas.edu/people/vince.html\r
+robot-owner-email: taluskie@utpapa.ph.utexas.edu\r
+robot-status: \r
+robot-purpose: \r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: halsoft.com\r
+robot-from: \r
+robot-useragent: Arachnophilia\r
+robot-language: \r
+robot-description: The purpose (undertaken by HaL Software) of this run was to\r
+ collect approximately 10k html documents for testing\r
+ automatic abstract generation\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: architext\r
+robot-name: ArchitextSpider\r
+robot-cover-url: http://www.excite.com/\r
+robot-details-url:\r
+robot-owner-name: Architext Software\r
+robot-owner-url: http://www.atext.com/spider.html\r
+robot-owner-email: spider@atext.com\r
+robot-status: \r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *.atext.com\r
+robot-from: yes\r
+robot-useragent: ArchitextSpider\r
+robot-language: perl 5 and c\r
+robot-description: Its purpose is to generate a Resource Discovery database,\r
+ and to generate statistics. The ArchitextSpider collects\r
+ information for the Excite and WebCrawler search engines.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Tue Oct 3 01:10:26 1995\r
+modified-by:\r
+\r
+robot-id: aretha\r
+robot-name: Aretha\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Dave Weiner\r
+robot-owner-url: http://www.hotwired.com/Staff/userland/ \r
+robot-owner-email: davew@well.com\r
+robot-status: \r
+robot-purpose: \r
+robot-type: \r
+robot-platform: Macintosh\r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: \r
+robot-host: \r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: A crude robot built on top of Netscape and Userland\r
+ Frontier, a scripting system for Macs\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: ariadne\r
+robot-name: ARIADNE\r
+robot-cover-url: (forthcoming)\r
+robot-details-url: (forthcoming)\r
+robot-owner-name: Mr. Matthias H. Gross\r
+robot-owner-url: http://www.lrz-muenchen.de/~gross/\r
+robot-owner-email: Gross@dbs.informatik.uni-muenchen.de\r
+robot-status: development\r
+robot-purpose: statistics, development of focused crawling strategies\r
+robot-type: standalone\r
+robot-platform: java\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: ariadne\r
+robot-noindex: no\r
+robot-host: dbs.informatik.uni-muenchen.de\r
+robot-from: no\r
+robot-useragent: Due to a deficiency in Java it's not currently possible\r
+ to set the User-Agent.\r
+robot-language: java\r
+robot-description: The ARIADNE robot is a prototype of a environment for\r
+ testing focused crawling strategies.\r
+robot-history: This robot is part of a research project at the\r
+ University of Munich (LMU), started in 2000.\r
+robot-environment: research\r
+modified-date: Mo, 13 Mar 2000 14:00:00 GMT\r
+modified-by: Mr. Matthias H. Gross\r
+\r
+robot-id: aspider\r
+robot-name: ASpider (Associative Spider)\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Fred Johansen\r
+robot-owner-url: http://www.pvv.ntnu.no/~fredj/\r
+robot-owner-email: fredj@pvv.ntnu.no\r
+robot-status: retired\r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: unix\r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: nova.pvv.unit.no\r
+robot-from: yes\r
+robot-useragent: ASpider/0.09\r
+robot-language: perl4\r
+robot-description: ASpider is a CGI script that searches the web for keywords given by the user through a form.\r
+robot-history: \r
+robot-environment: hobby\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: atn.txt\r
+robot-name: ATN Worldwide\r
+robot-details-url:\r
+robot-cover-url:\r
+robot-owner-name: All That Net\r
+robot-owner-url: http://www.allthatnet.com\r
+robot-owner-email: info@allthatnet.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type:\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: ATN_Worldwide\r
+robot-noindex:\r
+robot-nofollow:\r
+robot-host: www.allthatnet.com\r
+robot-from:\r
+robot-useragent: ATN_Worldwide\r
+robot-language:\r
+robot-description: The ATN robot is used to build the database for the\r
+ AllThatNet search service operated by All That Net. The robot runs weekly,\r
+ and visits sites in a random order.\r
+robot-history:\r
+robot-environment:\r
+modified-date: July 09, 2000 17:43 GMT\r
+\r
+robot-id: atomz\r
+robot-name: Atomz.com Search Robot\r
+robot-cover-url: http://www.atomz.com/help/\r
+robot-details-url: http://www.atomz.com/\r
+robot-owner-name: Mike Thompson\r
+robot-owner-url: http://www.atomz.com/\r
+robot-owner-email: mike@atomz.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: service\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Atomz\r
+robot-noindex: yes\r
+robot-host: www.atomz.com\r
+robot-from: no\r
+robot-useragent: Atomz/1.0\r
+robot-language: c\r
+robot-description: Robot used for web site search service.\r
+robot-history: Developed for Atomz.com, launched in 1999.\r
+robot-environment: service\r
+modified-date: Tue Jul 13 03:50:06 GMT 1999\r
+modified-by: Mike Thompson\r
+\r
+robot-id: auresys\r
+robot-name: AURESYS\r
+robot-cover-url: http://crrm.univ-mrs.fr\r
+robot-details-url: http://crrm.univ-mrs.fr \r
+robot-owner-name: Mannina Bruno \r
+robot-owner-url: ftp://crrm.univ-mrs.fr/pub/CVetud/Etudiants/Mannina/CVbruno.htm \r
+robot-owner-email: mannina@crrm.univ-mrs.fr \r
+robot-status: robot actively in use\r
+robot-purpose: indexing,statistics\r
+robot-type: Standalone\r
+robot-platform: Aix, Unix\r
+robot-availability: Protected by Password\r
+robot-exclusion: Yes\r
+robot-exclusion-useragent: \r
+robot-noindex: no\r
+robot-host: crrm.univ-mrs.fr, 192.134.99.192\r
+robot-from: Yes\r
+robot-useragent: AURESYS/1.0\r
+robot-language: Perl 5.001m\r
+robot-description: The AURESYS is used to build a personnal database for \r
+ somebody who search information. The database is structured to be \r
+ analysed. AURESYS can found new server by IP incremental. It generate \r
+ statistics... \r
+robot-history: This robot finds its roots in a research project at the \r
+ University of Marseille in 1995-1996\r
+robot-environment: used for Research\r
+modified-date: Mon, 1 Jul 1996 14:30:00 GMT \r
+modified-by: Mannina Bruno\r
+\r
+robot-id: backrub\r
+robot-name: BackRub\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Larry Page\r
+robot-owner-url: http://backrub.stanford.edu/\r
+robot-owner-email: page@leland.stanford.edu\r
+robot-status:\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: *.stanford.edu\r
+robot-from: yes\r
+robot-useragent: BackRub/*.*\r
+robot-language: Java.\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Wed Feb 21 02:57:42 1996.\r
+modified-by:\r
+\r
+robot-id: bigbrother\r
+robot-name: Big Brother\r
+robot-cover-url: http://pauillac.inria.fr/~fpottier/mac-soft.html.en\r
+robot-details-url:\r
+robot-owner-name: Francois Pottier\r
+robot-owner-url: http://pauillac.inria.fr/~fpottier/\r
+robot-owner-email: Francois.Pottier@inria.fr\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: mac\r
+robot-availability: binary\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: not as of 1.0\r
+robot-useragent: Big Brother\r
+robot-language: c++\r
+robot-description: Macintosh-hosted link validation tool.\r
+robot-history:\r
+robot-environment: shareware\r
+modified-date: Thu Sep 19 18:01:46 MET DST 1996\r
+modified-by: Francois Pottier\r
+\r
+robot-id: bjaaland\r
+robot-name: Bjaaland\r
+robot-cover-url: http://www.textuality.com\r
+robot-details-url: http://www.textuality.com\r
+robot-owner-name: Tim Bray\r
+robot-owner-url: http://www.textuality.com\r
+robot-owner-email: tbray@textuality.com\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Bjaaland\r
+robot-noindex: no\r
+robot-host: barry.bitmovers.net\r
+robot-from: no\r
+robot-useragent: Bjaaland/0.5\r
+robot-language: perl5\r
+robot-description: Crawls sites listed in the ODP (see http://dmoz.org)\r
+robot-history: None, yet\r
+robot-environment: service\r
+modified-date: Monday, 19 July 1999, 13:46:00 PDT\r
+modified-by: tbray@textuality.com\r
+\r
+robot-id: blackwidow\r
+robot-name: BlackWidow\r
+robot-cover-url: http://140.190.65.12/~khooghee/index.html\r
+robot-details-url:\r
+robot-owner-name: Kevin Hoogheem\r
+robot-owner-url:\r
+robot-owner-email: khooghee@marys.smumn.edu\r
+robot-status:\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: 140.190.65.*\r
+robot-from: yes\r
+robot-useragent: BlackWidow\r
+robot-language: C, C++.\r
+robot-description: Started as a research project and now is used to find links\r
+ for a random link generator. Also is used to research the\r
+ growth of specific sites.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Fri Feb 9 00:11:22 1996.\r
+modified-by:\r
+\r
+robot-id: blindekuh\r
+robot-name: Die Blinde Kuh\r
+robot-cover-url: http://www.blinde-kuh.de/\r
+robot-details-url: http://www.blinde-kuh.de/robot.html (german language)\r
+robot-owner-name: Stefan R. Mueller\r
+robot-owner-url: http://www.rrz.uni-hamburg.de/philsem/stefan_mueller/\r
+robot-owner-email:maschinist@blinde-kuh.de\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: browser\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: minerva.sozialwiss.uni-hamburg.de\r
+robot-from: yes\r
+robot-useragent: Die Blinde Kuh\r
+robot-language: perl5\r
+robot-description: The robot is use for indixing and proofing the\r
+ registered urls in the german language search-engine for kids.\r
+ Its a none-comercial one-woman-project of Birgit Bachmann\r
+ living in Hamburg, Germany.\r
+robot-history: The robot was developed by Stefan R. Mueller\r
+ to help by the manual proof of registered Links.\r
+robot-environment: hobby\r
+modified-date: Mon Jul 22 1998\r
+modified-by: Stefan R. Mueller\r
+\r
+robot-id:Bloodhound\r
+robot-name:Bloodhound\r
+robot-cover-url:http://web.ukonline.co.uk/genius/bloodhound.htm\r
+robot-details-url:http://web.ukonline.co.uk/genius/bloodhound.htm\r
+robot-owner-name:Dean Smart\r
+robot-owner-url:http://web.ukonline.co.uk/genius/bloodhound.htm\r
+robot-owner-email:genius@ukonline.co.uk\r
+robot-status:active\r
+robot-purpose:Web Site Download\r
+robot-type:standalone\r
+robot-platform:Windows95, WindowsNT, Windows98, Windows2000\r
+robot-availability:Executible\r
+robot-exclusion:No\r
+robot-exclusion-useragent:Ukonline\r
+robot-noindex:No\r
+robot-host:*\r
+robot-from:No\r
+robot-useragent:None\r
+robot-language:Perl5\r
+robot-description:Bloodhound will download an whole web site depending on the\r
+ number of links to follow specified by the user.\r
+robot-history:First version was released on the 1 july 2000\r
+robot-environment:Commercial\r
+modified-date:1 july 2000\r
+modified-by:Dean Smart\r
+\r
+robot-id: brightnet\r
+robot-name: bright.net caching robot\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name:\r
+robot-owner-url:\r
+robot-owner-email:\r
+robot-status: active \r
+robot-purpose: caching \r
+robot-type:\r
+robot-platform: \r
+robot-availability: none\r
+robot-exclusion: no\r
+robot-noindex:\r
+robot-host: 209.143.1.46\r
+robot-from: no\r
+robot-useragent: Mozilla/3.01 (compatible;)\r
+robot-language:\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Fri Nov 13 14:08:01 EST 1998\r
+modified-by: brian d foy <comdog@computerdog.com>\r
+\r
+robot-id: bspider\r
+robot-name: BSpider\r
+robot-cover-url: not yet\r
+robot-details-url: not yet\r
+robot-owner-name: Yo Okumura\r
+robot-owner-url: not yet\r
+robot-owner-email: okumura@rsl.crl.fujixerox.co.jp\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: bspider\r
+robot-noindex: yes\r
+robot-host: 210.159.73.34, 210.159.73.35\r
+robot-from: yes\r
+robot-useragent: BSpider/1.0 libwww-perl/0.40\r
+robot-language: perl\r
+robot-description: BSpider is crawling inside of Japanese domain for indexing.\r
+robot-history: Starts Apr 1997 in a research project at Fuji Xerox Corp.\r
+ Research Lab.\r
+robot-environment: research\r
+modified-date: Mon, 21 Apr 1997 18:00:00 JST\r
+modified-by: Yo Okumura\r
+\r
+robot-id: cactvschemistryspider\r
+robot-name: CACTVS Chemistry Spider\r
+robot-cover-url: http://schiele.organik.uni-erlangen.de/cactvs/spider.html\r
+robot-details-url:\r
+robot-owner-name: W. D. Ihlenfeldt\r
+robot-owner-url: http://schiele.organik.uni-erlangen.de/cactvs/\r
+robot-owner-email: wdi@eros.ccc.uni-erlangen.de\r
+robot-status:\r
+robot-purpose: indexing.\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: utamaro.organik.uni-erlangen.de\r
+robot-from: no\r
+robot-useragent: CACTVS Chemistry Spider\r
+robot-language: TCL, C\r
+robot-description: Locates chemical structures in Chemical MIME formats on WWW\r
+ and FTP servers and downloads them into database searchable\r
+ with structure queries (substructure, fullstructure,\r
+ formula, properties etc.)\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sat Mar 30 00:55:40 1996.\r
+modified-by:\r
+\r
+robot-id: calif\r
+robot-name: Calif\r
+robot-details-url: http://www.tnps.dp.ua/calif/details.html\r
+robot-cover-url: http://www.tnps.dp.ua/calif/\r
+robot-owner-name: Alexander Kosarev\r
+robot-owner-url: http://www.tnps.dp.ua/~dark/\r
+robot-owner-email: kosarev@tnps.net\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: calif\r
+robot-noindex: yes\r
+robot-host: cobra.tnps.dp.ua\r
+robot-from: yes\r
+robot-useragent: Calif/0.6 (kosarev@tnps.net; http://www.tnps.dp.ua)\r
+robot-language: c++\r
+robot-description: Used to build searchable index\r
+robot-history: In development stage\r
+robot-environment: research\r
+modified-date: Sun, 6 Jun 1999 13:25:33 GMT\r
+\r
+robot-id: cassandra\r
+robot-name: Cassandra\r
+robot-cover-url: http://post.mipt.rssi.ru/~billy/search/\r
+robot-details-url: http://post.mipt.rssi.ru/~billy/search/\r
+robot-owner-name: Mr. Oleg Bilibin\r
+robot-owner-url: http://post.mipt.rssi.ru/~billy/\r
+robot-owner-email: billy168@aha.ru\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: crossplatform\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: www.aha.ru\r
+robot-from: no\r
+robot-useragent:\r
+robot-language: java\r
+robot-description: Cassandra search robot is used to create and maintain indexed database for widespread Information Retrieval System\r
+robot-history: Master of Science degree project at Moscow Institute of Physics and Technology\r
+robot-environment: research\r
+modified-date: Wed, 3 Jun 1998 12:00:00 GMT\r
+\r
+robot-id: cgireader\r
+robot-name: Digimarc Marcspider/CGI\r
+robot-cover-url: http://www.digimarc.com/prod_fam.html\r
+robot-details-url: http://www.digimarc.com/prod_fam.html\r
+robot-owner-name: Digimarc Corporation\r
+robot-owner-url: http://www.digimarc.com\r
+robot-owner-email: wmreader@digimarc.com\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: 206.102.3.*\r
+robot-from:\r
+robot-useragent: Digimarc CGIReader/1.0\r
+robot-language: c++\r
+robot-description: Similar to Digimarc Marcspider, Marcspider/CGI examines\r
+ image files for watermarks but more focused on CGI Urls.\r
+ In order to not waste internet bandwidth with yet another crawler,\r
+ we have contracted with one of the major crawlers/seach engines\r
+ to provide us with a list of specific CGI URLs of interest to us.\r
+ If an URL is to a page of interest (via CGI), then we access the\r
+ page to get the image URLs from it, but we do not crawl to\r
+ any other pages.\r
+robot-history: First operation in December 1997\r
+robot-environment: service\r
+modified-date: Fri, 5 Dec 1997 12:00:00 GMT\r
+modified-by: Dan Ramos\r
+\r
+robot-id: checkbot\r
+robot-name: Checkbot\r
+robot-cover-url: http://www.xs4all.nl/~graaff/checkbot/\r
+robot-details-url:\r
+robot-owner-name: Hans de Graaff\r
+robot-owner-url: http://www.xs4all.nl/~graaff/checkbot/\r
+robot-owner-email: graaff@xs4all.nl\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: unix,WindowsNT\r
+robot-availability: source\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: Checkbot/x.xx LWP/5.x\r
+robot-language: perl 5\r
+robot-description: Checkbot checks links in a\r
+ given set of pages on one or more servers. It reports links\r
+ which returned an error code\r
+robot-history: \r
+robot-environment: hobby\r
+modified-date: Tue Jun 25 07:44:00 1996\r
+modified-by: Hans de Graaff\r
+\r
+robot-id: churl\r
+robot-name: churl\r
+robot-cover-url: http://www-personal.engin.umich.edu/~yunke/scripts/churl/\r
+robot-details-url:\r
+robot-owner-name: Justin Yunke\r
+robot-owner-url: http://www-personal.engin.umich.edu/~yunke/\r
+robot-owner-email: yunke@umich.edu\r
+robot-status: \r
+robot-purpose: maintenance\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: A URL checking robot, which stays within one step of the\r
+ local server\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: cmc\r
+robot-name: CMC/0.01\r
+robot-details-url: http://www2.next.ne.jp/cgi-bin/music/help.cgi?phase=robot\r
+robot-cover-url: http://www2.next.ne.jp/music/\r
+robot-owner-name: Shinobu Kubota.\r
+robot-owner-url: http://www2.next.ne.jp/cgi-bin/music/help.cgi?phase=profile\r
+robot-owner-email: shinobu@po.next.ne.jp\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: CMC/0.01\r
+robot-noindex: no\r
+robot-host: haruna.next.ne.jp, 203.183.218.4\r
+robot-from: yes\r
+robot-useragent: CMC/0.01\r
+robot-language: perl5\r
+robot-description: This CMC/0.01 robot collects the information\r
+ of the page that was registered to the music\r
+ specialty searching service.\r
+robot-history: This CMC/0.01 robot was made for the computer\r
+ music center on November 4, 1997.\r
+robot-environment: hobby\r
+modified-date: Sat, 23 May 1998 17:22:00 GMT\r
+\r
+robot-id:Collective\r
+robot-name:Collective\r
+robot-cover-url:http://web.ukonline.co.uk/genius/collective.htm\r
+robot-details-url:http://web.ukonline.co.uk/genius/collective.htm\r
+robot-owner-name:Dean Smart\r
+robot-owner-url:http://web.ukonline.co.uk/genius/collective.htm\r
+robot-owner-email:genius@ukonline.co.uk\r
+robot-status:development\r
+robot-purpose:Collective is a highly configurable program designed to interrogate\r
+ online search engines and online databases, it will ignore web pages\r
+ that lie about there content, and dead url's, it can be super strict, it searches each web page\r
+ it finds for your search terms to ensure those terms are present, any positive urls are added to\r
+ a html file for your to view at any time even before the program has finished.\r
+ Collective can wonder the web for days if required.\r
+robot-type:standalone\r
+robot-platform:Windows95, WindowsNT, Windows98, Windows2000\r
+robot-availability:Executible\r
+robot-exclusion:No\r
+robot-exclusion-useragent:\r
+robot-noindex:No\r
+robot-host:*\r
+robot-from:No\r
+robot-useragent:LWP\r
+robot-language:Perl5 (With Visual Basic front-end)\r
+robot-description:Collective is the most cleverest Internet search engine,\r
+ With all found url?s guaranteed to have your search terms.\r
+robot-history:Develpment started on August, 03, 2000\r
+robot-environment:Commercial\r
+modified-date:August, 03, 2000\r
+modified-by:Dean Smart\r
+\r
+robot-id: combine\r
+robot-name: Combine System\r
+robot-cover-url: http://www.ub2.lu.se/~tsao/combine.ps\r
+robot-details-url: http://www.ub2.lu.se/~tsao/combine.ps\r
+robot-owner-name: Yong Cao\r
+robot-owner-url: http://www.ub2.lu.se/\r
+robot-owner-email: tsao@munin.ub2.lu.se\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: combine\r
+robot-noindex: no\r
+robot-host: *.ub2.lu.se\r
+robot-from: yes\r
+robot-useragent: combine/0.0\r
+robot-language: c, perl5\r
+robot-description: An open, distributed, and efficient harvester.\r
+robot-history: A complete re-design of the NWI robot (w3index) for DESIRE project. \r
+robot-environment: research\r
+modified-date: Tue, 04 Mar 1997 16:11:40 GMT\r
+modified-by: Yong Cao\r
+\r
+robot-id: conceptbot\r
+robot-name: Conceptbot\r
+robot-cover-url: http://www.aptltd.com/~sifry/conceptbot/tech.html\r
+robot-details-url: http://www.aptltd.com/~sifry/conceptbot\r
+robot-owner-name: David L. Sifry\r
+robot-owner-url: http://www.aptltd.com/~sifry\r
+robot-owner-email: david@sifry.com\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: conceptbot\r
+robot-noindex: yes\r
+robot-host: router.sifry.com\r
+robot-from: yes\r
+robot-useragent: conceptbot/0.3\r
+robot-language: perl5\r
+robot-description:The Conceptbot spider is used to research\r
+ concept-based search indexing techniques. It uses a breadth first seach\r
+ to spread out the number of hits on a single site over time. The spider\r
+ runs at irregular intervals and is still under construction.\r
+robot-history: This spider began as a research project at Sifry\r
+ Consulting in April 1996.\r
+robot-environment: research\r
+modified-date: Mon, 9 Sep 1996 15:31:07 GMT\r
+modified-by: David L. Sifry <david@sifry.com>\r
+\r
+robot-id: core\r
+robot-name: Web Core / Roots\r
+robot-cover-url: http://www.di.uminho.pt/wc\r
+robot-details-url:\r
+robot-owner-name: Jorge Portugal Andrade\r
+robot-owner-url: http://www.di.uminho.pt/~cbm\r
+robot-owner-email: wc@di.uminho.pt\r
+robot-status:\r
+robot-purpose: indexing, maintenance\r
+robot-type:\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: shiva.di.uminho.pt, from www.di.uminho.pt\r
+robot-from: no\r
+robot-useragent: root/0.1\r
+robot-language: perl\r
+robot-description: Parallel robot developed in Minho Univeristy in Portugal to\r
+ catalog relations among URLs and to support a special\r
+ navigation aid.\r
+robot-history: First versions since October 1995.\r
+robot-environment:\r
+modified-date: Wed Jan 10 23:19:08 1996.\r
+modified-by:\r
+\r
+robot-id: cshkust\r
+robot-name: CS-HKUST WISE: WWW Index and Search Engine\r
+robot-cover-url: http://www.cs.ust.hk/IndexServer/\r
+robot-details-url:\r
+robot-owner-name: Budi Yuwono\r
+robot-owner-url: http://www.cis.ohio-state.edu/~yuwono-b/\r
+robot-owner-email: yuwono-b@cs.ust.hk\r
+robot-status: \r
+robot-purpose: \r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: dbx.cs.ust.hk\r
+robot-from: yes\r
+robot-useragent: CS-HKUST-IndexServer/1.0\r
+robot-language: c\r
+robot-description: Its purpose is to generate a Resource Discovery database,\r
+ and validate HTML. Part of an on-going research project on\r
+ Internet Resource Discovery at Department of Computer\r
+ Science, Hong Kong University of Science and Technology\r
+ (CS-HKUST)\r
+robot-history: \r
+robot-environment:\r
+modified-date: Tue Jun 20 02:39:16 1995\r
+modified-by:\r
+\r
+robot-id: cusco\r
+robot-name: Cusco\r
+robot-cover-url: http://www.cusco.pt/\r
+robot-details-url: http://www.cusco.pt/\r
+robot-owner-name: Filipe Costa Clerigo\r
+robot-owner-url: http://www.viatecla.pt/\r
+robot-owner-email: clerigo@viatecla.pt\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standlone\r
+robot-platform: any\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: cusco\r
+robot-noindex: yes\r
+robot-host: *.cusco.pt, *.viatecla.pt\r
+robot-from: yes\r
+robot-useragent: Cusco/3.2\r
+robot-language: Java\r
+robot-description: The Cusco robot is part of the CUCE indexing sistem. It\r
+ gathers information from several sources: HTTP, Databases or filesystem. At\r
+ this moment, it's universe is the .pt domain and the information it gathers\r
+ is available at the Portuguese search engine Cusco http://www.cusco.pt/.\r
+robot-history: The Cusco search engine started in the company ViaTecla as a\r
+ project to demonstrate our development capabilities and to fill the need of\r
+ a portuguese-specific search engine. Now, we are developping new\r
+ functionalities that cannot be found in any other on-line search engines.\r
+robot-environment:service, research\r
+modified-date: Mon, 21 Jun 1999 14:00:00 GMT\r
+modified-by: Filipe Costa Clerigo\r
+\r
+robot-id: cyberspyder\r
+robot-name: CyberSpyder Link Test\r
+robot-cover-url: http://www.cyberspyder.com/cslnkts1.html\r
+robot-details-url: http://www.cyberspyder.com/cslnkts1.html\r
+robot-owner-name: Tom Aman\r
+robot-owner-url: http://www.cyberspyder.com/\r
+robot-owner-email: amant@cyberspyder.com\r
+robot-status: active\r
+robot-purpose: link validation, some html validation\r
+robot-type: standalone\r
+robot-platform: windows 3.1x, windows95, windowsNT\r
+robot-availability: binary\r
+robot-exclusion: user configurable\r
+robot-exclusion-useragent: cyberspyder\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: CyberSpyder/2.1\r
+robot-language: Microsoft Visual Basic 4.0\r
+robot-description: CyberSpyder Link Test is intended to be used as a site\r
+ management tool to validate that HTTP links on a page are functional and to\r
+ produce various analysis reports to assist in managing a site.\r
+robot-history: The original robot was created to fill a widely seen need\r
+ for a easy to use link checking program.\r
+robot-environment: commercial\r
+modified-date: Tue, 31 Mar 1998 01:02:00 GMT\r
+modified-by: Tom Aman\r
+\r
+robot-id: deweb\r
+robot-name: DeWeb(c) Katalog/Index\r
+robot-cover-url: http://deweb.orbit.de/\r
+robot-details-url:\r
+robot-owner-name: Marc Mielke\r
+robot-owner-url: http://www.orbit.de/\r
+robot-owner-email: dewebmaster@orbit.de\r
+robot-status: \r
+robot-purpose: indexing, mirroring, statistics\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: deweb.orbit.de\r
+robot-from: yes\r
+robot-useragent: Deweb/1.01\r
+robot-language: perl 4\r
+robot-description: Its purpose is to generate a Resource Discovery database,\r
+ perform mirroring, and generate statistics. Uses combination\r
+ of Informix(tm) Database and WN 1.11 serversoftware for\r
+ indexing/ressource discovery, fulltext search, text\r
+ excerpts.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Wed Jan 10 08:23:00 1996\r
+modified-by:\r
+\r
+robot-id: dienstspider\r
+robot-name: DienstSpider\r
+robot-cover-url: http://sappho.csi.forth.gr:22000/\r
+robot-details-url:\r
+robot-owner-name: Antonis Sidiropoulos \r
+robot-owner-url: http://www.csi.forth.gr/~asidirop\r
+robot-owner-email: asidirop@csi.forth.gr\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone \r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion:\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: sappho.csi.forth.gr \r
+robot-from:\r
+robot-useragent: dienstspider/1.0 \r
+robot-language: C\r
+robot-description: Indexing and searching the NCSTRL(Networked Computer Science Technical Report Library) and ERCIM Collection\r
+robot-history: The version 1.0 was the developer's master thesis project\r
+robot-environment: research\r
+modified-date: Fri, 4 Dec 1998 0:0:0 GMT\r
+modified-by: asidirop@csi.forth.gr\r
+\r
+robot-id: diibot\r
+robot-name: Digital Integrity Robot\r
+robot-cover-url: http://www.digital-integrity.com/robotinfo.html\r
+robot-details-url: http://www.digital-integrity.com/robotinfo.html\r
+robot-owner-name: Digital Integrity, Inc.\r
+robot-owner-url: \r
+robot-owner-email: robot@digital-integrity.com\r
+robot-status: Production\r
+robot-purpose: WWW Indexing\r
+robot-type:\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: Conforms to robots.txt convention\r
+robot-exclusion-useragent: DIIbot\r
+robot-noindex: Yes\r
+robot-host: digital-integrity.com\r
+robot-from:\r
+robot-useragent: DIIbot\r
+robot-language: Java/C\r
+robot-description:\r
+robot-history: \r
+robot-environment:\r
+modified-date:\r
+modified-by:\r
+\r
+robot-id: directhit\r
+robot-name: Direct Hit Grabber\r
+robot-cover-url: www.directhit.com\r
+robot-details-url: http://www.directhit.com/about/company/spider.html\r
+robot-status: active\r
+robot-description: Direct Hit Grabber indexes documents and\r
+ collects Web statistics for the Direct Hit Search Engine (available at\r
+ www.directhit.com and our partners' sites)\r
+robot-purpose: Indexing and statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-language: C++\r
+robot-owner-name: Direct Hit Technologies, Inc.\r
+robot-owner-url: www.directhit.com\r
+robot-owner-email: DirectHitGrabber@directhit.com\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: grabber\r
+robot-noindex: yes\r
+robot-host: *.directhit.com\r
+robot-from: yes\r
+robot-useragent: grabber\r
+robot-environment: service\r
+modified-by: grabber@directhit.com\r
+\r
+robot-id: dnabot\r
+robot-name: DNAbot\r
+robot-cover-url: http://xx.dnainc.co.jp/dnabot/\r
+robot-details-url: http://xx.dnainc.co.jp/dnabot/\r
+robot-owner-name: Tom Tanaka\r
+robot-owner-url: http://xx.dnainc.co.jp\r
+robot-owner-email: tomatell@xx.dnainc.co.jp\r
+robot-status: development \r
+robot-purpose: indexing \r
+robot-type: standalone \r
+robot-platform: unix, windows, windows95, windowsNT, mac\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: xx.dnainc.co.jp\r
+robot-from: yes \r
+robot-useragent: DNAbot/1.0\r
+robot-language: java \r
+robot-description: A search robot in 100 java, with its own built-in\r
+ database engine and web server . Currently in Japanese.\r
+robot-history: Developed by DNA, Inc.(Niigata City, Japan) in 1998.\r
+robot-environment: commercial\r
+modified-date: Mon, 4 Jan 1999 14:30:00 GMT\r
+modified-by: Tom Tanaka\r
+\r
+robot-id: download_express\r
+robot-name: DownLoad Express\r
+robot-cover-url: http://www.jacksonville.net/~dlxpress\r
+robot-details-url: http://www.jacksonville.net/~dlxpress\r
+robot-owner-name: DownLoad Express Inc\r
+robot-owner-url: http://www.jacksonville.net/~dlxpress\r
+robot-owner-email: dlxpress@mediaone.net\r
+robot-status: active\r
+robot-purpose: graphic download\r
+robot-type: standalone\r
+robot-platform: win95/98/NT\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: downloadexpress\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent:\r
+robot-language: visual basic\r
+robot-description: automatically downloads graphics from the web\r
+robot-history:\r
+robot-environment: commerical\r
+modified-date: Wed, 05 May 1998\r
+modified-by: DownLoad Express Inc\r
+\r
+robot-id: dragonbot\r
+robot-name: DragonBot\r
+robot-cover-url: http://www.paczone.com/\r
+robot-details-url:\r
+robot-owner-name: Paul Law\r
+robot-owner-url:\r
+robot-owner-email: admin@paczone.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: DragonBot\r
+robot-noindex: no\r
+robot-host: *.paczone.com\r
+robot-from: no\r
+robot-useragent: DragonBot/1.0 libwww/5.0\r
+robot-language: C++\r
+robot-description: Collects web pages related to East Asia\r
+robot-history:\r
+robot-environment: service\r
+modified-date: Mon, 11 Aug 1997 00:00:00 GMT\r
+modified-by:\r
+\r
+robot-id: dwcp\r
+robot-name: DWCP (Dridus' Web Cataloging Project)\r
+robot-cover-url: http://www.dridus.com/~rmm/dwcp.php3\r
+robot-details-url: http://www.dridus.com/~rmm/dwcp.php3\r
+robot-owner-name: Ross Mellgren (Dridus Norwind)\r
+robot-owner-url: http://www.dridus.com/~rmm\r
+robot-owner-email: rmm@dridus.com\r
+robot-status: development\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: java\r
+robot-availability: source, binary, data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: dwcp\r
+robot-noindex: no\r
+robot-host: *.dridus.com\r
+robot-from: dridus@dridus.com\r
+robot-useragent: DWCP/2.0\r
+robot-language: java\r
+robot-description: The DWCP robot is used to gather information for\r
+ Dridus' Web Cataloging Project, which is intended to catalog domains and\r
+ urls (no content).\r
+robot-history: Developed from scratch by Dridus Norwind.\r
+robot-environment: hobby\r
+modified-date: Sat, 10 Jul 1999 00:05:40 GMT\r
+modified-by: Ross Mellgren\r
+\r
+robot-id: ebiness\r
+robot-name: EbiNess\r
+robot-cover-url: http://www.carisbrook.co.uk/ebiness/\r
+robot-details-url: http://www.carisbrook.co.uk/ebiness/tech/\r
+robot-owner-name: Mike Davis\r
+robot-owner-url: http://www.carisbrook.co.uk/mike/\r
+robot-owner-email: mdavis@kieser.net\r
+robot-status: development\r
+robot-purpose: statistics\r
+robot-type: standalone\r
+robot-platform: unix(Linux)\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: ebiness\r
+robot-noindex: no\r
+robot-host:\r
+robot-from: no\r
+robot-useragent: EbiNess/0.01a\r
+robot-language: c++\r
+robot-description: Used to build a url relationship database, to be \r
+ viewed in 3D\r
+robot-history: Dreamed it up over some beers\r
+robot-environment: hobby\r
+modified-date: Mon, 29 May 2000 01:37:00 GMT\r
+modified-by: Mike Davis\r
+\r
+robot-id: eit\r
+robot-name: EIT Link Verifier Robot\r
+robot-cover-url: http://wsk.eit.com/wsk/dist/doc/admin/webtest/verify_links.html\r
+robot-details-url:\r
+robot-owner-name: Jim McGuire\r
+robot-owner-url: http://www.eit.com/people/mcguire.html\r
+robot-owner-email: mcguire@eit.COM\r
+robot-status: \r
+robot-purpose: maintenance\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: \r
+robot-useragent: EIT-Link-Verifier-Robot/0.2\r
+robot-language: \r
+robot-description: Combination of an HTML form and a CGI script that verifies\r
+ links from a given starting point (with some controls to\r
+ prevent it going off-site or limitless)\r
+robot-history: Announced on 12 July 1994\r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: emacs\r
+robot-name: Emacs-w3 Search Engine\r
+robot-cover-url: http://www.cs.indiana.edu/elisp/w3/docs.html\r
+robot-details-url:\r
+robot-owner-name: William M. Perry\r
+robot-owner-url: http://www.cs.indiana.edu/hyplan/wmperry.html\r
+robot-owner-email: wmperry@spry.com\r
+robot-status: retired\r
+robot-purpose: indexing\r
+robot-type: browser\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: Emacs-w3/v[0-9\.]+\r
+robot-language: lisp\r
+robot-description: Its purpose is to generate a Resource Discovery database\r
+ This code has not been looked at in a while, but will be\r
+ spruced up for the Emacs-w3 2.2.0 release sometime this\r
+ month. It will honor the /robots.txt file at that\r
+ time.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Fri May 5 16:09:18 1995\r
+modified-by:\r
+\r
+robot-id: emcspider\r
+robot-name: ananzi\r
+robot-cover-url: http://www.empirical.com/\r
+robot-details-url:\r
+robot-owner-name: Hunter Payne\r
+robot-owner-url: http://www.psc.edu/~hpayne/\r
+robot-owner-email: hpayne@u-media.com\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: bilbo.internal.empirical.com\r
+robot-from: yes\r
+robot-useragent: EMC Spider\r
+robot-language: java This spider is still in the development stages but, it\r
+ will be hitting sites while I finish debugging it.\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Wed May 29 14:47:01 1996.\r
+modified-by:\r
+\r
+robot-id: esther\r
+robot-name: Esther\r
+robot-details-url: http://search.falconsoft.com/\r
+robot-cover-url: http://search.falconsoft.com/\r
+robot-owner-name: Tim Gustafson\r
+robot-owner-url: http://www.falconsoft.com/\r
+robot-owner-email: tim@falconsoft.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix (FreeBSD 2.2.8)\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: esther\r
+robot-noindex: no\r
+robot-host: *.falconsoft.com\r
+robot-from: yes\r
+robot-useragent: esther\r
+robot-language: perl5\r
+robot-description: This crawler is used to build the search database at\r
+ http://search.falconsoft.com/\r
+robot-history: Developed by FalconSoft.\r
+robot-environment: service\r
+modified-date: Tue, 22 Dec 1998 00:22:00 PST\r
+\r
+robot-id: evliyacelebi\r
+robot-name: Evliya Celebi\r
+robot-cover-url: http://ilker.ulak.net.tr/EvliyaCelebi\r
+robot-details-url: http://ilker.ulak.net.tr/EvliyaCelebi\r
+robot-owner-name: Ilker TEMIR\r
+robot-owner-url: http://ilker.ulak.net.tr\r
+robot-owner-email: ilker@ulak.net.tr\r
+robot-status: development\r
+robot-purpose: indexing turkish content\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: N/A\r
+robot-noindex: no\r
+robot-nofollow: no\r
+robot-host: 193.140.83.*\r
+robot-from: ilker@ulak.net.tr\r
+robot-useragent: Evliya Celebi v0.151 - http://ilker.ulak.net.tr\r
+robot-language: perl5\r
+robot-history:\r
+robot-description: crawles pages under ".tr" domain or having turkish character\r
+ encoding (iso-8859-9 or windows-1254)\r
+robot-environment: hobby\r
+modified-date: Fri Mar 31 15:03:12 GMT 2000\r
+\r
+robot-id: nzexplorer\r
+robot-name: nzexplorer\r
+robot-cover-url: http://nzexplorer.co.nz/\r
+robot-details-url:\r
+robot-owner-name: Paul Bourke\r
+robot-owner-url: http://bourke.gen.nz/paul.html\r
+robot-owner-email: paul@bourke.gen.nz\r
+robot-status: active\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: source (commercial)\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: bitz.co.nz\r
+robot-from: no\r
+robot-useragent: explorersearch\r
+robot-language: c++\r
+robot-history: Started in 1995 to provide a comprehensive index\r
+ to WWW pages within New Zealand. Now also used in\r
+ Malaysia and other countries.\r
+robot-environment: service\r
+modified-date: Tues, 25 Jun 1996\r
+modified-by: Paul Bourke\r
+\r
+robot-id:fdse\r
+robot-name:Fluid Dynamics Search Engine robot\r
+robot-cover-url:http://www.xav.com/scripts/search/\r
+robot-details-url:http://www.xav.com/scripts/search/\r
+robot-owner-name:Zoltan Milosevic\r
+robot-owner-url:http://www.xav.com/\r
+robot-owner-email:zoltanm@nickname.net\r
+robot-status:active\r
+robot-purpose:indexing\r
+robot-type:standalone\r
+robot-platform:unix;windows\r
+robot-availability:source;data\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:FDSE\r
+robot-noindex:yes\r
+robot-host:yes\r
+robot-from:*\r
+robot-useragent:Mozilla/4.0 (compatible: FDSE robot)\r
+robot-language:perl5\r
+robot-description:Crawls remote sites as part of a shareware search engine\r
+ program\r
+robot-history:Developed in late 1998 over three pots of coffee\r
+robot-environment:commercial\r
+modified-date:Fri, 21 Jan 2000 10:15:49 GMT\r
+modified-by:Zoltan Milosevic\r
+\r
+robot-id: felix\r
+robot-name: Felix IDE\r
+robot-cover-url: http://www.pentone.com\r
+robot-details-url: http://www.pentone.com\r
+robot-owner-name: The Pentone Group, Inc.\r
+robot-owner-url: http://www.pentone.com\r
+robot-owner-email: felix@pentone.com\r
+robot-status: active\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: windows95, windowsNT\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: FELIX IDE\r
+robot-noindex: yes\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: FelixIDE/1.0\r
+robot-language: visual basic\r
+robot-description: Felix IDE is a retail personal search spider sold by\r
+ The Pentone Group, Inc.\r
+ It supports the proprietary exclusion "Frequency: ??????????" in the\r
+ robots.txt file. Question marks represent an integer\r
+ indicating number of milliseconds to delay between document requests. This\r
+ is called VDRF(tm) or Variable Document Retrieval Frequency. Note that\r
+ users can re-define the useragent name.\r
+robot-history: This robot began as an in-house tool for the lucrative Felix\r
+ IDS (Information Discovery Service) and has gone retail.\r
+robot-environment: service, commercial, research\r
+modified-date: Fri, 11 Apr 1997 19:08:02 GMT\r
+modified-by: Kerry B. Rogers\r
+\r
+robot-id: ferret\r
+robot-name: Wild Ferret Web Hopper #1, #2, #3\r
+robot-cover-url: http://www.greenearth.com/\r
+robot-details-url:\r
+robot-owner-name: Greg Boswell\r
+robot-owner-url: http://www.greenearth.com/\r
+robot-owner-email: ghbos@postoffice.worldnet.att.net\r
+robot-status:\r
+robot-purpose: indexing maintenance statistics\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: Hazel's Ferret Web hopper, \r
+robot-language: C++, Visual Basic, Java\r
+robot-description: The wild ferret web hopper's are designed as specific agents\r
+ to retrieve data from all available sources on the internet.\r
+ They work in an onion format hopping from spot to spot one\r
+ level at a time over the internet. The information is\r
+ gathered into different relational databases, known as\r
+ "Hazel's Horde". The information is publicly available and\r
+ will be free for the browsing at www.greenearth.com.\r
+ Effective date of the data posting is to be\r
+ announced.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Mon Feb 19 00:28:37 1996.\r
+modified-by:\r
+\r
+robot-id: fetchrover\r
+robot-name: FetchRover\r
+robot-cover-url: http://www.engsoftware.com/fetch.htm\r
+robot-details-url: http://www.engsoftware.com/spiders/\r
+robot-owner-name: Dr. Kenneth R. Wadland\r
+robot-owner-url: http://www.engsoftware.com/\r
+robot-owner-email: ken@engsoftware.com\r
+robot-status: active\r
+robot-purpose: maintenance, statistics\r
+robot-type: standalone\r
+robot-platform: Windows/NT, Windows/95, Solaris SPARC\r
+robot-availability: binary, source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: ESI\r
+robot-noindex: N/A\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: ESIRover v1.0\r
+robot-language: C++\r
+robot-description: FetchRover fetches Web Pages. \r
+ It is an automated page-fetching engine. FetchRover can be\r
+ used stand-alone or as the front-end to a full-featured Spider.\r
+ Its database can use any ODBC compliant database server, including\r
+ Microsoft Access, Oracle, Sybase SQL Server, FoxPro, etc.\r
+robot-history: Used as the front-end to SmartSpider (another Spider \r
+ product sold by Engineeering Software, Inc.)\r
+robot-environment: commercial, service\r
+modified-date: Thu, 03 Apr 1997 21:49:50 EST\r
+modified-by: Ken Wadland\r
+\r
+robot-id: fido\r
+robot-name: fido\r
+robot-cover-url: http://www.planetsearch.com/\r
+robot-details-url: http://www.planetsearch.com/info/fido.html\r
+robot-owner-name: Steve DeJarnett\r
+robot-owner-url: http://www.planetsearch.com/staff/steved.html\r
+robot-owner-email: fido@planetsearch.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: fido\r
+robot-noindex: no\r
+robot-host: fido.planetsearch.com, *.planetsearch.com, 206.64.113.*\r
+robot-from: yes\r
+robot-useragent: fido/0.9 Harvest/1.4.pl2\r
+robot-language: c, perl5\r
+robot-description: fido is used to gather documents for the search engine \r
+ provided in the PlanetSearch service, which is operated by\r
+ the Philips Multimedia Center. The robots runs on an\r
+ ongoing basis.\r
+robot-history: fido was originally based on the Harvest Gatherer, but has since\r
+ evolved into a new creature. It still uses some support code\r
+ from Harvest.\r
+robot-environment: service\r
+modified-date: Sat, 2 Nov 1996 00:08:18 GMT\r
+modified-by: Steve DeJarnett\r
+\r
+robot-id: finnish\r
+robot-name: Hämähäkki\r
+robot-cover-url: http://www.fi/search.html\r
+robot-details-url: http://www.fi/www/spider.html\r
+robot-owner-name: Timo Metsälä\r
+robot-owner-url: http://www.fi/~timo/\r
+robot-owner-email: Timo.Metsala@www.fi\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: no\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Hämähäkki\r
+robot-noindex: no\r
+robot-host: *.www.fi\r
+robot-from: yes\r
+robot-useragent: Hämähäkki/0.2\r
+robot-language: C\r
+robot-description: Its purpose is to generate a Resource Discovery\r
+ database from the Finnish (top-level domain .fi) www servers.\r
+ The resulting database is used by the search engine \r
+ at http://www.fi/search.html.\r
+robot-history: (The name Hämähäkki is just Finnish for spider.)\r
+robot-environment:\r
+modified-date: 1996-06-25 \r
+modified-by: Jaakko.Hyvatti@www.fi\r
+\r
+robot-id: fireball\r
+robot-name: KIT-Fireball\r
+robot-cover-url: http://www.fireball.de\r
+robot-details-url: http://www.fireball.de/technik.html (in German)\r
+robot-owner-name: Gruner + Jahr Electronic Media Service GmbH\r
+robot-owner-url: http://www.ems.guj.de\r
+robot-owner-email:info@fireball.de\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: KIT-Fireball\r
+robot-noindex: yes\r
+robot-host: *.fireball.de\r
+robot-from: yes\r
+robot-useragent: KIT-Fireball/2.0 libwww/5.0a\r
+robot-language: c\r
+robot-description: The Fireball robots gather web documents in German\r
+ language for the database of the Fireball search service.\r
+robot-history: The robot was developed by Benhui Chen in a research\r
+ project at the Technical University of Berlin in 1996 and was\r
+ re-implemented by its developer in 1997 for the present owner.\r
+robot-environment: service \r
+modified-date: Mon Feb 23 11:26:08 1998\r
+modified-by: Detlev Kalb\r
+\r
+robot-id: fish\r
+robot-name: Fish search\r
+robot-cover-url: http://www.win.tue.nl/bin/fish-search\r
+robot-details-url:\r
+robot-owner-name: Paul De Bra\r
+robot-owner-url: http://www.win.tue.nl/win/cs/is/debra/\r
+robot-owner-email: debra@win.tue.nl\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: binary\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: www.win.tue.nl\r
+robot-from: no\r
+robot-useragent: Fish-Search-Robot\r
+robot-language: c\r
+robot-description: Its purpose is to discover resources on the fly a version\r
+ exists that is integrated into the Tübingen Mosaic\r
+ 2.4.2 browser (also written in C)\r
+robot-history: Originated as an addition to Mosaic for X\r
+robot-environment:\r
+modified-date: Mon May 8 09:31:19 1995\r
+modified-by:\r
+\r
+robot-id: fouineur\r
+robot-name: Fouineur\r
+robot-cover-url: http://fouineur.9bit.qc.ca/\r
+robot-details-url: http://fouineur.9bit.qc.ca/informations.html\r
+robot-owner-name: Joel Vandal\r
+robot-owner-url: http://www.9bit.qc.ca/~jvandal/\r
+robot-owner-email: jvandal@9bit.qc.ca\r
+robot-status: development\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: unix, windows \r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: fouineur\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: Mozilla/2.0 (compatible fouineur v2.0; fouineur.9bit.qc.ca)\r
+robot-language: perl5\r
+robot-description: This robot build automaticaly a database that is used\r
+ by our own search engine. This robot auto-detect the\r
+ language (french, english & spanish) used in the HTML\r
+ page. Each database record generated by this robot\r
+ include: date, url, title, total words, title, size\r
+ and de-htmlized text. Also support server-side and\r
+ client-side IMAGEMAP.\r
+robot-history: No robots does all thing that we need for our usage.\r
+robot-environment: service\r
+modified-date: Thu, 9 Jan 1997 22:57:28 EST\r
+modified-by: jvandal@9bit.qc.ca\r
+\r
+robot-id: francoroute\r
+robot-name: Robot Francoroute\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Marc-Antoine Parent\r
+robot-owner-url: http://www.crim.ca/~maparent\r
+robot-owner-email: maparent@crim.ca\r
+robot-status:\r
+robot-purpose: indexing, mirroring, statistics\r
+robot-type: browser\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: zorro.crim.ca\r
+robot-from: yes\r
+robot-useragent: Robot du CRIM 1.0a\r
+robot-language: perl5, sqlplus\r
+robot-description: Part of the RISQ's Francoroute project for researching\r
+ francophone. Uses the Accept-Language tag and reduces demand\r
+ accordingly\r
+robot-history:\r
+robot-environment:\r
+modified-date: Wed Jan 10 23:56:22 1996.\r
+modified-by:\r
+\r
+robot-id: freecrawl\r
+robot-name: Freecrawl\r
+robot-cover-url: http://euroseek.net/\r
+robot-owner-name: Jesper Ekhall\r
+robot-owner-email: ekhall@freeside.net\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Freecrawl\r
+robot-noindex: no\r
+robot-host: *.freeside.net\r
+robot-from: yes\r
+robot-useragent: Freecrawl\r
+robot-language: c\r
+robot-description: The Freecrawl robot is used to build a database for the\r
+ EuroSeek service.\r
+robot-environment: service\r
+\r
+robot-id: funnelweb\r
+robot-name: FunnelWeb\r
+robot-cover-url: http://funnelweb.net.au\r
+robot-details-url:\r
+robot-owner-name: David Eagles\r
+robot-owner-url: http://www.pc.com.au\r
+robot-owner-email: eaglesd@pc.com.au\r
+robot-status: \r
+robot-purpose: indexing, statisitics\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: earth.planets.com.au\r
+robot-from: yes\r
+robot-useragent: FunnelWeb-1.0\r
+robot-language: c and c++\r
+robot-description: Its purpose is to generate a Resource Discovery database,\r
+ and generate statistics. Localised South Pacific Discovery\r
+ and Search Engine, plus distributed operation under\r
+ development.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Mon Nov 27 21:30:11 1995\r
+modified-by:\r
+\r
+robot-id: gazz\r
+robot-name: gazz\r
+robot-cover-url: http://gazz.nttrd.com/\r
+robot-details-url: http://gazz.nttrd.com/\r
+robot-owner-name: NTT Cyberspace Laboratories\r
+robot-owner-url: http://gazz.nttrd.com/\r
+robot-owner-email: gazz@nttrd.com\r
+robot-status: development\r
+robot-purpose: statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: gazz\r
+robot-noindex: yes\r
+robot-host: *.nttrd.com, *.infobee.ne.jp\r
+robot-from: yes\r
+robot-useragent: gazz/1.0\r
+robot-language: c\r
+robot-description: This robot is used for research purposes.\r
+robot-history: Its root is TITAN project in NTT.\r
+robot-environment: research\r
+modified-date: Wed, 09 Jun 1999 10:43:18 GMT\r
+modified-by: noto@isl.ntt.co.jp\r
+\r
+robot-id: gcreep\r
+robot-name: GCreep\r
+robot-cover-url: http://www.instrumentpolen.se/gcreep/index.html\r
+robot-details-url: http://www.instrumentpolen.se/gcreep/index.html\r
+robot-owner-name: Instrumentpolen AB\r
+robot-owner-url: http://www.instrumentpolen.se/ip-kontor/eng/index.html\r
+robot-owner-email: anders@instrumentpolen.se\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: browser+standalone\r
+robot-platform: linux+mysql\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: gcreep\r
+robot-noindex: yes\r
+robot-host: mbx.instrumentpolen.se\r
+robot-from: yes\r
+robot-useragent: gcreep/1.0\r
+robot-language: c\r
+robot-description: Indexing robot to learn SQL\r
+robot-history: Spare time project begun late '96, maybe early '97\r
+robot-environment: hobby\r
+modified-date: Fri, 23 Jan 1998 16:09:00 MET\r
+modified-by: Anders Hedstrom\r
+\r
+robot-id: getbot\r
+robot-name: GetBot\r
+robot-cover-url: http://www.blacktop.com.zav/bots \r
+robot-details-url:\r
+robot-owner-name: Alex Zavatone\r
+robot-owner-url: http://www.blacktop.com/zav\r
+robot-owner-email: zav@macromedia.com\r
+robot-status:\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no.\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: no\r
+robot-useragent: ???\r
+robot-language: Shockwave/Director.\r
+robot-description: GetBot's purpose is to index all the sites it can find that\r
+ contain Shockwave movies. It is the first bot or spider\r
+ written in Shockwave. The bot was originally written at\r
+ Macromedia on a hungover Sunday as a proof of concept. -\r
+ Alex Zavatone 3/29/96\r
+robot-history:\r
+robot-environment:\r
+modified-date: Fri Mar 29 20:06:12 1996.\r
+modified-by:\r
+\r
+robot-id: geturl\r
+robot-name: GetURL\r
+robot-cover-url: http://Snark.apana.org.au/James/GetURL/\r
+robot-details-url:\r
+robot-owner-name: James Burton\r
+robot-owner-url: http://Snark.apana.org.au/James/\r
+robot-owner-email: James@Snark.apana.org.au\r
+robot-status: \r
+robot-purpose: maintenance, mirroring\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: GetURL.rexx v1.05\r
+robot-language: ARexx (Amiga REXX)\r
+robot-description: Its purpose is to validate links, perform mirroring, and\r
+ copy document trees. Designed as a tool for retrieving web\r
+ pages in batch mode without the encumbrance of a browser.\r
+ Can be used to describe a set of pages to fetch, and to\r
+ maintain an archive or mirror. Is not run by a central site\r
+ and accessed by clients - is run by the end user or archive\r
+ maintainer\r
+robot-history: \r
+robot-environment:\r
+modified-date: Tue May 9 15:13:12 1995 \r
+modified-by:\r
+\r
+robot-id: golem\r
+robot-name: Golem\r
+robot-cover-url: http://www.quibble.com/golem/\r
+robot-details-url: http://www.quibble.com/golem/\r
+robot-owner-name: Geoff Duncan\r
+robot-owner-url: http://www.quibble.com/geoff/\r
+robot-owner-email: geoff@quibble.com\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: mac\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: golem\r
+robot-noindex: no\r
+robot-host: *.quibble.com\r
+robot-from: yes\r
+robot-useragent: Golem/1.1\r
+robot-language: HyperTalk/AppleScript/C++\r
+robot-description: Golem generates status reports on collections of URLs\r
+ supplied by clients. Designed to assist with editorial updates of\r
+ Web-related sites or products.\r
+robot-history: Personal project turned into a contract service for private\r
+ clients.\r
+robot-environment: service,research\r
+modified-date: Wed, 16 Apr 1997 20:50:00 GMT\r
+modified-by: Geoff Duncan\r
+\r
+robot-id: googlebot\r
+robot-name: Googlebot\r
+robot-cover-url: http://googlebot.com/ \r
+robot-details-url: http://googlebot.com/\r
+robot-owner-name: Google Inc.\r
+robot-owner-url: http://google.com/\r
+robot-owner-email: googlebot@googlebot.com \r
+robot-status: active\r
+robot-purpose: indexing statistics \r
+robot-type: standalone \r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Googlebot\r
+robot-noindex: yes\r
+robot-host: *.googlebot.com\r
+robot-from: yes \r
+robot-useragent: Googlebot/2.0 beta (googlebot(at)googlebot.com)\r
+robot-language: Python\r
+robot-description:\r
+robot-history: Used to be called backrub and run from stanford.edu\r
+robot-environment: service\r
+modified-date: Wed, 29 Sep 1999 18:36:25 -0700\r
+modified-by: Amit Patel <amitp@google.com>\r
+\r
+robot-id: grapnel\r
+robot-name: Grapnel/0.01 Experiment\r
+robot-cover-url: varies\r
+robot-details-url: mailto:v93_kat@ce.kth.se\r
+robot-owner-name: Philip Kallerman\r
+robot-owner-url: v93_kat@ce.kth.se\r
+robot-owner-email: v93_kat@ce.kth.se\r
+robot-status: Experimental\r
+robot-purpose: Indexing\r
+robot-type:\r
+robot-platform: WinNT\r
+robot-availability: None, yet\r
+robot-exclusion: Yes\r
+robot-exclusion-useragent: No\r
+robot-noindex: No\r
+robot-host: varies\r
+robot-from: Varies\r
+robot-useragent:\r
+robot-language: Perl\r
+robot-description: Resource Discovery Experimentation\r
+robot-history: None, hoping to make some\r
+robot-environment:\r
+modified-date:\r
+modified-by: 7 Feb 1997\r
+\r
+robot-id:griffon\r
+robot-name:Griffon \r
+robot-cover-url:http://navi.ocn.ne.jp/ \r
+robot-details-url:http://navi.ocn.ne.jp/griffon/ \r
+robot-owner-name:NTT Communications Corporate Users Business Division \r
+robot-owner-url:http://navi.ocn.ne.jp/ \r
+robot-owner-email:griffon@super.navi.ocn.ne.jp \r
+robot-status:active \r
+robot-purpose:indexing \r
+robot-type:standalone \r
+robot-platform:unix \r
+robot-availability:none \r
+robot-exclusion:yes \r
+robot-exclusion-useragent:griffon \r
+robot-noindex:yes \r
+robot-nofollow:yes \r
+robot-host:*.navi.ocn.ne.jp \r
+robot-from:yes \r
+robot-useragent:griffon/1.0 \r
+robot-language:c \r
+robot-description:The Griffon robot is used to build database for the OCN navi \r
+ search service operated by NTT Communications Corporation.\r
+ It mainly gathers pages written in Japanese. \r
+robot-history:Its root is TITAN project in NTT. \r
+robot-environment:service \r
+modified-date:Mon,25 Jan 2000 15:25:30 GMT \r
+modified-by:toka@navi.ocn.ne.jp\r
+\r
+robot-id: gromit\r
+robot-name: Gromit\r
+robot-cover-url: http://www.austlii.edu.au/\r
+robot-details-url: http://www2.austlii.edu.au/~dan/gromit/\r
+robot-owner-name: Daniel Austin\r
+robot-owner-url: http://www2.austlii.edu.au/~dan/\r
+robot-owner-email: dan@austlii.edu.au\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Gromit\r
+robot-noindex: no\r
+robot-host: *.austlii.edu.au\r
+robot-from: yes\r
+robot-useragent: Gromit/1.0\r
+robot-language: perl5\r
+robot-description: Gromit is a Targetted Web Spider that indexes legal\r
+ sites contained in the AustLII legal links database.\r
+robot-history: This robot is based on the Perl5 LWP::RobotUA module.\r
+robot-environment: research\r
+modified-date: Wed, 11 Jun 1997 03:58:40 GMT\r
+modified-by: Daniel Austin\r
+\r
+robot-id: gulliver\r
+robot-name: Northern Light Gulliver\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Mike Mulligan\r
+robot-owner-url:\r
+robot-owner-email: crawler@northernlight.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: gulliver\r
+robot-noindex: yes\r
+robot-host: scooby.northernlight.com, taz.northernlight.com,\r
+ gulliver.northernlight.com\r
+robot-from: yes\r
+robot-useragent: Gulliver/1.1\r
+robot-language: c\r
+robot-description: Gulliver is a robot to be used to collect\r
+ web pages for indexing and subsequent searching of the index.\r
+robot-history: Oct 1996: development; Dec 1996-Jan 1997: crawl & debug;\r
+ Mar 1997: crawl again;\r
+robot-environment: service\r
+modified-date: Wed, 21 Apr 1999 16:00:00 GMT\r
+modified-by: Mike Mulligan\r
+\r
+robot-id: hambot\r
+robot-name: HamBot\r
+robot-cover-url: http://www.hamrad.com/search.html\r
+robot-details-url: http://www.hamrad.com/\r
+robot-owner-name: John Dykstra\r
+robot-owner-url:\r
+robot-owner-email: john@futureone.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix, Windows95\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: hambot\r
+robot-noindex: yes\r
+robot-host: *.hamrad.com\r
+robot-from:\r
+robot-useragent:\r
+robot-language: perl5, C++\r
+robot-description: Two HamBot robots are used (stand alone & browser based)\r
+ to aid in building the database for HamRad Search - The Search Engine for\r
+ Search Engines. The robota are run intermittently and perform nearly\r
+ identical functions.\r
+robot-history: A non commercial (hobby?) project to aid in building and\r
+ maintaining the database for the the HamRad search engine.\r
+robot-environment: service\r
+modified-date: Fri, 17 Apr 1998 21:44:00 GMT\r
+modified-by: JD\r
+\r
+robot-id: harvest\r
+robot-name: Harvest\r
+robot-cover-url: http://harvest.cs.colorado.edu\r
+robot-details-url:\r
+robot-owner-name: \r
+robot-owner-url: \r
+robot-owner-email: \r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: \r
+robot-host: bruno.cs.colorado.edu\r
+robot-from: yes\r
+robot-useragent: yes\r
+robot-language: \r
+robot-description: Harvest's motivation is to index community- or topic-\r
+ specific collections, rather than to locate and index all\r
+ HTML objects that can be found. Also, Harvest allows users\r
+ to control the enumeration several ways, including stop\r
+ lists and depth and count limits. Therefore, Harvest\r
+ provides a much more controlled way of indexing the Web than\r
+ is typical of robots. Pauses 1 second between requests (by\r
+ default).\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: havindex\r
+robot-name: havIndex\r
+robot-cover-url: http://www.hav.com/\r
+robot-details-url: http://www.hav.com/\r
+robot-owner-name: hav.Software and Horace A. (Kicker) Vallas\r
+robot-owner-url: http://www.hav.com/\r
+robot-owner-email: havIndex@hav.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Java VM 1.1\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: havIndex\r
+robot-noindex: yes\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: havIndex/X.xx[bxx]\r
+robot-language: Java\r
+robot-description: havIndex allows individuals to build searchable word\r
+ index of (user specified) lists of URLs. havIndex does not crawl -\r
+ rather it requires one or more user supplied lists of URLs to be\r
+ indexed. havIndex does (optionally) save urls parsed from indexed\r
+ pages.\r
+robot-history: Developed to answer client requests for URL specific\r
+ index capabilities.\r
+robot-environment: commercial, service\r
+modified-date: 6-27-98\r
+modified-by: Horace A. (Kicker) Vallas\r
+\r
+robot-id: hi\r
+robot-name: HI (HTML Index) Search\r
+robot-cover-url: http://cs6.cs.ait.ac.th:21870/pa.html\r
+robot-details-url:\r
+robot-owner-name: Razzakul Haider Chowdhury\r
+robot-owner-url: http://cs6.cs.ait.ac.th:21870/index.html\r
+robot-owner-email: a94385@cs.ait.ac.th\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: yes\r
+robot-useragent: AITCSRobot/1.1\r
+robot-language: perl 5\r
+robot-description: Its purpose is to generate a Resource Discovery database.\r
+ This Robot traverses the net and creates a searchable\r
+ database of Web pages. It stores the title string of the\r
+ HTML document and the absolute url. A search engine provides\r
+ the boolean AND & OR query models with or without filtering\r
+ the stop list of words. Feature is kept for the Web page\r
+ owners to add the url to the searchable database.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Wed Oct 4 06:54:31 1995\r
+modified-by:\r
+\r
+robot-id: hometown\r
+robot-name: Hometown Spider Pro\r
+robot-cover-url: http://www.hometownsingles.com\r
+robot-details-url: http://www.hometownsingles.com\r
+robot-owner-name: Bob Brown\r
+robot-owner-url: http://www.hometownsingles.com\r
+robot-owner-email: admin@hometownsingles.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: *\r
+robot-noindex: yes\r
+robot-host: 63.195.193.17\r
+robot-from: no\r
+robot-useragent: Hometown Spider Pro\r
+robot-language: delphi\r
+robot-description: The Hometown Spider Pro is used to maintain the indexes\r
+ for Hometown Singles.\r
+robot-history: Innerprise URL Spider Pro\r
+robot-environment: commercial\r
+modified-date: Tue, 28 Mar 2000 16:00:00 GMT\r
+modified-by: Hometown Singles\r
+\r
+robot-id: wired-digital\r
+robot-name: Wired Digital\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Bowen Dwelle\r
+robot-owner-url:\r
+robot-owner-email: bowen@hotwired.com\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: hotwired\r
+robot-noindex: no\r
+robot-host: gossip.hotwired.com\r
+robot-from: yes\r
+robot-useragent: wired-digital-newsbot/1.5\r
+robot-language: perl-5.004\r
+robot-description: this is a test\r
+robot-history:\r
+robot-environment: research\r
+modified-date: Thu, 30 Oct 1997\r
+modified-by: bowen@hotwired.com\r
+\r
+robot-id: htdig\r
+robot-name: ht://Dig\r
+robot-cover-url: http://www.htdig.org/\r
+robot-details-url: http://www.htdig.org/howitworks.html\r
+robot-owner-name: Andrew Scherpbier\r
+robot-owner-url: http://www.htdig.org/author.html\r
+robot-owner-email: andrew@contigo.com\r
+robot-owner-name2: Geoff Hutchison \r
+robot-owner-url2: http://wso.williams.edu/~ghutchis/\r
+robot-owner-email2: ghutchis@wso.williams.edu\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: htdig\r
+robot-noindex: yes\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: htdig/3.1.0b2\r
+robot-language: C,C++.\r
+robot-history:This robot was originally developed for use at San Diego\r
+ State University.\r
+robot-environment:\r
+modified-date:Tue, 3 Nov 1998 10:09:02 EST \r
+modified-by: Geoff Hutchison <Geoffrey.R.Hutchison@williams.edu>\r
+\r
+robot-id: htmlgobble\r
+robot-name: HTMLgobble\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Andreas Ley\r
+robot-owner-url: \r
+robot-owner-email: ley@rz.uni-karlsruhe.de\r
+robot-status: \r
+robot-purpose: mirror\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: tp70.rz.uni-karlsruhe.de\r
+robot-from: yes\r
+robot-useragent: HTMLgobble v2.2\r
+robot-language: \r
+robot-description: A mirroring robot. Configured to stay within a directory,\r
+ sleeps between requests, and the next version will use HEAD\r
+ to check if the entire document needs to be\r
+ retrieved\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: hyperdecontextualizer\r
+robot-name: Hyper-Decontextualizer\r
+robot-cover-url: http://www.tricon.net/Comm/synapse/spider/\r
+robot-details-url:\r
+robot-owner-name: Cliff Hall\r
+robot-owner-url: http://kpt1.tricon.net/cgi-bin/cliff.cgi\r
+robot-owner-email: cliff@tricon.net\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: no\r
+robot-useragent: no\r
+robot-language: Perl 5 Takes an input sentence and marks up each word with\r
+ an appropriate hyper-text link.\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Mon May 6 17:41:29 1996.\r
+modified-by:\r
+\r
+robot-id: ibm\r
+robot-name: IBM_Planetwide\r
+robot-cover-url: http://www.ibm.com/%7ewebmaster/\r
+robot-details-url:\r
+robot-owner-name: Ed Costello\r
+robot-owner-url: http://www.ibm.com/%7ewebmaster/\r
+robot-owner-email: epc@www.ibm.com"\r
+robot-status:\r
+robot-purpose: indexing, maintenance, mirroring\r
+robot-type: standalone and\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: www.ibm.com www2.ibm.com\r
+robot-from: yes\r
+robot-useragent: IBM_Planetwide, \r
+robot-language: Perl5\r
+robot-description: Restricted to IBM owned or related domains.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Mon Jan 22 22:09:19 1996.\r
+modified-by:\r
+\r
+robot-id: iconoclast\r
+robot-name: Popular Iconoclast\r
+robot-cover-url: http://gestalt.sewanee.edu/ic/\r
+robot-details-url: http://gestalt.sewanee.edu/ic/info.html\r
+robot-owner-name: Chris Cappuccio\r
+robot-owner-url: http://sefl.satelnet.org/~ccappuc/\r
+robot-owner-email: chris@gestalt.sewanee.edu\r
+robot-status: development\r
+robot-purpose: statistics \r
+robot-type: standalone\r
+robot-platform: unix (OpenBSD)\r
+robot-availability: source\r
+robot-exclusion: no \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: gestalt.sewanee.edu\r
+robot-from: yes \r
+robot-useragent: gestaltIconoclast/1.0 libwww-FM/2.17\r
+robot-language: c,perl5\r
+robot-description: This guy likes statistics\r
+robot-history: This robot has a history in mathematics and english\r
+robot-environment: research\r
+modified-date: Wed, 5 Mar 1997 17:35:16 CST\r
+modified-by: chris@gestalt.sewanee.edu\r
+\r
+robot-id: Ilse\r
+robot-name: Ingrid\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Ilse c.v.\r
+robot-owner-url: http://www.ilse.nl/\r
+robot-owner-email: ilse@ilse.nl\r
+robot-status: Running\r
+robot-purpose: Indexing\r
+robot-type: Web Indexer\r
+robot-platform: UNIX\r
+robot-availability: Commercial as part of search engine package\r
+robot-exclusion: Yes\r
+robot-exclusion-useragent: INGRID/0.1\r
+robot-noindex: Yes\r
+robot-host: bart.ilse.nl\r
+robot-from: Yes\r
+robot-useragent: INGRID/0.1\r
+robot-language: C\r
+robot-description: \r
+robot-history:\r
+robot-environment:\r
+modified-date: 06/13/1997\r
+modified-by: Ilse\r
+\r
+robot-id: imagelock\r
+robot-name: Imagelock \r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Ken Belanger \r
+robot-owner-url:\r
+robot-owner-email: belanger@imagelock.com\r
+robot-status: development\r
+robot-purpose: maintenance \r
+robot-type:\r
+robot-platform: windows95\r
+robot-availability: none\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: 209.111.133.*\r
+robot-from: no\r
+robot-useragent: Mozilla 3.01 PBWF (Win95)\r
+robot-language:\r
+robot-description: searches for image links\r
+robot-history:\r
+robot-environment: service\r
+modified-date: Tue, 11 Aug 1998 17:28:52 GMT\r
+modified-by: brian@smithrenaud.com\r
+\r
+robot-id: incywincy\r
+robot-name: IncyWincy\r
+robot-cover-url: http://osiris.sunderland.ac.uk/sst-scripts/simon.html\r
+robot-details-url:\r
+robot-owner-name: Simon Stobart\r
+robot-owner-url: http://osiris.sunderland.ac.uk/sst-scripts/simon.html\r
+robot-owner-email: simon.stobart@sunderland.ac.uk\r
+robot-status:\r
+robot-purpose:\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: osiris.sunderland.ac.uk\r
+robot-from: yes\r
+robot-useragent: IncyWincy/1.0b1\r
+robot-language: C++\r
+robot-description: Various Research projects at the University of\r
+ Sunderland\r
+robot-history:\r
+robot-environment:\r
+modified-date: Fri Jan 19 21:50:32 1996.\r
+modified-by:\r
+\r
+robot-id: informant\r
+robot-name: Informant\r
+robot-cover-url: http://informant.dartmouth.edu/\r
+robot-details-url: http://informant.dartmouth.edu/about.html\r
+robot-owner-name: Bob Gray\r
+robot-owner-name2: Aditya Bhasin\r
+robot-owner-name3: Katsuhiro Moizumi\r
+robot-owner-name4: Dr. George V. Cybenko\r
+robot-owner-url: http://informant.dartmouth.edu/\r
+robot-owner-email: info_adm@cosmo.dartmouth.edu\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: no\r
+robot-exclusion-useragent: Informant\r
+robot-noindex: no\r
+robot-host: informant.dartmouth.edu\r
+robot-from: yes\r
+robot-useragent: Informant\r
+robot-language: c, c++\r
+robot-description: The Informant robot continually checks the Web pages\r
+ that are relevant to user queries. Users are notified of any new or\r
+ updated pages. The robot runs daily, but the number of hits per site\r
+ per day should be quite small, and these hits should be randomly\r
+ distributed over several hours. Since the robot does not actually \r
+ follow links (aside from those returned from the major search engines \r
+ such as Lycos), it does not fall victim to the common looping problems.\r
+ The robot will support the Robot Exclusion Standard by early December, 1996.\r
+robot-history: The robot is part of a research project at Dartmouth College. \r
+ The robot may become part of a commercial service (at which time it may be \r
+ subsumed by some other, existing robot).\r
+robot-environment: research, service\r
+modified-date: Sun, 3 Nov 1996 11:55:00 GMT\r
+modified-by: Bob Gray\r
+\r
+robot-id: infoseek\r
+robot-name: InfoSeek Robot 1.0\r
+robot-cover-url: http://www.infoseek.com\r
+robot-details-url:\r
+robot-owner-name: Steve Kirsch\r
+robot-owner-url: http://www.infoseek.com\r
+robot-owner-email: stk@infoseek.com\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: corp-gw.infoseek.com\r
+robot-from: yes\r
+robot-useragent: InfoSeek Robot 1.0\r
+robot-language: python\r
+robot-description: Its purpose is to generate a Resource Discovery database.\r
+ Collects WWW pages for both InfoSeek's free WWW search and\r
+ commercial search. Uses a unique proprietary algorithm to\r
+ identify the most popular and interesting WWW pages. Very\r
+ fast, but never has more than one request per site\r
+ outstanding at any given time. Has been refined for more\r
+ than a year.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Sun May 28 01:35:48 1995\r
+modified-by:\r
+\r
+robot-id: infoseeksidewinder\r
+robot-name: Infoseek Sidewinder\r
+robot-cover-url: http://www.infoseek.com/\r
+robot-details-url:\r
+robot-owner-name: Mike Agostino\r
+robot-owner-url: http://www.infoseek.com/\r
+robot-owner-email: mna@infoseek.com\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: Infoseek Sidewinder\r
+robot-language: C Collects WWW pages for both InfoSeek's free WWW search\r
+ services. Uses a unique, incremental, very fast proprietary\r
+ algorithm to find WWW pages. \r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sat Apr 27 01:20:15 1996.\r
+modified-by:\r
+\r
+robot-id: infospider\r
+robot-name: InfoSpiders\r
+robot-cover-url: http://www-cse.ucsd.edu/users/fil/agents/agents.html\r
+robot-owner-name: Filippo Menczer\r
+robot-owner-url: http://www-cse.ucsd.edu/users/fil/\r
+robot-owner-email: fil@cs.ucsd.edu\r
+robot-status: development\r
+robot-purpose: search\r
+robot-type: standalone\r
+robot-platform: unix, mac\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: InfoSpiders\r
+robot-noindex: no\r
+robot-host: *.ucsd.edu\r
+robot-from: yes\r
+robot-useragent: InfoSpiders/0.1\r
+robot-language: c, perl5\r
+robot-description: application of artificial life algorithm to adaptive\r
+ distributed information retrieval\r
+robot-history: UC San Diego, Computer Science Dept. PhD research project\r
+ (1995-97) under supervision of Prof. Rik Belew\r
+robot-environment: research\r
+modified-date: Mon, 16 Sep 1996 14:08:00 PDT\r
+\r
+robot-id: inspectorwww\r
+robot-name: Inspector Web\r
+robot-cover-url: http://www.greenpac.com/inspector/\r
+robot-details-url: http://www.greenpac.com/inspector/ourrobot.html\r
+robot-owner-name: Doug Green\r
+robot-owner-url: http://www.greenpac.com\r
+robot-owner-email: doug@greenpac.com\r
+robot-status: active: robot significantly developed, but still undergoing fixes\r
+robot-purpose: maintentance: link validation, html validation, image size\r
+ validation, etc\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: free service and more extensive commercial service\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: inspectorwww\r
+robot-noindex: no\r
+robot-host: www.corpsite.com, www.greenpac.com, 38.234.171.*\r
+robot-from: yes\r
+robot-useragent: inspectorwww/1.0 http://www.greenpac.com/inspectorwww.html\r
+robot-language: c\r
+robot-description: Provide inspection reports which give advise to WWW\r
+ site owners on missing links, images resize problems, syntax errors, etc.\r
+robot-history: development started in Mar 1997\r
+robot-environment: commercial\r
+modified-date: Tue Jun 17 09:24:58 EST 1997\r
+modified-by: Doug Green\r
+\r
+robot-id: intelliagent\r
+robot-name: IntelliAgent\r
+robot-cover-url: http://www.geocities.com/SiliconValley/3086/iagent.html\r
+robot-details-url:\r
+robot-owner-name: David Reilly\r
+robot-owner-url: http://www.geocities.com/SiliconValley/3086/index.html\r
+robot-owner-email: s1523@sand.it.bond.edu.au\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: sand.it.bond.edu.au\r
+robot-from: no\r
+robot-useragent: 'IAGENT/1.0'\r
+robot-language: C\r
+robot-description: IntelliAgent is still in development. Indeed, it is very far\r
+ from completion. I'm planning to limit the depth at which it\r
+ will probe, so hopefully IAgent won't cause anyone much of a\r
+ problem. At the end of its completion, I hope to publish\r
+ both the raw data and original source code.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Fri May 31 02:10:39 1996.\r
+modified-by:\r
+\r
+robot-id:iron33\r
+robot-name:Iron33\r
+robot-cover-url:http://verno.ueda.info.waseda.ac.jp/iron33/\r
+robot-details-url:http://verno.ueda.info.waseda.ac.jp/iron33/history.html\r
+robot-owner-name:Takashi Watanabe\r
+robot-owner-url:http://www.ueda.info.waseda.ac.jp/~watanabe/\r
+robot-owner-email:watanabe@ueda.info.waseda.ac.jp\r
+robot-status:active\r
+robot-purpose:indexing, statistics\r
+robot-type:standalone\r
+robot-platform:unix\r
+robot-availability:source\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:Iron33\r
+robot-noindex:no\r
+robot-host:*.folon.ueda.info.waseda.ac.jp, 133.9.215.*\r
+robot-from:yes\r
+robot-useragent:Iron33/0.0\r
+robot-language:c\r
+robot-description:The robot "Iron33" is used to build the\r
+ database for the WWW search engine "Verno".\r
+robot-history:\r
+robot-environment:research\r
+modified-date:Fri, 20 Mar 1998 18:34 JST\r
+modified-by:Watanabe Takashi\r
+\r
+robot-id: israelisearch\r
+robot-name: Israeli-search\r
+robot-cover-url: http://www.idc.ac.il/Sandbag/\r
+robot-details-url:\r
+robot-owner-name: Etamar Laron\r
+robot-owner-url: http://www.xpert.com/~etamar/\r
+robot-owner-email: etamar@xpert.co\r
+robot-status:\r
+robot-purpose: indexing.\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: dylan.ius.cs.cmu.edu\r
+robot-from: no\r
+robot-useragent: IsraeliSearch/1.0\r
+robot-language: C A complete software designed to collect information in a\r
+ distributed workload and supports context queries. Intended\r
+ to be a complete updated resource for Israeli sites and\r
+ information related to Israel or Israeli\r
+ Society.\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Tue Apr 23 19:23:55 1996.\r
+modified-by:\r
+\r
+robot-id: javabee\r
+robot-name: JavaBee\r
+robot-cover-url: http://www.javabee.com\r
+robot-details-url:\r
+robot-owner-name:ObjectBox\r
+robot-owner-url:http://www.objectbox.com/\r
+robot-owner-email:info@objectbox.com\r
+robot-status:Active\r
+robot-purpose:Stealing Java Code\r
+robot-type:standalone\r
+robot-platform:Java\r
+robot-availability:binary\r
+robot-exclusion:no\r
+robot-exclusion-useragent:\r
+robot-noindex:no\r
+robot-host:*\r
+robot-from:no\r
+robot-useragent:JavaBee\r
+robot-language:Java\r
+robot-description:This robot is used to grab java applets and run them\r
+ locally overriding the security implemented\r
+robot-history:\r
+robot-environment:commercial\r
+modified-date:\r
+modified-by:\r
+\r
+robot-id: jcrawler\r
+robot-name: JCrawler\r
+robot-cover-url: http://www.nihongo.org/jcrawler/\r
+robot-details-url:\r
+robot-owner-name: Benjamin Franz\r
+robot-owner-url: http://www.nihongo.org/snowhare/\r
+robot-owner-email: snowhare@netimages.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: jcrawler\r
+robot-noindex: yes\r
+robot-host: db.netimages.com\r
+robot-from: yes\r
+robot-useragent: JCrawler/0.2\r
+robot-language: perl5\r
+robot-description: JCrawler is currently used to build the Vietnam topic\r
+ specific WWW index for VietGATE\r
+ <URL:http://www.vietgate.net/>. It schedules visits\r
+ randomly, but will not visit a site more than once\r
+ every two minutes. It uses a subject matter relevance\r
+ pruning algorithm to determine what pages to crawl\r
+ and index and will not generally index pages with\r
+ no Vietnam related content. Uses Unicode internally,\r
+ and detects and converts several different Vietnamese\r
+ character encodings.\r
+robot-history:\r
+robot-environment: service\r
+modified-date: Wed, 08 Oct 1997 00:09:52 GMT\r
+modified-by: Benjamin Franz\r
+\r
+robot-id: jeeves\r
+robot-name: Jeeves\r
+robot-cover-url: http://www-students.doc.ic.ac.uk/~lglb/Jeeves/\r
+robot-details-url:\r
+robot-owner-name: Leon Brocard\r
+robot-owner-url: http://www-students.doc.ic.ac.uk/~lglb/\r
+robot-owner-email: lglb@doc.ic.ac.uk\r
+robot-status: development\r
+robot-purpose: indexing maintenance statistics\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: none\r
+robot-exclusion: no\r
+robot-exclusion-useragent: jeeves\r
+robot-noindex: no\r
+robot-host: *.doc.ic.ac.uk\r
+robot-from: yes\r
+robot-useragent: Jeeves v0.05alpha (PERL, LWP, lglb@doc.ic.ac.uk)\r
+robot-language: perl5\r
+robot-description: Jeeves is basically a web-mirroring robot built as a\r
+ final-year degree project. It will have many nice features and is\r
+ already web-friendly. Still in development.\r
+robot-history: Still short (0.05alpha)\r
+robot-environment: research\r
+modified-date: Wed, 23 Apr 1997 17:26:50 GMT\r
+modified-by: Leon Brocard\r
+\r
+robot-id: jobot\r
+robot-name: Jobot\r
+robot-cover-url: http://www.micrognosis.com/~ajack/jobot/jobot.html\r
+robot-details-url:\r
+robot-owner-name: Adam Jack\r
+robot-owner-url: http://www.micrognosis.com/~ajack/index.html\r
+robot-owner-email: ajack@corp.micrognosis.com\r
+robot-status: inactive\r
+robot-purpose: standalone\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: supernova.micrognosis.com\r
+robot-from: yes\r
+robot-useragent: Jobot/0.1alpha libwww-perl/4.0\r
+robot-language: perl 4\r
+robot-description: Its purpose is to generate a Resource Discovery database.\r
+ Intended to seek out sites of potential "career interest".\r
+ Hence - Job Robot.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Tue Jan 9 18:55:55 1996\r
+modified-by:\r
+\r
+robot-id: joebot\r
+robot-name: JoeBot\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Ray Waldin\r
+robot-owner-url: http://www.primenet.com/~rwaldin\r
+robot-owner-email: rwaldin@primenet.com\r
+robot-status:\r
+robot-purpose:\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: JoeBot/x.x, \r
+robot-language: java JoeBot is a generic web crawler implemented as a\r
+ collection of Java classes which can be used in a variety of\r
+ applications, including resource discovery, link validation,\r
+ mirroring, etc. It currently limits itself to one visit per\r
+ host per minute.\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sun May 19 08:13:06 1996.\r
+modified-by:\r
+\r
+robot-id: jubii\r
+robot-name: The Jubii Indexing Robot\r
+robot-cover-url: http://www.jubii.dk/robot/default.htm\r
+robot-details-url:\r
+robot-owner-name: Jakob Faarvang\r
+robot-owner-url: http://www.cybernet.dk/staff/jakob/\r
+robot-owner-email: jakob@jubii.dk\r
+robot-status: \r
+robot-purpose: indexing, maintainance\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: any host in the cybernet.dk domain\r
+robot-from: yes\r
+robot-useragent: JubiiRobot/version#\r
+robot-language: visual basic 4.0\r
+robot-description: Its purpose is to generate a Resource Discovery database,\r
+ and validate links. Used for indexing the .dk top-level\r
+ domain as well as other Danish sites for aDanish web\r
+ database, as well as link validation.\r
+robot-history: Will be in constant operation from Spring\r
+ 1996\r
+robot-environment:\r
+modified-date: Sat Jan 6 20:58:44 1996\r
+modified-by:\r
+\r
+robot-id: jumpstation\r
+robot-name: JumpStation\r
+robot-cover-url: http://js.stir.ac.uk/jsbin/jsii\r
+robot-details-url:\r
+robot-owner-name: Jonathon Fletcher\r
+robot-owner-url: http://www.stir.ac.uk/~jf1\r
+robot-owner-email: j.fletcher@stirling.ac.uk \r
+robot-status: retired\r
+robot-purpose: indexing\r
+robot-type:\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: *.stir.ac.uk\r
+robot-from: yes\r
+robot-useragent: jumpstation\r
+robot-language: perl, C, c++\r
+robot-description:\r
+robot-history: Originated as a weekend project in 1993.\r
+robot-environment:\r
+modified-date: Tue May 16 00:57:42 1995.\r
+modified-by:\r
+\r
+robot-id: katipo\r
+robot-name: Katipo\r
+robot-cover-url: http://www.vuw.ac.nz/~newbery/Katipo.html\r
+robot-details-url: http://www.vuw.ac.nz/~newbery/Katipo/Katipo-doc.html\r
+robot-owner-name: Michael Newbery\r
+robot-owner-url: http://www.vuw.ac.nz/~newbery\r
+robot-owner-email: Michael.Newbery@vuw.ac.nz\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: Macintosh\r
+robot-availability: binary\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: Katipo/1.0\r
+robot-language: c\r
+robot-description: Watches all the pages you have previously visited\r
+ and tells you when they have changed.\r
+robot-history: \r
+robot-environment: commercial (free)\r
+modified-date: Tue, 25 Jun 96 11:40:07 +1200\r
+modified-by: Michael Newbery\r
+\r
+robot-id: kdd\r
+robot-name: KDD-Explorer\r
+robot-cover-url: http://mlc.kddvw.kcom.or.jp/CLINKS/html/clinks.html\r
+robot-details-url: not available\r
+robot-owner-name: Kazunori Matsumoto\r
+robot-owner-url: not available\r
+robot-owner-email: matsu@lab.kdd.co.jp\r
+robot-status: development (to be avtive in June 1997)\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:KDD-Explorer\r
+robot-noindex: no\r
+robot-host: mlc.kddvw.kcom.or.jp\r
+robot-from: yes\r
+robot-useragent: KDD-Explorer/0.1\r
+robot-language: c\r
+robot-description: KDD-Explorer is used for indexing valuable documents\r
+ which will be retrieved via an experimental cross-language\r
+ search engine, CLINKS.\r
+robot-history: This robot was designed in Knowledge-bases Information\r
+ processing Laboratory, KDD R&D Laboratories, 1996-1997\r
+robot-environment: research\r
+modified-date: Mon, 2 June 1997 18:00:00 JST\r
+modified-by: Kazunori Matsumoto\r
+\r
+robot-id:kilroy\r
+robot-name:Kilroy\r
+robot-cover-url:http://purl.org/kilroy\r
+robot-details-url:http://purl.org/kilroy\r
+robot-owner-name:OCLC\r
+robot-owner-url:http://www.oclc.org\r
+robot-owner-email:kilroy@oclc.org\r
+robot-status:active\r
+robot-purpose:indexing,statistics\r
+robot-type:standalone\r
+robot-platform:unix,windowsNT\r
+robot-availability:none\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:*\r
+robot-noindex:no\r
+robot-host:*.oclc.org\r
+robot-from:no\r
+robot-useragent:yes\r
+robot-language:java\r
+robot-description:Used to collect data for several projects. \r
+ Runs constantly and visits site no faster than once every 90 seconds.\r
+robot-history:none\r
+robot-environment:research,service\r
+modified-date:Thursday, 24 Apr 1997 20:00:00 GMT\r
+modified-by:tkac\r
+\r
+robot-id: ko_yappo_robot\r
+robot-name: KO_Yappo_Robot\r
+robot-cover-url: http://yappo.com/info/robot.html\r
+robot-details-url: http://yappo.com/\r
+robot-owner-name: Kazuhiro Osawa\r
+robot-owner-url: http://yappo.com/\r
+robot-owner-email: office_KO@yappo.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: ko_yappo_robot\r
+robot-noindex: yes\r
+robot-host: yappo.com,209.25.40.1\r
+robot-from: yes\r
+robot-useragent: KO_Yappo_Robot/1.0.4(http://yappo.com/info/robot.html)\r
+robot-language: perl\r
+robot-description: The KO_Yappo_Robot robot is used to build the database\r
+ for the Yappo search service by k,osawa\r
+ (part of AOL).\r
+ The robot runs random day, and visits sites in a random order.\r
+robot-history: The robot is hobby of k,osawa\r
+ at the Tokyo in 1997\r
+robot-environment: hobby\r
+modified-date: Fri, 18 Jul 1996 12:34:21 GMT\r
+modified-by: KO\r
+\r
+robot-id: labelgrabber.txt\r
+robot-name: LabelGrabber\r
+robot-cover-url: http://www.w3.org/PICS/refcode/LabelGrabber/index.htm\r
+robot-details-url: http://www.w3.org/PICS/refcode/LabelGrabber/index.htm\r
+robot-owner-name: Kyle Jamieson\r
+robot-owner-url: http://www.w3.org/PICS/refcode/LabelGrabber/index.htm\r
+robot-owner-email: jamieson@mit.edu\r
+robot-status: active\r
+robot-purpose: Grabs PICS labels from web pages, submits them to a label bueau\r
+robot-type: standalone\r
+robot-platform: windows, windows95, windowsNT, unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: label-grabber\r
+robot-noindex: no\r
+robot-host: head.w3.org\r
+robot-from: no\r
+robot-useragent: LabelGrab/1.1\r
+robot-language: java\r
+robot-description: The label grabber searches for PICS labels and submits\r
+ them to a label bureau\r
+robot-history: N/A\r
+robot-environment: research\r
+modified-date: Wed, 28 Jan 1998 17:32:52 GMT\r
+modified-by: jamieson@mit.edu\r
+\r
+robot-id: larbin\r
+robot-name: larbin\r
+robot-cover-url: http://para.inria.fr/~ailleret/larbin/index-eng.html\r
+robot-owner-name: Sebastien Ailleret\r
+robot-owner-url: http://para.inria.fr/~ailleret/\r
+robot-owner-email: sebastien.ailleret@inria.fr\r
+robot-status: active\r
+robot-purpose: Your imagination is the only limit\r
+robot-type: standalone\r
+robot-platform: Linux\r
+robot-availability: source (GPL), mail me for customization\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: larbin\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: larbin (+mail)\r
+robot-language: c++\r
+robot-description: Parcourir le web, telle est ma passion\r
+robot-history: french research group (INRIA Verso)\r
+robot-environment: hobby\r
+modified-date: 2000-3-28\r
+modified-by: Sebastien Ailleret\r
+\r
+robot-id: legs\r
+robot-name: legs\r
+robot-cover-url: http://www.MagPortal.com/\r
+robot-details-url:\r
+robot-owner-name: Bill Dimm\r
+robot-owner-url: http://www.HotNeuron.com/\r
+robot-owner-email: admin@magportal.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: linux\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: legs\r
+robot-noindex: no\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: legs\r
+robot-language: perl5\r
+robot-description: The legs robot is used to build the magazine article\r
+ database for MagPortal.com.\r
+robot-history:\r
+robot-environment: service\r
+modified-date: Wed, 22 Mar 2000 14:10:49 GMT\r
+modified-by: Bill Dimm\r
+\r
+robot-id:linkscan\r
+robot-name:LinkScan\r
+robot-cover-url:http://www.elsop.com/\r
+robot-details-url:http://www.elsop.com/linkscan/overview.html\r
+robot-owner-name:Electronic Software Publishing Corp. (Elsop)\r
+robot-owner-url:http://www.elsop.com/\r
+robot-owner-email:sales@elsop.com\r
+robot-status:Robot actively in use\r
+robot-purpose:Link checker, SiteMapper, and HTML Validator\r
+robot-type:Standalone\r
+robot-platform:Unix, Linux, Windows 98/NT\r
+robot-availability:Program is shareware\r
+robot-exclusion:No\r
+robot-exclusion-useragent:\r
+robot-noindex:Yes\r
+robot-host:*\r
+robot-from:\r
+robot-useragent:LinkScan Server/5.5 | LinkScan Workstation/5.5\r
+robot-language:perl5\r
+robot-description:LinkScan checks links, validates HTML and creates site maps\r
+robot-history: First developed by Elsop in January,1997\r
+robot-environment:Commercial\r
+modified-date:Fri, 3 September 1999 17:00:00 PDT\r
+modified-by: Kenneth R. Churilla\r
+\r
+robot-id: linkwalker\r
+robot-name: LinkWalker\r
+robot-cover-url: http://www.seventwentyfour.com\r
+robot-details-url: http://www.seventwentyfour.com/tech.html\r
+robot-owner-name: Roy Bryant\r
+robot-owner-url: \r
+robot-owner-email: rbryant@seventwentyfour.com\r
+robot-status: active\r
+robot-purpose: maintenance, statistics\r
+robot-type: standalone\r
+robot-platform: windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: linkwalker\r
+robot-noindex: yes\r
+robot-host: *.seventwentyfour.com\r
+robot-from: yes\r
+robot-useragent: LinkWalker\r
+robot-language: c++\r
+robot-description: LinkWalker generates a database of links.\r
+ We send reports of bad ones to webmasters.\r
+robot-history: Constructed late 1997 through April 1998.\r
+ In full service April 1998.\r
+robot-environment: service\r
+modified-date: Wed, 22 Apr 1998\r
+modified-by: Roy Bryant\r
+\r
+robot-id:lockon\r
+robot-name:Lockon\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name:Seiji Sasazuka & Takahiro Ohmori\r
+robot-owner-url:\r
+robot-owner-email:search@rsch.tuis.ac.jp\r
+robot-status:active\r
+robot-purpose:indexing\r
+robot-type:standalone\r
+robot-platform:UNIX\r
+robot-availability:none\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:Lockon\r
+robot-noindex:yes\r
+robot-host:*.hitech.tuis.ac.jp\r
+robot-from:yes\r
+robot-useragent:Lockon/xxxxx\r
+robot-language:perl5 \r
+robot-description:This robot gathers only HTML document.\r
+robot-history:This robot was developed in the Tokyo university of information sciences in 1998.\r
+robot-environment:research\r
+modified-date:Tue. 10 Nov 1998 20:00:00 GMT\r
+modified-by:Seiji Sasazuka & Takahiro Ohmori\r
+\r
+robot-id:logo_gif\r
+robot-name: logo.gif Crawler\r
+robot-cover-url: http://www.inm.de/projects/logogif.html\r
+robot-details-url:\r
+robot-owner-name: Sevo Stille\r
+robot-owner-url: http://www.inm.de/people/sevo\r
+robot-owner-email: sevo@inm.de\r
+robot-status: under development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: logo_gif_crawler\r
+robot-noindex: no\r
+robot-host: *.inm.de\r
+robot-from: yes\r
+robot-useragent: logo.gif crawler\r
+robot-language: perl\r
+robot-description: meta-indexing engine for corporate logo graphics\r
+ The robot runs at irregular intervals and will only pull a start page and\r
+ its associated /.*logo\.gif/i (if any). It will be terminated once a\r
+ statistically\r
+ significant number of samples has been collected.\r
+robot-history: logo.gif is part of the design diploma of Markus Weisbeck,\r
+ and tries to analyze the abundance of the logo metaphor in WWW\r
+ corporate design.\r
+ The crawler and image database were written by Sevo Stille and Peter\r
+ Frank of the Institut für Neue Medien, respectively.\r
+robot-environment: research, statistics\r
+modified-date: 25.5.97\r
+modified-by: Sevo Stille\r
+\r
+robot-id: lycos\r
+robot-name: Lycos\r
+robot-cover-url: http://lycos.cs.cmu.edu/\r
+robot-details-url:\r
+robot-owner-name: Dr. Michael L. Mauldin\r
+robot-owner-url: http://fuzine.mt.cs.cmu.edu/mlm/home.html\r
+robot-owner-email: fuzzy@cmu.edu\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: fuzine.mt.cs.cmu.edu, lycos.com\r
+robot-from: \r
+robot-useragent: Lycos/x.x\r
+robot-language: \r
+robot-description: This is a research program in providing information\r
+ retrieval and discovery in the WWW, using a finite memory\r
+ model of the web to guide intelligent, directed searches for\r
+ specific information needs\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: macworm\r
+robot-name: Mac WWWWorm\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Sebastien Lemieux\r
+robot-owner-url: \r
+robot-owner-email: lemieuse@ERE.UMontreal.CA\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: Macintosh\r
+robot-availability: none\r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: \r
+robot-useragent: \r
+robot-language: hypercard\r
+robot-description: a French Keyword-searching robot for the Mac The author has\r
+ decided not to release this robot to the\r
+ public\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: magpie\r
+robot-name: Magpie\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Keith Jones\r
+robot-owner-url: \r
+robot-owner-email: Keith.Jones@blueberry.co.uk\r
+robot-status: development\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *.blueberry.co.uk, 194.70.52.*, 193.131.167.144\r
+robot-from: no\r
+robot-useragent: Magpie/1.0\r
+robot-language: perl5\r
+robot-description: Used to obtain information from a specified list of web pages for local indexing. Runs every two hours, and visits only a small number of sites.\r
+robot-history: Part of a research project. Alpha testing from 10 July 1996, Beta testing from 10 September.\r
+robot-environment: research\r
+modified-date: Wed, 10 Oct 1996 13:15:00 GMT\r
+modified-by: Keith Jones\r
+\r
+robot-id: mediafox\r
+robot-name: MediaFox\r
+robot-cover-url: none\r
+robot-details-url: none\r
+robot-owner-name: Lars Eilebrecht \r
+robot-owner-url: http://www.home.unix-ag.org/sfx/\r
+robot-owner-email: sfx@uni-media.de\r
+robot-status: development\r
+robot-purpose: indexing and maintenance\r
+robot-type: standalone\r
+robot-platform: (Java)\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: mediafox\r
+robot-noindex: yes\r
+robot-host: 141.99.*.*\r
+robot-from: yes\r
+robot-useragent: MediaFox/x.y\r
+robot-language: Java\r
+robot-description: The robot is used to index meta information of a\r
+ specified set of documents and update a database\r
+ accordingly.\r
+robot-history: Project at the University of Siegen\r
+robot-environment: research\r
+modified-date: Fri Aug 14 03:37:56 CEST 1998\r
+modified-by: Lars Eilebrecht\r
+\r
+robot-id:merzscope\r
+robot-name:MerzScope\r
+robot-cover-url:http://www.merzcom.com\r
+robot-details-url:http://www.merzcom.com\r
+robot-owner-name:(Client based robot)\r
+robot-owner-url:(Client based robot)\r
+robot-owner-email:\r
+robot-status:actively in use\r
+robot-purpose:WebMapping\r
+robot-type:standalone\r
+robot-platform: (Java Based) unix,windows95,windowsNT,os2,mac etc ..\r
+robot-availability:binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: MerzScope\r
+robot-noindex: no\r
+robot-host:(Client Based)\r
+robot-from:\r
+robot-useragent: MerzScope\r
+robot-language: java\r
+robot-description: Robot is part of a Web-Mapping package called MerzScope,\r
+ to be used mainly by consultants, and web masters to create and\r
+ publish maps, on and of the World wide web.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Fri, 13 March 1997 16:31:00\r
+modified-by: Philip Lenir, MerzScope lead developper\r
+\r
+robot-id: meshexplorer\r
+robot-name: NEC-MeshExplorer\r
+robot-cover-url: http://netplaza.biglobe.or.jp/\r
+robot-details-url: http://netplaza.biglobe.or.jp/keyword.html\r
+robot-owner-name: web search service maintenance group\r
+robot-owner-url: http://netplaza.biglobe.or.jp/keyword.html\r
+robot-owner-email: web-dir@mxa.meshnet.or.jp\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: NEC-MeshExplorer\r
+robot-noindex: no\r
+robot-host: meshsv300.tk.mesh.ad.jp\r
+robot-from: yes\r
+robot-useragent: NEC-MeshExplorer\r
+robot-language: c\r
+robot-description: The NEC-MeshExplorer robot is used to build database for the NETPLAZA\r
+ search service operated by NEC Corporation. The robot searches URLs\r
+ around sites in japan(JP domain).\r
+ The robot runs every day, and visits sites in a random order.\r
+robot-history: Prototype version of this robot was developed in C&C Research\r
+ Laboratories, NEC Corporation. Current robot (Version 1.0) is based\r
+ on the prototype and has more functions.\r
+robot-environment: research\r
+modified-date: Jan 1, 1997\r
+modified-by: Nobuya Kubo, Hajime Takano\r
+\r
+robot-id: MindCrawler\r
+robot-name: MindCrawler\r
+robot-cover-url: http://www.mindpass.com/_technology_faq.htm\r
+robot-details-url:\r
+robot-owner-name: Mindpass\r
+robot-owner-url: http://www.mindpass.com/\r
+robot-owner-email: support@mindpass.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: linux\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: MindCrawler\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: MindCrawler\r
+robot-language: c++\r
+robot-description: \r
+robot-history:\r
+robot-environment:\r
+modified-date: Tue Mar 28 11:30:09 CEST 2000\r
+modified-by:\r
+\r
+robot-id:moget\r
+robot-name:moget\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name:NTT-ME Infomation Xing,Inc\r
+robot-owner-url:http://www.nttx.co.jp\r
+robot-owner-email:moget@goo.ne.jp\r
+robot-status:active\r
+robot-purpose:indexing,statistics\r
+robot-type:standalone\r
+robot-platform:unix\r
+robot-availability:none\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:moget\r
+robot-noindex:yes\r
+robot-host:*.goo.ne.jp\r
+robot-from:yes\r
+robot-useragent:moget/1.0\r
+robot-language:c\r
+robot-description: This robot is used to build the database for the search service operated by goo\r
+robot-history:\r
+robot-environment:service\r
+modified-date:Thu, 30 Mar 2000 18:40:37 GMT\r
+modified-by:moget@goo.ne.jp\r
+\r
+robot-id: momspider\r
+robot-name: MOMspider\r
+robot-cover-url: http://www.ics.uci.edu/WebSoft/MOMspider/\r
+robot-details-url:\r
+robot-owner-name: Roy T. Fielding\r
+robot-owner-url: http://www.ics.uci.edu/dir/grad/Software/fielding\r
+robot-owner-email: fielding@ics.uci.edu\r
+robot-status: active\r
+robot-purpose: maintenance, statistics\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: MOMspider/1.00 libwww-perl/0.40\r
+robot-language: perl 4\r
+robot-description: to validate links, and generate statistics. It's usually run\r
+ from anywhere\r
+robot-history: Originated as a research project at the University of\r
+ California, Irvine, in 1993. Presented at the First\r
+ International WWW Conference in Geneva, 1994.\r
+robot-environment:\r
+modified-date: Sat May 6 08:11:58 1995 \r
+modified-by: fielding@ics.uci.edu\r
+\r
+robot-id: monster\r
+robot-name: Monster\r
+robot-cover-url: http://www.neva.ru/monster.list/russian.www.html\r
+robot-details-url: \r
+robot-owner-name: Dmitry Dicky\r
+robot-owner-url: http://wild.stu.neva.ru/\r
+robot-owner-email: diwil@wild.stu.neva.ru\r
+robot-status: active\r
+robot-purpose: maintenance, mirroring\r
+robot-type: standalone\r
+robot-platform: UNIX (Linux)\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: wild.stu.neva.ru\r
+robot-from: \r
+robot-useragent: Monster/vX.X.X -$TYPE ($OSTYPE)\r
+robot-language: C\r
+robot-description: The Monster has two parts - Web searcher and Web analyzer.\r
+ Searcher is intended to perform the list of WWW sites of \r
+ desired domain (for example it can perform list of all \r
+ WWW sites of mit.edu, com, org, etc... domain)\r
+ In the User-agent field $TYPE is set to 'Mapper' for Web searcher\r
+ and 'StAlone' for Web analyzer. \r
+robot-history: Now the full (I suppose) list of ex-USSR sites is produced.\r
+robot-environment: \r
+modified-date: Tue Jun 25 10:03:36 1996\r
+modified-by:\r
+\r
+robot-id: motor\r
+robot-name: Motor\r
+robot-cover-url: http://www.cybercon.de/Motor/index.html\r
+robot-details-url:\r
+robot-owner-name: Mr. Oliver Runge, Mr. Michael Goeckel\r
+robot-owner-url: http://www.cybercon.de/index.html\r
+robot-owner-email: Motor@cybercon.technopark.gmd.de\r
+robot-status: developement\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: mac\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Motor\r
+robot-noindex: no\r
+robot-host: Michael.cybercon.technopark.gmd.de\r
+robot-from: yes\r
+robot-useragent: Motor/0.2\r
+robot-language: 4th dimension\r
+robot-description: The Motor robot is used to build the database for the \r
+ www.webindex.de search service operated by CyberCon. The robot ios under \r
+ development - it runs in random intervals and visits site in a priority \r
+ driven order (.de/.ch/.at first, root and robots.txt first)\r
+robot-history: \r
+robot-environment: service\r
+modified-date: Wed, 3 Jul 1996 15:30:00 +0100\r
+modified-by: Michael Goeckel (Michael@cybercon.technopark.gmd.de)\r
+\r
+robot-id: muscatferret\r
+robot-name: Muscat Ferret\r
+robot-cover-url: http://www.muscat.co.uk/euroferret/\r
+robot-details-url:\r
+robot-owner-name: Olly Betts\r
+robot-owner-url: http://www.muscat.co.uk/~olly/\r
+robot-owner-email: olly@muscat.co.uk\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: MuscatFerret\r
+robot-noindex: yes\r
+robot-host: 193.114.89.*, 194.168.54.11\r
+robot-from: yes\r
+robot-useragent: MuscatFerret/<version>\r
+robot-language: c, perl5\r
+robot-description: Used to build the database for the EuroFerret\r
+ <URL:http://www.muscat.co.uk/euroferret/>\r
+robot-history:\r
+robot-environment: service\r
+modified-date: Tue, 21 May 1997 17:11:00 GMT\r
+modified-by: olly@muscat.co.uk\r
+\r
+robot-id: mwdsearch\r
+robot-name: Mwd.Search\r
+robot-cover-url: (none)\r
+robot-details-url: (none)\r
+robot-owner-name: Antti Westerberg\r
+robot-owner-url: (none)\r
+robot-owner-email: Antti.Westerberg@mwd.sci.fi\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix (Linux)\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: MwdSearch\r
+robot-noindex: yes\r
+robot-host: *.fifi.net\r
+robot-from: no\r
+robot-useragent: MwdSearch/0.1\r
+robot-language: perl5, c\r
+robot-description: Robot for indexing finnish (toplevel domain .fi)\r
+ webpages for search engine called Fifi.\r
+ Visits sites in random order.\r
+robot-history: (none)\r
+robot-environment: service (+ commercial)mwd.sci.fi>\r
+modified-date: Mon, 26 May 1997 15:55:02 EEST\r
+modified-by: Antti.Westerberg@mwd.sci.fi\r
+\r
+robot-id: myweb\r
+robot-name: Internet Shinchakubin\r
+robot-cover-url: http://naragw.sharp.co.jp/myweb/home/\r
+robot-details-url:\r
+robot-owner-name: SHARP Corp.\r
+robot-owner-url: http://naragw.sharp.co.jp/myweb/home/\r
+robot-owner-email: shinchakubin-request@isl.nara.sharp.co.jp\r
+robot-status: active\r
+robot-purpose: find new links and changed pages\r
+robot-type: standalone\r
+robot-platform: Windows98\r
+robot-availability: binary as bundled software\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: sharp-info-agent\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: User-Agent: Mozilla/4.0 (compatible; sharp-info-agent v1.0; )\r
+robot-language: Java\r
+robot-description: makes a list of new links and changed pages based\r
+ on user's frequently clicked pages in the past 31 days.\r
+ client may run this software one or few times every day, manually or\r
+ specified time.\r
+robot-history: shipped for SHARP's PC users since Feb 2000\r
+robot-environment: commercial\r
+modified-date: Fri, 30 Jun 2000 19:02:52 JST\r
+modified-by: Katsuo Doi <doi@isl.nara.sharp.co.jp>\r
+\r
+robot-id: netcarta\r
+robot-name: NetCarta WebMap Engine\r
+robot-cover-url: http://www.netcarta.com/\r
+robot-details-url:\r
+robot-owner-name: NetCarta WebMap Engine\r
+robot-owner-url: http://www.netcarta.com/\r
+robot-owner-email: info@netcarta.com\r
+robot-status:\r
+robot-purpose: indexing, maintenance, mirroring, statistics\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: NetCarta CyberPilot Pro\r
+robot-language: C++.\r
+robot-description: The NetCarta WebMap Engine is a general purpose, commercial\r
+ spider. Packaged with a full GUI in the CyberPilo Pro\r
+ product, it acts as a personal spider to work with a browser\r
+ to facilitiate context-based navigation. The WebMapper\r
+ product uses the robot to manage a site (site copy, site\r
+ diff, and extensive link management facilities). All\r
+ versions can create publishable NetCarta WebMaps, which\r
+ capture the crawled information. If the robot sees a\r
+ published map, it will return the published map rather than\r
+ continuing its crawl. Since this is a personal spider, it\r
+ will be launched from multiple domains. This robot tends to\r
+ focus on a particular site. No instance of the robot should\r
+ have more than one outstanding request out to any given site\r
+ at a time. The User-agent field contains a coded ID\r
+ identifying the instance of the spider; specific users can\r
+ be blocked via robots.txt using this ID.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sun Feb 18 02:02:49 1996.\r
+modified-by:\r
+\r
+robot-id: netmechanic\r
+robot-name: NetMechanic\r
+robot-cover-url: http://www.netmechanic.com\r
+robot-details-url: http://www.netmechanic.com/faq.html\r
+robot-owner-name: Tom Dahm\r
+robot-owner-url: http://iquest.com/~tdahm\r
+robot-owner-email: tdahm@iquest.com\r
+robot-status: development\r
+robot-purpose: Link and HTML validation\r
+robot-type: standalone with web gateway\r
+robot-platform: UNIX\r
+robot-availability: via web page\r
+robot-exclusion: Yes\r
+robot-exclusion-useragent: WebMechanic\r
+robot-noindex: no\r
+robot-host: 206.26.168.18\r
+robot-from: no\r
+robot-useragent: NetMechanic\r
+robot-language: C\r
+robot-description: NetMechanic is a link validation and\r
+ HTML validation robot run using a web page interface.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sat, 17 Aug 1996 12:00:00 GMT\r
+modified-by:\r
+\r
+robot-id: netscoop\r
+robot-name: NetScoop\r
+robot-cover-url: http://www-a2k.is.tokushima-u.ac.jp/search/index.html\r
+robot-owner-name: Kenji Kita\r
+robot-owner-url: http://www-a2k.is.tokushima-u.ac.jp/member/kita/index.html\r
+robot-owner-email: kita@is.tokushima-u.ac.jp\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: NetScoop\r
+robot-host: alpha.is.tokushima-u.ac.jp, beta.is.tokushima-u.ac.jp\r
+robot-useragent: NetScoop/1.0 libwww/5.0a\r
+robot-language: C\r
+robot-description: The NetScoop robot is used to build the database\r
+ for the NetScoop search engine.\r
+robot-history: The robot has been used in the research project\r
+ at the Faculty of Engineering, Tokushima University, Japan.,\r
+ since Dec. 1996.\r
+robot-environment: research\r
+modified-date: Fri, 10 Jan 1997.\r
+modified-by: Kenji Kita\r
+\r
+robot-id: newscan-online\r
+robot-name: newscan-online\r
+robot-cover-url: http://www.newscan-online.de/\r
+robot-details-url: http://www.newscan-online.de/info.html\r
+robot-owner-name: Axel Mueller\r
+robot-owner-url:\r
+robot-owner-email: mueller@newscan-online.de\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Linux\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: newscan-online\r
+robot-noindex: no\r
+robot-host: *newscan-online.de\r
+robot-from: yes\r
+robot-useragent: newscan-online/1.1\r
+robot-language: perl\r
+robot-description: The newscan-online robot is used to build a database for\r
+ the newscan-online news search service operated by smart information\r
+ services. The robot runs daily and visits predefined sites in a random order.\r
+robot-history: This robot finds its roots in a prereleased software for\r
+ news filtering for Lotus Notes in 1995.\r
+robot-environment: service\r
+modified-date: Fri, 9 Apr 1999 11:45:00 GMT\r
+modified-by: Axel Mueller\r
+\r
+robot-id: nhse\r
+robot-name: NHSE Web Forager\r
+robot-cover-url: http://nhse.mcs.anl.gov/\r
+robot-details-url:\r
+robot-owner-name: Robert Olson\r
+robot-owner-url: http://www.mcs.anl.gov/people/olson/\r
+robot-owner-email: olson@mcs.anl.gov\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *.mcs.anl.gov\r
+robot-from: yes\r
+robot-useragent: NHSEWalker/3.0\r
+robot-language: perl 5\r
+robot-description: to generate a Resource Discovery database\r
+robot-history: \r
+robot-environment:\r
+modified-date: Fri May 5 15:47:55 1995\r
+modified-by:\r
+\r
+robot-id: nomad\r
+robot-name: Nomad\r
+robot-cover-url: http://www.cs.colostate.edu/~sonnen/projects/nomad.html\r
+robot-details-url:\r
+robot-owner-name: Richard Sonnen\r
+robot-owner-url: http://www.cs.colostate.edu/~sonnen/\r
+robot-owner-email: sonnen@cs.colostat.edu\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: *.cs.colostate.edu\r
+robot-from: no\r
+robot-useragent: Nomad-V2.x\r
+robot-language: Perl 4\r
+robot-description:\r
+robot-history: Developed in 1995 at Colorado State University.\r
+robot-environment:\r
+modified-date: Sat Jan 27 21:02:20 1996.\r
+modified-by:\r
+\r
+robot-id: northstar\r
+robot-name: The NorthStar Robot\r
+robot-cover-url: http://comics.scs.unr.edu:7000/top.html\r
+robot-details-url:\r
+robot-owner-name: Fred Barrie\r
+robot-owner-url: \r
+robot-owner-email: barrie@unr.edu\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: \r
+robot-host: frognot.utdallas.edu, utdallas.edu, cnidir.org\r
+robot-from: yes\r
+robot-useragent: NorthStar\r
+robot-language: \r
+robot-description: Recent runs (26 April 94) will concentrate on textual\r
+ analysis of the Web versus GopherSpace (from the Veronica\r
+ data) as well as indexing.\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: occam\r
+robot-name: Occam\r
+robot-cover-url: http://www.cs.washington.edu/research/projects/ai/www/occam/\r
+robot-details-url:\r
+robot-owner-name: Marc Friedman\r
+robot-owner-url: http://www.cs.washington.edu/homes/friedman/\r
+robot-owner-email: friedman@cs.washington.edu\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Occam\r
+robot-noindex: no\r
+robot-host: gentian.cs.washington.edu, sekiu.cs.washington.edu, saxifrage.cs.washington.edu\r
+robot-from: yes\r
+robot-useragent: Occam/1.0\r
+robot-language: CommonLisp, perl4\r
+robot-description: The robot takes high-level queries, breaks them down into\r
+ multiple web requests, and answers them by combining disparate\r
+ data gathered in one minute from numerous web sites, or from\r
+ the robots cache. Currently the only user is me.\r
+robot-history: The robot is a descendant of Rodney,\r
+ an earlier project at the University of Washington.\r
+robot-environment: research\r
+modified-date: Thu, 21 Nov 1996 20:30 GMT\r
+modified-by: friedman@cs.washington.edu (Marc Friedman)\r
+\r
+robot-id: octopus\r
+robot-name: HKU WWW Octopus\r
+robot-cover-url: http://phoenix.cs.hku.hk:1234/~jax/w3rui.shtml\r
+robot-details-url:\r
+robot-owner-name: Law Kwok Tung , Lee Tak Yeung , Lo Chun Wing\r
+robot-owner-url: http://phoenix.cs.hku.hk:1234/~jax\r
+robot-owner-email: jax@cs.hku.hk\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no.\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: phoenix.cs.hku.hk\r
+robot-from: yes\r
+robot-useragent: HKU WWW Robot, \r
+robot-language: Perl 5, C, Java.\r
+robot-description: HKU Octopus is an ongoing project for resource discovery in\r
+ the Hong Kong and China WWW domain . It is a research\r
+ project conducted by three undergraduate at the University\r
+ of Hong Kong\r
+robot-history:\r
+robot-environment:\r
+modified-date: Thu Mar 7 14:21:55 1996.\r
+modified-by:\r
+\r
+robot-id: orb_search\r
+robot-name: Orb Search\r
+robot-cover-url: http://orbsearch.home.ml.org\r
+robot-details-url: http://orbsearch.home.ml.org\r
+robot-owner-name: Matt Weber\r
+robot-owner-url: http://www.weberworld.com\r
+robot-owner-email: webernet@geocities.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Orbsearch/1.0\r
+robot-noindex: yes\r
+robot-host: cow.dyn.ml.org, *.dyn.ml.org\r
+robot-from: yes\r
+robot-useragent: Orbsearch/1.0\r
+robot-language: Perl5\r
+robot-description: Orbsearch builds the database for Orb Search Engine.\r
+ It runs when requested.\r
+robot-history: This robot was started as a hobby.\r
+robot-environment: hobby\r
+modified-date: Sun, 31 Aug 1997 02:28:52 GMT\r
+modified-by: Matt Weber\r
+\r
+robot-id: packrat\r
+robot-name: Pack Rat\r
+robot-cover-url: http://web.cps.msu.edu/~dexterte/isl/packrat.html\r
+robot-details-url: \r
+robot-owner-name: Terry Dexter\r
+robot-owner-url: http://web.cps.msu.edu/~dexterte\r
+robot-owner-email: dexterte@cps.msu.edu\r
+robot-status: development\r
+robot-purpose: both maintenance and mirroring\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: at the moment, none...source when developed.\r
+robot-exclusion: yes \r
+robot-exclusion-useragent: packrat or *\r
+robot-noindex: no, not yet\r
+robot-host: cps.msu.edu\r
+robot-from: \r
+robot-useragent: PackRat/1.0\r
+robot-language: perl with libwww-5.0\r
+robot-description: Used for local maintenance and for gathering \r
+ web pages so\r
+ that local statisistical info can be used in artificial intelligence programs.\r
+ Funded by NEMOnline.\r
+robot-history: In the making...\r
+robot-environment: research\r
+modified-date: Tue, 20 Aug 1996 15:45:11\r
+modified-by: Terry Dexter\r
+\r
+robot-id:pageboy\r
+robot-name:PageBoy\r
+robot-cover-url:http://www.webdocs.org/\r
+robot-details-url:http://www.webdocs.org/ \r
+robot-owner-name:Chihiro Kuroda \r
+robot-owner-url:http://www.webdocs.org/\r
+robot-owner-email:pageboy@webdocs.org\r
+robot-status:development\r
+robot-purpose:indexing\r
+robot-type:standalone\r
+robot-platform:unix\r
+robot-availability:none\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:pageboy\r
+robot-noindex:yes\r
+robot-nofollow:yes\r
+robot-host:*.webdocs.org\r
+robot-from:yes\r
+robot-useragent:PageBoy/1.0\r
+robot-language:c\r
+robot-description:The robot visits at regular intervals.\r
+robot-history:none\r
+robot-environment:service\r
+modified-date:Fri, 21 Oct 1999 17:28:52 GMT\r
+modified-by:webdocs\r
+\r
+robot-id: parasite\r
+robot-name: ParaSite\r
+robot-cover-url: http://www.ianett.com/parasite/\r
+robot-details-url: http://www.ianett.com/parasite/\r
+robot-owner-name: iaNett.com\r
+robot-owner-url: http://www.ianett.com/\r
+robot-owner-email: parasite@ianett.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: ParaSite\r
+robot-noindex: yes\r
+robot-nofollow: yes\r
+robot-host: *.ianett.com\r
+robot-from: yes\r
+robot-useragent: ParaSite/0.21 (http://www.ianett.com/parasite/)\r
+robot-language: c++\r
+robot-description: Builds index for ianett.com search database. Runs\r
+ continiously.\r
+robot-history: Second generation of ianett.com spidering technology,\r
+ originally called Sven.\r
+robot-environment: service\r
+modified-date: July 28, 2000\r
+modified-by: Marty Anstey\r
+\r
+robot-id: patric\r
+robot-name: Patric\r
+robot-cover-url: http://www.nwnet.net/technical/ITR/index.html\r
+robot-details-url: http://www.nwnet.net/technical/ITR/index.html\r
+robot-owner-name: toney@nwnet.net\r
+robot-owner-url: http://www.nwnet.net/company/staff/toney\r
+robot-owner-email: webmaster@nwnet.net\r
+robot-status: development\r
+robot-purpose: statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: patric \r
+robot-noindex: yes \r
+robot-host: *.nwnet.net \r
+robot-from: no\r
+robot-useragent: Patric/0.01a \r
+robot-language: perl\r
+robot-description: (contained at http://www.nwnet.net/technical/ITR/index.html )\r
+robot-history: (contained at http://www.nwnet.net/technical/ITR/index.html )\r
+robot-environment: service \r
+modified-date: Thurs, 15 Aug 1996\r
+modified-by: toney@nwnet.net\r
+\r
+robot-id: perignator\r
+robot-name: The Peregrinator\r
+robot-cover-url: http://www.maths.usyd.edu.au:8000/jimr/pe/Peregrinator.html\r
+robot-details-url:\r
+robot-owner-name: Jim Richardson\r
+robot-owner-url: http://www.maths.usyd.edu.au:8000/jimr.html\r
+robot-owner-email: jimr@maths.su.oz.au\r
+robot-status: \r
+robot-purpose: \r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: yes\r
+robot-useragent: Peregrinator-Mathematics/0.7\r
+robot-language: perl 4\r
+robot-description: This robot is being used to generate an index of documents\r
+ on Web sites connected with mathematics and statistics. It\r
+ ignores off-site links, so does not stray from a list of\r
+ servers specified initially.\r
+robot-history: commenced operation in August 1994\r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: perlcrawler\r
+robot-name: PerlCrawler 1.0\r
+robot-cover-url: http://perlsearch.hypermart.net/\r
+robot-details-url: http://www.xav.com/scripts/xavatoria/index.html\r
+robot-owner-name: Matt McKenzie \r
+robot-owner-url: http://perlsearch.hypermart.net/\r
+robot-owner-email: webmaster@perlsearch.hypermart.net\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: perlcrawler\r
+robot-noindex: yes\r
+robot-host: server5.hypermart.net\r
+robot-from: yes\r
+robot-useragent: PerlCrawler/1.0 Xavatoria/2.0\r
+robot-language: perl5\r
+robot-description: The PerlCrawler robot is designed to index and build\r
+ a database of pages relating to the Perl programming language.\r
+robot-history: Originated in modified form on 25 June 1998\r
+robot-environment: hobby\r
+modified-date: Fri, 18 Dec 1998 23:37:40 GMT\r
+modified-by: Matt McKenzie\r
+\r
+robot-id: phantom\r
+robot-name: Phantom\r
+robot-cover-url: http://www.maxum.com/phantom/\r
+robot-details-url:\r
+robot-owner-name: Larry Burke\r
+robot-owner-url: http://www.aktiv.com/\r
+robot-owner-email: lburke@aktiv.com\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Macintosh\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: Duppies\r
+robot-language:\r
+robot-description: Designed to allow webmasters to provide a searchable index\r
+ of their own site as well as to other sites, perhaps with\r
+ similar content.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Fri Jan 19 05:08:15 1996.\r
+modified-by:\r
+\r
+robot-id: piltdownman\r
+robot-name: PiltdownMan\r
+robot-cover-url: http://profitnet.bizland.com/\r
+robot-details-url: http://profitnet.bizland.com/piltdownman.html\r
+robot-owner-name: Daniel Vilà\r
+robot-owner-url: http://profitnet.bizland.com/aboutus.html\r
+robot-owner-email: profitnet@myezmail.com\r
+robot-status: active\r
+robot-purpose: statistics\r
+robot-type: standalone\r
+robot-platform: windows95, windows98, windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: piltdownman\r
+robot-noindex: no\r
+robot-nofollow: no\r
+robot-host: 62.36.128.*, 194.133.59.*, 212.106.215.*\r
+robot-from: no\r
+robot-useragent: PiltdownMan/1.0 profitnet@myezmail.com\r
+robot-language: c++\r
+robot-description: The PiltdownMan robot is used to get a\r
+ list of links from the search engines\r
+ in our database. These links are\r
+ followed, and the page that they refer\r
+ is downloaded to get some statistics\r
+ from them.\r
+ The robot runs once a month, more or\r
+ less, and visits the first 10 pages\r
+ listed in every search engine, for a\r
+ group of keywords.\r
+robot-history: To maintain a database of search engines,\r
+ we needed an automated tool. That's why\r
+ we began the creation of this robot.\r
+robot-environment: service\r
+modified-date: Mon, 13 Dec 1999 21:50:32 GMT\r
+modified-by: Daniel Vilà\r
+\r
+robot-id: pioneer\r
+robot-name: Pioneer\r
+robot-cover-url: http://sequent.uncfsu.edu/~micah/pioneer.html\r
+robot-details-url:\r
+robot-owner-name: Micah A. Williams\r
+robot-owner-url: http://sequent.uncfsu.edu/~micah/\r
+robot-owner-email: micah@sequent.uncfsu.edu\r
+robot-status:\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: *.uncfsu.edu or flyer.ncsc.org\r
+robot-from: yes\r
+robot-useragent: Pioneer\r
+robot-language: C.\r
+robot-description: Pioneer is part of an undergraduate research\r
+ project.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Mon Feb 5 02:49:32 1996.\r
+modified-by:\r
+\r
+robot-id: pitkow\r
+robot-name: html_analyzer\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: James E. Pitkow\r
+robot-owner-url: \r
+robot-owner-email: pitkow@aries.colorado.edu\r
+robot-status: \r
+robot-purpose: maintainance\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: to check validity of Web servers. I'm not sure if it has\r
+ ever been run remotely.\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: pjspider\r
+robot-name: Portal Juice Spider\r
+robot-cover-url: http://www.portaljuice.com\r
+robot-details-url: http://www.portaljuice.com/pjspider.html\r
+robot-owner-name: Nextopia Software Corporation\r
+robot-owner-url: http://www.portaljuice.com\r
+robot-owner-email: pjspider@portaljuice.com\r
+robot-status: active\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: pjspider\r
+robot-noindex: yes\r
+robot-host: *.portaljuice.com, *.nextopia.com\r
+robot-from: yes\r
+robot-useragent: PortalJuice.com/4.0\r
+robot-language: C/C++\r
+robot-description: Indexing web documents for Portal Juice vertical portal\r
+ search engine\r
+robot-history: Indexing the web since 1998 for the purposes of offering our\r
+ commerical Portal Juice search engine services.\r
+robot-environment: service\r
+modified-date: Wed Jun 23 17:00:00 EST 1999\r
+modified-by: pjspider@portaljuice.com\r
+\r
+robot-id: pka\r
+robot-name: PGP Key Agent\r
+robot-cover-url: http://www.starnet.it/pgp\r
+robot-details-url:\r
+robot-owner-name: Massimiliano Pucciarelli\r
+robot-owner-url: http://www.starnet.it/puma\r
+robot-owner-email: puma@comm2000.it\r
+robot-status: Active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: UNIX, Windows NT\r
+robot-availability: none\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: salerno.starnet.it\r
+robot-from: yes\r
+robot-useragent: PGP-KA/1.2\r
+robot-language: Perl 5\r
+robot-description: This program search the pgp public key for the \r
+ specified user.\r
+robot-history: Originated as a research project at Salerno \r
+ University in 1995.\r
+robot-environment: Research\r
+modified-date: June 27 1996.\r
+modified-by: Massimiliano Pucciarelli\r
+\r
+robot-id: plumtreewebaccessor\r
+robot-name: PlumtreeWebAccessor \r
+robot-cover-url:\r
+robot-details-url: http://www.plumtree.com/\r
+robot-owner-name: Joseph A. Stanko \r
+robot-owner-url:\r
+robot-owner-email: josephs@plumtree.com\r
+robot-status: development\r
+robot-purpose: indexing for the Plumtree Server\r
+robot-type: standalone\r
+robot-platform: windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: PlumtreeWebAccessor\r
+robot-noindex: yes\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: PlumtreeWebAccessor/0.9\r
+robot-language: c++\r
+robot-description: The Plumtree Web Accessor is a component that\r
+ customers can add to the\r
+ Plumtree Server to index documents on the World Wide Web.\r
+robot-history:\r
+robot-environment: commercial\r
+modified-date: Thu, 17 Dec 1998\r
+modified-by: Joseph A. Stanko <josephs@plumtree.com>\r
+\r
+robot-id: poppi\r
+robot-name: Poppi\r
+robot-cover-url: http://members.tripod.com/poppisearch\r
+robot-details-url: http://members.tripod.com/poppisearch\r
+robot-owner-name: Antonio Provenzano\r
+robot-owner-url: Antonio Provenzano\r
+robot-owner-email:\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix/linux\r
+robot-availability: none\r
+robot-exclusion:\r
+robot-exclusion-useragent:\r
+robot-noindex: yes\r
+robot-host:=20\r
+robot-from:\r
+robot-useragent: Poppi/1.0\r
+robot-language: C\r
+robot-description: Poppi is a crawler to index the web that runs weekly \r
+ gathering and indexing hypertextual, multimedia and executable file \r
+ formats\r
+robot-history: Created by Antonio Provenzano in the april of 2000, has \r
+ been acquired from Tomi Officine Multimediali srl and it is next to \r
+ release as service and commercial\r
+robot-environment: service\r
+modified-date: Mon, 22 May 2000 15:47:30 GMT\r
+modified-by: Antonio Provenzano\r
+\r
+robot-id: portalb\r
+robot-name: PortalB Spider\r
+robot-cover-url: http://www.portalb.com/\r
+robot-details-url:\r
+robot-owner-name: PortalB Spider Bug List\r
+robot-owner-url:\r
+robot-owner-email: spider@portalb.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: PortalBSpider\r
+robot-noindex: yes\r
+robot-nofollow: yes\r
+robot-host: spider1.portalb.com, spider2.portalb.com, etc.\r
+robot-from: no\r
+robot-useragent: PortalBSpider/1.0 (spider@portalb.com)\r
+robot-language: C++\r
+robot-description: The PortalB Spider indexes selected sites for\r
+ high-quality business information.\r
+robot-history:\r
+robot-environment: service\r
+\r
+robot-id: Puu\r
+robot-name: GetterroboPlus Puu\r
+robot-details-url: http://marunaka.homing.net/straight/getter/\r
+robot-cover-url: http://marunaka.homing.net/straight/\r
+robot-owner-name: marunaka\r
+robot-owner-url: http://marunaka.homing.net\r
+robot-owner-email: marunaka@homing.net\r
+robot-status: active: robot actively in use\r
+robot-purpose: Purpose of the robot. One or more of:\r
+ - gathering: gather data of original standerd TAG for Puu contains the\r
+ information of the sites registered my Search Engin.\r
+ - maintenance: link validation\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes (Puu patrols only registered url in my Search Engine)\r
+robot-exclusion-useragent: Getterrobo-Plus\r
+robot-noindex: no\r
+robot-host: straight FLASH!! Getterrobo-Plus, *.homing.net\r
+robot-from: yes\r
+robot-useragent: straight FLASH!! GetterroboPlus 1.5\r
+robot-language: perl5\r
+robot-description:\r
+ Puu robot is used to gater data from registered site in Search Engin\r
+ "straight FLASH!!" for building anouncement page of state of renewal of\r
+ registered site in "straight FLASH!!".\r
+ Robot runs everyday.\r
+robot-history:\r
+ This robot patorols based registered sites in Search Engin "straight FLASH!!"\r
+robot-environment: hobby\r
+modified-date: Fri, 26 Jun 1998\r
+\r
+robot-id: python\r
+robot-name: The Python Robot\r
+robot-cover-url: http://www.python.org/\r
+robot-details-url: \r
+robot-owner-name: Guido van Rossum\r
+robot-owner-url: http://www.python.org/~guido/\r
+robot-owner-email: guido@python.org\r
+robot-status: retired\r
+robot-purpose: \r
+robot-type: \r
+robot-platform: \r
+robot-availability: none\r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: \r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: raven \r
+robot-name: Raven Search\r
+robot-cover-url: http://ravensearch.tripod.com\r
+robot-details-url: http://ravensearch.tripod.com\r
+robot-owner-name: Raven Group\r
+robot-owner-url: http://ravensearch.tripod.com\r
+robot-owner-email: ravensearch@hotmail.com\r
+robot-status: Development: robot under development\r
+robot-purpose: Indexing: gather content for commercial query engine.\r
+robot-type: Standalone: a separate program\r
+robot-platform: Unix, Windows98, WindowsNT, Windows2000\r
+robot-availability: None\r
+robot-exclusion: Yes\r
+robot-exclusion-useragent: Raven\r
+robot-noindex: Yes\r
+robot-nofollow: Yes\r
+robot-host: 192.168.1.*\r
+robot-from: Yes\r
+robot-useragent: Raven-v2\r
+robot-language: Perl-5\r
+robot-description: Raven was written for the express purpose of indexing the web.\r
+ It can parallel process hundreds of URLS's at a time. It runs on a sporadic basis \r
+ as testing continues. It is really several programs running concurrently.\r
+ It takes four computers to run Raven Search. Scalable in sets of four.\r
+robot-history: This robot is new. First active on March 25, 2000.\r
+robot-environment: Commercial: is a commercial product. Possibly GNU later ;-)\r
+modified-date: Fri, 25 Mar 2000 17:28:52 GMT\r
+modified-by: Raven Group\r
+\r
+robot-id: rbse\r
+robot-name: RBSE Spider\r
+robot-cover-url: http://rbse.jsc.nasa.gov/eichmann/urlsearch.html\r
+robot-details-url:\r
+robot-owner-name: David Eichmann\r
+robot-owner-url: http://rbse.jsc.nasa.gov/eichmann/home.html\r
+robot-owner-email: eichmann@rbse.jsc.nasa.gov\r
+robot-status: active\r
+robot-purpose: indexing, statistics\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: \r
+robot-host: rbse.jsc.nasa.gov (192.88.42.10)\r
+robot-from: \r
+robot-useragent: \r
+robot-language: C, oracle, wais\r
+robot-description: Developed and operated as part of the NASA-funded Repository\r
+ Based Software Engineering Program at the Research Institute\r
+ for Computing and Information Systems, University of Houston\r
+ - Clear Lake.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Thu May 18 04:47:02 1995\r
+modified-by:\r
+\r
+robot-id: resumerobot\r
+robot-name: Resume Robot\r
+robot-cover-url: http://www.onramp.net/proquest/resume/robot/robot.html\r
+robot-details-url:\r
+robot-owner-name: James Stakelum\r
+robot-owner-url: http://www.onramp.net/proquest/resume/java/resume.html\r
+robot-owner-email: proquest@onramp.net\r
+robot-status:\r
+robot-purpose: indexing.\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: Resume Robot\r
+robot-language: C++.\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Tue Mar 12 15:52:25 1996.\r
+modified-by:\r
+\r
+robot-id: rhcs\r
+robot-name: RoadHouse Crawling System\r
+robot-cover-url: http://stage.perceval.be (under developpement)\r
+robot-details-url:\r
+robot-owner-name: Gregoire Welraeds, Emmanuel Bergmans\r
+robot-owner-url: http://www.perceval.be\r
+robot-owner-email: helpdesk@perceval.be\r
+robot-status: development\r
+robot-purpose1: indexing\r
+robot-purpose2: maintenance\r
+robot-purpose3: statistics\r
+robot-type: standalone\r
+robot-platform1: unix (FreeBSD & Linux)\r
+robot-availability: none\r
+robot-exclusion: no (under development)\r
+robot-exclusion-useragent: RHCS\r
+robot-noindex: no (under development)\r
+robot-host: stage.perceval.be\r
+robot-from: no\r
+robot-useragent: RHCS/1.0a\r
+robot-language: c\r
+robot-description: robot used tp build the database for the RoadHouse search service project operated by Perceval \r
+robot-history: The need of this robot find its roots in the actual RoadHouse directory not maintenained since 1997\r
+robot-environment: service\r
+modified-date: Fri, 26 Feb 1999 12:00:00 GMT\r
+modified-by: Gregoire Welraeds\r
+\r
+robot-id: roadrunner\r
+robot-name: Road Runner: The ImageScape Robot\r
+robot-owner-name: LIM Group\r
+robot-owner-email: lim@cs.leidenuniv.nl\r
+robot-status: development/active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: roadrunner\r
+robot-useragent: Road Runner: ImageScape Robot (lim@cs.leidenuniv.nl)\r
+robot-language: C, perl5\r
+robot-description: Create Image/Text index for WWW\r
+robot-history: ImageScape Project\r
+robot-environment: commercial service\r
+modified-date: Dec. 1st, 1996\r
+\r
+robot-id: robbie\r
+robot-name: Robbie the Robot\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Robert H. Pollack\r
+robot-owner-url:\r
+robot-owner-email: robert.h.pollack@lmco.com\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix, windows95, windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Robbie\r
+robot-noindex: no\r
+robot-host: *.lmco.com\r
+robot-from: yes\r
+robot-useragent: Robbie/0.1\r
+robot-language: java\r
+robot-description: Used to define document collections for the DISCO system.\r
+ Robbie is still under development and runs several\r
+ times a day, but usually only for ten minutes or so.\r
+ Sites are visited in the order in which references\r
+ are found, but no host is visited more than once in\r
+ any two-minute period.\r
+robot-history: The DISCO system is a resource-discovery component in\r
+ the OLLA system, which is a prototype system, developed\r
+ under DARPA funding, to support computer-based education\r
+ and training.\r
+robot-environment: research\r
+modified-date: Wed, 5 Feb 1997 19:00:00 GMT\r
+modified-by:\r
+\r
+\r
+robot-id: robi\r
+robot-name: ComputingSite Robi/1.0\r
+robot-cover-url: http://www.computingsite.com/robi/\r
+robot-details-url: http://www.computingsite.com/robi/\r
+robot-owner-name: Tecor Communications S.L.\r
+robot-owner-url: http://www.tecor.com/\r
+robot-owner-email: robi@computingsite.com\r
+robot-status: Active\r
+robot-purpose: indexing,maintenance\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: robi\r
+robot-noindex: no\r
+robot-host: robi.computingsite.com\r
+robot-from:\r
+robot-useragent: ComputingSite Robi/1.0 (robi@computingsite.com)\r
+robot-language: python\r
+robot-description: Intelligent agent used to build the ComputingSite Search\r
+ Directory.\r
+robot-history: It was born on August 1997.\r
+robot-environment: service\r
+modified-date: Wed, 13 May 1998 17:28:52 GMT\r
+modified-by: Jorge Alegre\r
+\r
+robot-id: roverbot\r
+robot-name: Roverbot\r
+robot-cover-url: http://www.roverbot.com/\r
+robot-details-url:\r
+robot-owner-name: GlobalMedia Design (Andrew Cowan & Brian\r
+ Clark)\r
+robot-owner-url: http://www.radzone.org/gmd/\r
+robot-owner-email: gmd@spyder.net\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: roverbot.com\r
+robot-from: yes\r
+robot-useragent: Roverbot\r
+robot-language: perl5\r
+robot-description: Targeted email gatherer utilizing user-defined seed points\r
+ and interacting with both the webserver and MX servers of\r
+ remote sites.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Tue Jun 18 19:16:31 1996.\r
+modified-by:\r
+\r
+robot-id: safetynetrobot\r
+robot-name: SafetyNet Robot\r
+robot-cover-url: http://www.urlabs.com/\r
+robot-details-url:\r
+robot-owner-name: Michael L. Nelson\r
+robot-owner-url: http://www.urlabs.com/\r
+robot-owner-email: m.l.nelson@urlabs.com\r
+robot-status:\r
+robot-purpose: indexing.\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no.\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: *.urlabs.com\r
+robot-from: yes\r
+robot-useragent: SafetyNet Robot 0.1, \r
+robot-language: Perl 5\r
+robot-description: Finds URLs for K-12 content management.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sat Mar 23 20:12:39 1996.\r
+modified-by:\r
+\r
+robot-id: scooter\r
+robot-name: Scooter\r
+robot-cover-url: http://www.altavista.com/\r
+robot-details-url: http://www.altavista.com/av/content/addurl.htm\r
+robot-owner-name: AltaVista\r
+robot-owner-url: http://www.altavista.com/\r
+robot-owner-email: scooter@pa.dec.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Scooter\r
+robot-noindex: yes\r
+robot-host: *.av.pa-x.dec.com\r
+robot-from: yes\r
+robot-useragent: Scooter/2.0 G.R.A.B. V1.1.0\r
+robot-language: c\r
+robot-description: Scooter is AltaVista's prime index agent.\r
+robot-history: Version 2 of Scooter/1.0 developed by Louis Monier of WRL.\r
+robot-environment: service\r
+modified-date: Wed, 13 Jan 1999 17:18:59 GMT\r
+modified-by: steves@avs.dec.com\r
+\r
+robot-id: search_au\r
+robot-name: Search.Aus-AU.COM\r
+robot-details-url: http://Search.Aus-AU.COM/\r
+robot-cover-url: http://Search.Aus-AU.COM/\r
+robot-owner-name: Dez Blanchfield\r
+robot-owner-url: not currently available\r
+robot-owner-email: dez@geko.com\r
+robot-status: - development: robot under development\r
+robot-purpose: - indexing: gather content for an indexing service\r
+robot-type: - standalone: a separate program\r
+robot-platform: - mac - unix - windows95 - windowsNT\r
+robot-availability: - none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Search-AU\r
+robot-noindex: yes\r
+robot-host: Search.Aus-AU.COM, 203.55.124.29, 203.2.239.29\r
+robot-from: no\r
+robot-useragent: not available\r
+robot-language: c, perl, sql\r
+robot-description: Search-AU is a development tool I have built\r
+ to investigate the power of a search engine and web crawler\r
+ to give me access to a database of web content ( html / url's )\r
+ and address's etc from which I hope to build more accurate stats\r
+ about the .au zone's web content.\r
+ the robot started crawling from http://www.geko.net.au/ on\r
+ march 1st, 1998 and after nine days had 70mb of compressed ascii\r
+ in a database to work with. i hope to run a refresh of the crawl\r
+ every month initially, and soon every week bandwidth and cpu allowing.\r
+ if the project warrants further development, i will turn it into\r
+ an australian ( .au ) zone search engine and make it commercially\r
+ available for advertising to cover the costs which are starting\r
+ to mount up. --dez (980313 - black friday!)\r
+robot-environment: - hobby: written as a hobby\r
+modified-date: Fri Mar 13 10:03:32 EST 1998\r
+\r
+robot-id: searchprocess\r
+robot-name: SearchProcess\r
+robot-cover-url: http://www.searchprocess.com\r
+robot-details-url: http://www.intelligence-process.com\r
+robot-owner-name: Mannina Bruno\r
+robot-owner-url: http://www.intelligence-process.com\r
+robot-owner-email: bruno@intelligence-process.com\r
+robot-status: active\r
+robot-purpose: Statistic\r
+robot-type: browser\r
+robot-platform: linux\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: searchprocess\r
+robot-noindex: yes\r
+robot-host: searchprocess.com\r
+robot-from: yes\r
+robot-useragent: searchprocess/0.9\r
+robot-language: perl\r
+robot-description: An intelligent Agent Online. SearchProcess is used to\r
+ provide structured information to user.\r
+robot-history: This is the son of Auresys\r
+robot-environment: Service freeware\r
+modified-date: Thus, 22 Dec 1999\r
+modified-by: Mannina Bruno\r
+\r
+robot-id: senrigan\r
+robot-name: Senrigan\r
+robot-cover-url: http://www.info.waseda.ac.jp/search-e.html\r
+robot-details-url:\r
+robot-owner-name: TAMURA Kent\r
+robot-owner-url: http://www.info.waseda.ac.jp/muraoka/members/kent/\r
+robot-owner-email: kent@muraoka.info.waseda.ac.jp\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Java\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:Senrigan\r
+robot-noindex: yes\r
+robot-host: aniki.olu.info.waseda.ac.jp\r
+robot-from: yes\r
+robot-useragent: Senrigan/xxxxxx\r
+robot-language: Java\r
+robot-description: This robot now gets HTMLs from only jp domain.\r
+robot-history: It has been running since Dec 1994\r
+robot-environment: research\r
+modified-date: Mon Jul 1 07:30:00 GMT 1996\r
+modified-by: TAMURA Kent\r
+\r
+robot-id: sgscout\r
+robot-name: SG-Scout\r
+robot-cover-url: http://www-swiss.ai.mit.edu/~ptbb/SG-Scout/SG-Scout.html\r
+robot-details-url:\r
+robot-owner-name: Peter Beebee\r
+robot-owner-url: http://www-swiss.ai.mit.edu/~ptbb/personal/index.html\r
+robot-owner-email: ptbb@ai.mit.edu, beebee@parc.xerox.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: beta.xerox.com\r
+robot-from: yes\r
+robot-useragent: SG-Scout\r
+robot-language: \r
+robot-description: Does a "server-oriented" breadth-first search in a\r
+ round-robin fashion, with multiple processes.\r
+robot-history: Run since 27 June 1994, for an internal XEROX research\r
+ project\r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id:shaggy\r
+robot-name:ShagSeeker\r
+robot-cover-url:http://www.shagseek.com\r
+robot-details-url:\r
+robot-owner-name:Joseph Reynolds\r
+robot-owner-url:http://www.shagseek.com\r
+robot-owner-email:joe.reynolds@shagseek.com\r
+robot-status:active\r
+robot-purpose:indexing\r
+robot-type:standalone\r
+robot-platform:unix\r
+robot-availability:data\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:Shagseeker\r
+robot-noindex:yes\r
+robot-host:shagseek.com\r
+robot-from:\r
+robot-useragent:Shagseeker at http://www.shagseek.com /1.0\r
+robot-language:perl5\r
+robot-description:Shagseeker is the gatherer for the Shagseek.com search \r
+ engine and goes out weekly.\r
+robot-history:none yet\r
+robot-environment:service\r
+modified-date:Mon 17 Jan 2000 10:00:00 EST\r
+modified-by:Joseph Reynolds\r
+\r
+robot-id: shaihulud\r
+robot-name: Shai'Hulud\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Dimitri Khaoustov\r
+robot-owner-url:\r
+robot-owner-email: shawdow@usa.net\r
+robot-status: active\r
+robot-purpose: mirroring\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: no\r
+robot-exclusion-useragent: \r
+robot-noindex: no\r
+robot-host: *.rdtex.ru\r
+robot-from:\r
+robot-useragent: Shai'Hulud\r
+robot-language: C\r
+robot-description: Used to build mirrors for internal use\r
+robot-history: This robot finds its roots in a research project at RDTeX \r
+ Perspective Projects Group in 1996\r
+robot-environment: research\r
+modified-date: Mon, 5 Aug 1996 14:35:08 GMT\r
+modified-by: Dimitri Khaoustov\r
+\r
+robot-id: sift\r
+robot-name: Sift\r
+robot-cover-url: http://www.worthy.com/\r
+robot-details-url: http://www.worthy.com/\r
+robot-owner-name: Bob Worthy \r
+robot-owner-url: http://www.worthy.com/~bworthy \r
+robot-owner-email: bworthy@worthy.com\r
+robot-status: development, active \r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: sift\r
+robot-noindex: yes\r
+robot-host: www.worthy.com\r
+robot-from:\r
+robot-useragent: libwww-perl-5.41\r
+robot-language: perl\r
+robot-description: Subject directed (via key phrase list) indexing.\r
+robot-history: Libwww of course, implementation using MySQL August, 1999.\r
+ Indexing Search and Rescue sites.\r
+robot-environment: research, service\r
+modified-date: Sat, 16 Oct 1999 19:40:00 GMT\r
+modified-by: Bob Worthy\r
+\r
+robot-id: simbot\r
+robot-name: Simmany Robot Ver1.0\r
+robot-cover-url: http://simmany.hnc.net/\r
+robot-details-url: http://simmany.hnc.net/irman1.html\r
+robot-owner-name: Youngsik, Lee(\ e@L?5=D\ f)\r
+robot-owner-url:\r
+robot-owner-email: ailove@hnc.co.kr\r
+robot-status: development & active\r
+robot-purpose: indexing, maintenance, statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: SimBot\r
+robot-noindex: no \r
+robot-host: sansam.hnc.net\r
+robot-from: no\r
+robot-useragent: SimBot/1.0\r
+robot-language: C\r
+robot-description: The Simmany Robot is used to build the Map(DB) for\r
+ the simmany service operated by HNC(Hangul & Computer Co., Ltd.). The\r
+ robot runs weekly, and visits sites that have a useful korean\r
+ information in a defined order.\r
+robot-history: This robot is a part of simmany service and simmini\r
+ products. The simmini is the Web products that make use of the indexing\r
+ and retrieving modules of simmany.\r
+robot-environment: service, commercial\r
+modified-date: Thu, 19 Sep 1996 07:02:26 GMT\r
+modified-by: Youngsik, Lee\r
+\r
+robot-id: site-valet\r
+robot-name: Site Valet\r
+robot-cover-url: http://valet.webthing.com/\r
+robot-details-url: http://valet.webthing.com/\r
+robot-owner-name: Nick Kew\r
+robot-owner-url:\r
+robot-owner-email: nick@webthing.com\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Site Valet\r
+robot-noindex: no\r
+robot-host: valet.webthing.com,valet.*\r
+robot-from: yes\r
+robot-useragent: Site Valet\r
+robot-language: perl\r
+robot-description: a deluxe site monitoring and analysis service\r
+robot-history: builds on cg-eye, the WDG Validator, and the Link Valet\r
+robot-environment: service\r
+modified-date: Tue, 27 June 2000\r
+modified-by: nick@webthing.com\r
+\r
+robot-id: sitegrabber\r
+robot-name: Open Text Index Robot\r
+robot-cover-url: http://index.opentext.net/main/faq.html\r
+robot-details-url: http://index.opentext.net/OTI_Robot.html\r
+robot-owner-name: John Faichney\r
+robot-owner-url:\r
+robot-owner-email: faichney@opentext.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: inquire to markk@opentext.com (Mark Kraatz)\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Open Text Site Crawler\r
+robot-noindex: no\r
+robot-host: *.opentext.com\r
+robot-from: yes\r
+robot-useragent: Open Text Site Crawler V1.0\r
+robot-language: perl/C\r
+robot-description: This robot is run by Open Text Corporation to produce the\r
+ data for the Open Text Index\r
+robot-history: Started in May/95 to replace existing Open Text robot which\r
+ was based on libwww\r
+robot-environment: commercial\r
+modified-date: Fri Jul 25 11:46:56 EDT 1997\r
+modified-by: John Faichney\r
+\r
+robot-id: sitetech\r
+robot-name: SiteTech-Rover\r
+robot-cover-url: http://www.sitetech.com/\r
+robot-details-url:\r
+robot-owner-name: Anil Peres-da-Silva\r
+robot-owner-url: http://www.sitetech.com\r
+robot-owner-email: adasilva@sitetech.com\r
+robot-status:\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: SiteTech-Rover\r
+robot-language: C++.\r
+robot-description: Originated as part of a suite of Internet Products to\r
+ organize, search & navigate Intranet sites and to validate\r
+ links in HTML documents.\r
+robot-history: This robot originally went by the name of LiberTech-Rover\r
+robot-environment:\r
+modified-date: Fri Aug 9 17:06:56 1996.\r
+modified-by: Anil Peres-da-Silva\r
+\r
+robot-id: slurp\r
+robot-name: Inktomi Slurp\r
+robot-cover-url: http://www.inktomi.com/\r
+robot-details-url: http://www.inktomi.com/slurp.html\r
+robot-owner-name: Inktomi Corporation\r
+robot-owner-url: http://www.inktomi.com/\r
+robot-owner-email: slurp@inktomi.com\r
+robot-status: active\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: slurp\r
+robot-noindex: yes\r
+robot-host: *.inktomi.com\r
+robot-from: yes\r
+robot-useragent: Slurp/2.0\r
+robot-language: C/C++\r
+robot-description: Indexing documents for the HotBot search engine\r
+ (www.hotbot.com), collecting Web statistics\r
+robot-history: Switch from Slurp/1.0 to Slurp/2.0 November 1996\r
+robot-environment: service\r
+modified-date: Fri Feb 28 13:57:43 PST 1997\r
+modified-by: slurp@inktomi.com\r
+\r
+robot-id: smartspider\r
+robot-name: Smart Spider\r
+robot-cover-url: http://www.travel-finder.com\r
+robot-details-url: http://www.engsoftware.com/robots.htm\r
+robot-owner-name: Ken Wadland\r
+robot-owner-url: http://www.engsoftware.com\r
+robot-owner-email: ken@engsoftware.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: windows95, windowsNT\r
+robot-availability: data, binary, source\r
+robot-exclusion: Yes\r
+robot-exclusion-useragent: ESI\r
+robot-noindex: Yes\r
+robot-host: 207.16.241.*\r
+robot-from: Yes\r
+robot-useragent: ESISmartSpider/2.0\r
+robot-language: C++\r
+robot-description: Classifies sites using a Knowledge Base. Robot collects \r
+ web pages which are then parsed and feed to the Knowledge Base. The\r
+ Knowledge Base classifies the sites into any of hundreds of categories\r
+ based on the vocabulary used. Currently used by: //www.travel-finder.com\r
+ (Travel and Tourist Info) and //www.golightway.com (Christian Sites).\r
+ Several options exist to control whether sites are discovered and/or\r
+ classified fully automatically, full manually or somewhere in between.\r
+robot-history: Feb '96 -- Product design begun. May '96 -- First data\r
+ results published by Travel-Finder. Oct '96 -- Generalized and announced\r
+ and a product for other sites. Jan '97 -- First data results published by\r
+ GoLightWay.\r
+robot-environment: service, commercial\r
+modified-date: Mon, 13 Jan 1997 10:41:00 EST\r
+modified-by: Ken Wadland\r
+\r
+robot-id: snooper\r
+robot-name: Snooper\r
+robot-cover-url: http://darsun.sit.qc.ca\r
+robot-details-url:\r
+robot-owner-name: Isabelle A. Melnick\r
+robot-owner-url:\r
+robot-owner-email: melnicki@sit.ca\r
+robot-status: part under development and part active\r
+robot-purpose:\r
+robot-type:\r
+robot-platform:\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: snooper\r
+robot-noindex:\r
+robot-host:\r
+robot-from:\r
+robot-useragent: Snooper/b97_01\r
+robot-language:\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date:\r
+modified-by:\r
+\r
+robot-id: solbot\r
+robot-name: Solbot\r
+robot-cover-url: http://kvasir.sol.no/\r
+robot-details-url:\r
+robot-owner-name: Frank Tore Johansen\r
+robot-owner-url:\r
+robot-owner-email: ftj@sys.sol.no\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: solbot\r
+robot-noindex: yes\r
+robot-host: robot*.sol.no\r
+robot-from:\r
+robot-useragent: Solbot/1.0 LWP/5.07\r
+robot-language: perl, c\r
+robot-description: Builds data for the Kvasir search service. Only searches\r
+ sites which ends with one of the following domains: "no", "se", "dk", "is", "fi"robot-history: This robot is the result of a 3 years old late night hack when\r
+ the Verity robot (of that time) was unable to index sites with iso8859\r
+ characters (in URL and other places), and we just _had_ to have something up and going the next day...\r
+robot-environment: service\r
+modified-date: Tue Apr 7 16:25:05 MET DST 1998\r
+modified-by: Frank Tore Johansen <ftj@sys.sol.no>\r
+\r
+robot-id: spanner\r
+robot-name: Spanner\r
+robot-cover-url: http://www.kluge.net/NES/spanner/\r
+robot-details-url: http://www.kluge.net/NES/spanner/\r
+robot-owner-name: Theo Van Dinter\r
+robot-owner-url: http://www.kluge.net/~felicity/\r
+robot-owner-email: felicity@kluge.net\r
+robot-status: development\r
+robot-purpose: indexing,maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Spanner\r
+robot-noindex: yes\r
+robot-host: *.kluge.net\r
+robot-from: yes\r
+robot-useragent: Spanner/1.0 (Linux 2.0.27 i586)\r
+robot-language: perl\r
+robot-description: Used to index/check links on an intranet.\r
+robot-history: Pet project of the author since beginning of 1996.\r
+robot-environment: hobby\r
+modified-date: Mon, 06 Jan 1997 00:00:00 GMT\r
+modified-by: felicity@kluge.net\r
+\r
+robot-id:speedy\r
+robot-name:Speedy Spider\r
+robot-cover-url:http://www.entireweb.com/\r
+robot-details-url:http://www.entireweb.com/speedy.html\r
+robot-owner-name:WorldLight.com AB\r
+robot-owner-url:http://www.worldlight.com\r
+robot-owner-email:speedy@worldlight.com\r
+robot-status:active\r
+robot-purpose:indexing\r
+robot-type:standalone\r
+robot-platform:Windows\r
+robot-availability:none\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:speedy\r
+robot-noindex:yes\r
+robot-host:router-00.sverige.net, 193.15.210.29, *.entireweb.com,\r
+ *.worldlight.com\r
+robot-from:yes\r
+robot-useragent:Speedy Spider ( http://www.entireweb.com/speedy.html )\r
+robot-language:C, C++\r
+robot-description:Speedy Spider is used to build the database\r
+ for the Entireweb.com search service operated by WorldLight.com\r
+ (part of WorldLight Network).\r
+ The robot runs constantly, and visits sites in a random order.\r
+robot-history:This robot is a part of the highly advanced search engine\r
+ Entireweb.com, that was developed in Halmstad, Sweden during 1998-2000.\r
+robot-environment:service, commercial\r
+modified-date:Mon, 17 July 2000 11:05:03 GMT\r
+modified-by:Marcus Andersson\r
+\r
+robot-id: spider_monkey\r
+robot-name: spider_monkey\r
+robot-cover-url: http://www.mobrien.com/add_site.html\r
+robot-details-url: http://www.mobrien.com/add_site.html\r
+robot-owner-name: MPRM Group Limited\r
+robot-owner-url: http://www.mobrien.com\r
+robot-owner-email: mprm@ionsys.com\r
+robot-status: robot actively in use\r
+robot-purpose: gather content for a free indexing service\r
+robot-type: FDSE robot\r
+robot-platform: unix\r
+robot-availability: bulk data gathered by robot available\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: spider_monkey\r
+robot-noindex: yes\r
+robot-host: snowball.ionsys.com\r
+robot-from: yes\r
+robot-useragent: mouse.house/7.1\r
+robot-language: perl5\r
+robot-description: Robot runs every 30 days for a full index and weekly =\r
+ on a list of accumulated visitor requests\r
+robot-history: This robot is under development and currently active\r
+robot-environment: written as an employee / guest service\r
+modified-date: Mon, 22 May 2000 12:28:52 GMT\r
+modified-by: MPRM Group Limited\r
+\r
+robot-id: spiderbot\r
+robot-name: SpiderBot\r
+robot-cover-url: http://pisuerga.inf.ubu.es/lsi/Docencia/TFC/ITIG/icruzadn/cover.htm\r
+robot-details-url: http://pisuerga.inf.ubu.es/lsi/Docencia/TFC/ITIG/icruzadn/details.htm\r
+robot-owner-name: Ignacio Cruzado Nu.o\r
+robot-owner-url: http://pisuerga.inf.ubu.es/lsi/Docencia/TFC/ITIG/icruzadn/icruzadn.htm\r
+robot-owner-email: spidrboticruzado@solaria.emp.ubu.es\r
+robot-status: active\r
+robot-purpose: indexing, mirroring\r
+robot-type: standalone, browser\r
+robot-platform: unix, windows, windows95, windowsNT\r
+robot-availability: source, binary, data\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: SpiderBot/1.0\r
+robot-noindex: yes\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: SpiderBot/1.0\r
+robot-language: C++, Tcl\r
+robot-description: Recovers Web Pages and saves them on your hard disk. Then it reindexes them.\r
+robot-history: This Robot belongs to Ignacio Cruzado Nu.o End of Studies Thesis "Recuperador p.ginas Web", to get the titulation of "Management Tecnical Informatics Engineer" in the for the Burgos University in Spain.\r
+robot-environment: research\r
+modified-date: Sun, 27 Jun 1999 09:00:00 GMT\r
+modified-by: Ignacio Cruzado Nu.o\r
+\r
+robot-id:spiderman\r
+robot-name:SpiderMan\r
+robot-cover-url:http://www.comp.nus.edu.sg/~leunghok\r
+robot-details-url:http://www.comp.nus.edu.sg/~leunghok/honproj.html\r
+robot-owner-name:Leung Hok Peng , The School Of Computing Nus , Singapore\r
+robot-owner-url:http://www.comp.nus.edu.sg/~leunghok\r
+robot-owner-email:leunghok@comp.nus.edu.sg\r
+robot-status:development & active\r
+robot-purpose:user searching using IR technique\r
+robot-type:stand alone\r
+robot-platform:Java 1.2\r
+robot-availability:binary&source\r
+robot-exclusion:no\r
+robot-exclusion-useragent:nil\r
+robot-noindex:no\r
+robot-host:NA\r
+robot-from:NA\r
+robot-useragent:SpiderMan 1.0\r
+robot-language:java\r
+robot-description:It is used for any user to search the web given a query string\r
+robot-history:Originated from The Center for Natural Product Research and The\r
+ School of computing National University Of Singapore\r
+robot-environment:research\r
+modified-date:08/08/1999\r
+modified-by:Leung Hok Peng and Dr Hsu Wynne\r
+\r
+robot-id: spry\r
+robot-name: Spry Wizard Robot\r
+robot-cover-url: http://www.spry.com/wizard/index.html\r
+robot-details-url:\r
+robot-owner-name: spry\r
+robot-owner-url: ttp://www.spry.com/index.html\r
+robot-owner-email: info@spry.com\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: \r
+robot-host: wizard.spry.com or tiger.spry.com\r
+robot-from: no\r
+robot-useragent: no\r
+robot-language: \r
+robot-description: Its purpose is to generate a Resource Discovery database\r
+ Spry is refusing to give any comments about this\r
+ robot\r
+robot-history: \r
+robot-environment:\r
+modified-date: Tue Jul 11 09:29:45 GMT 1995\r
+modified-by:\r
+\r
+robot-id: ssearcher\r
+robot-name: Site Searcher\r
+robot-cover-url: www.satacoy.com\r
+robot-details-url: www.satacoy.com\r
+robot-owner-name: Zackware\r
+robot-owner-url: www.satacoy.com\r
+robot-owner-email: zackware@hotmail.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: winows95, windows98, windowsNT\r
+robot-availability: binary\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: ssearcher100\r
+robot-language: C++\r
+robot-description: Site Searcher scans web sites for specific file types.\r
+ (JPG, MP3, MPG, etc)\r
+robot-history: Released 4/4/1999\r
+robot-environment: hobby\r
+modified-date: 04/26/1999\r
+\r
+robot-id: suke\r
+robot-name: Suke\r
+robot-cover-url: http://www.kensaku.org/\r
+robot-details-url: http://www.kensaku.org/\r
+robot-owner-name: Yosuke Kuroda\r
+robot-owner-url: http://www.kensaku.org/yk/\r
+robot-owner-email: robot@kensaku.org\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: FreeBSD3.*\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: suke\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: suke/*.*\r
+robot-language: c\r
+robot-description: This robot visits mainly sites in japan.\r
+robot-history: since 1999\r
+robot-environment: service\r
+\r
+robot-id: sven\r
+robot-name: Sven\r
+robot-cover-url: \r
+robot-details-url: http://marty.weathercity.com/sven/\r
+robot-owner-name: Marty Anstey\r
+robot-owner-url: http://marty.weathercity.com/\r
+robot-owner-email: rhondle@home.com\r
+robot-status: Active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Windows\r
+robot-availability: none\r
+robot-exclusion: no\r
+robot-exclusion-useragent: \r
+robot-noindex: no\r
+robot-host: 24.113.12.29\r
+robot-from: no\r
+robot-useragent:\r
+robot-language: VB5\r
+robot-description: Used to gather sites for netbreach.com. Runs constantly.\r
+robot-history: Developed as an experiment in web indexing.\r
+robot-environment: hobby, service\r
+modified-date: Tue, 3 Mar 1999 08:15:00 PST\r
+modified-by: Marty Anstey\r
+\r
+robot-id: tach_bw\r
+robot-name: TACH Black Widow\r
+robot-cover-url: http://theautochannel.com/~mjenn/bw.html\r
+robot-details-url: http://theautochannel.com/~mjenn/bw-syntax.html\r
+robot-owner-name: Michael Jennings\r
+robot-owner-url: http://www.spd.louisville.edu/~mejenn01/\r
+robot-owner-email: mjenn@theautochannel.com\r
+robot-status: development\r
+robot-purpose: maintenance: link validation\r
+robot-type: standalone\r
+robot-platform: UNIX, Linux\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: tach_bw\r
+robot-noindex: no\r
+robot-host: *.theautochannel.com\r
+robot-from: yes\r
+robot-useragent: Mozilla/3.0 (Black Widow v1.1.0; Linux 2.0.27; Dec 31 1997 12:25:00\r
+robot-language: C/C++\r
+robot-description: Exhaustively recurses a single site to check for broken links\r
+robot-history: Corporate application begun in 1996 for The Auto Channel\r
+robot-environment: commercial\r
+modified-date: Thu, Jan 23 1997 23:09:00 GMT\r
+modified-by: Michael Jennings\r
+\r
+robot-id:tarantula\r
+robot-name: Tarantula\r
+robot-cover-url: http://www.nathan.de/nathan/software.html#TARANTULA\r
+robot-details-url: http://www.nathan.de/\r
+robot-owner-name: Markus Hoevener\r
+robot-owner-url:\r
+robot-owner-email: Markus.Hoevener@evision.de\r
+robot-status: development\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: yes\r
+robot-noindex: yes\r
+robot-host: yes\r
+robot-from: no\r
+robot-useragent: Tarantula/1.0\r
+robot-language: C\r
+robot-description: Tarantual gathers information for german search engine Nathanrobot-history: Started February 1997\r
+robot-environment: service\r
+modified-date: Mon, 29 Dec 1997 15:30:00 GMT\r
+modified-by: Markus Hoevener\r
+\r
+robot-id: tarspider\r
+robot-name: tarspider\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Olaf Schreck\r
+robot-owner-url: http://www.chemie.fu-berlin.de/user/chakl/ChaklHome.html\r
+robot-owner-email: chakl@fu-berlin.de\r
+robot-status: \r
+robot-purpose: mirroring\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: chakl@fu-berlin.de\r
+robot-useragent: tarspider\r
+robot-language: \r
+robot-description: \r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: tcl\r
+robot-name: Tcl W3 Robot\r
+robot-cover-url: http://hplyot.obspm.fr/~dl/robo.html\r
+robot-details-url:\r
+robot-owner-name: Laurent Demailly\r
+robot-owner-url: http://hplyot.obspm.fr/~dl/\r
+robot-owner-email: dl@hplyot.obspm.fr\r
+robot-status: \r
+robot-purpose: maintenance, statistics\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: hplyot.obspm.fr\r
+robot-from: yes\r
+robot-useragent: dlw3robot/x.y (in TclX by http://hplyot.obspm.fr/~dl/)\r
+robot-language: tcl\r
+robot-description: Its purpose is to validate links, and generate\r
+ statistics.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Tue May 23 17:51:39 1995\r
+modified-by:\r
+\r
+robot-id: techbot\r
+robot-name: TechBOT\r
+robot-cover-url: http://www.techaid.net/\r
+robot-details-url: http://www.echaid.net/TechBOT/\r
+robot-owner-name: TechAID Internet Services\r
+robot-owner-url: http://www.techaid.net/\r
+robot-owner-email: techbot@techaid.net\r
+robot-status: active\r
+robot-purpose:statistics, maintenance\r
+robot-type: standalone\r
+robot-platform: Unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: TechBOT\r
+robot-noindex: yes\r
+robot-host: techaid.net\r
+robot-from: yes\r
+robot-useragent: TechBOT\r
+robot-language: perl5\r
+robot-description: TechBOT is constantly upgraded. Currently he is used for\r
+ Link Validation, Load Time, HTML Validation and much much more.\r
+robot-history: TechBOT started his life as a Page Change Detection robot,\r
+ but has taken on many new and exciting roles.\r
+robot-environment: service\r
+modified-date: Sat, 18 Dec 1998 14:26:00 EST\r
+modified-by: techbot@techaid.net\r
+\r
+robot-id: templeton\r
+robot-name: Templeton\r
+robot-cover-url: http://www.bmtmicro.com/catalog/tton/\r
+robot-details-url: http://www.bmtmicro.com/catalog/tton/\r
+robot-owner-name: Neal Krawetz\r
+robot-owner-url: http://www.cs.tamu.edu/people/nealk/\r
+robot-owner-email: nealk@net66.com\r
+robot-status: active\r
+robot-purpose: mirroring, mapping, automating web applications\r
+robot-type: standalone\r
+robot-platform: OS/2, Linux, SunOS, Solaris\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: templeton\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: Templeton/{version} for {platform}\r
+robot-language: C\r
+robot-description: Templeton is a very configurable robots for mirroring, mapping, and automating applications on retrieved documents.\r
+robot-history: This robot was originally created as a test-of-concept.\r
+robot-environment: service, commercial, research, hobby\r
+modified-date: Sun, 6 Apr 1997 10:00:00 GMT\r
+modified-by: Neal Krawetz\r
+\r
+robot-id: titin\r
+robot-name: TitIn\r
+robot-cover-url: http://www.foi.hr/~dpavlin/titin/\r
+robot-details-url: http://www.foi.hr/~dpavlin/titin/tehnical.htm\r
+robot-owner-name: Dobrica Pavlinusic\r
+robot-owner-url: http://www.foi.hr/~dpavlin/\r
+robot-owner-email: dpavlin@foi.hr\r
+robot-status: development\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: data, source on request\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: titin\r
+robot-noindex: no\r
+robot-host: barok.foi.hr\r
+robot-from: no\r
+robot-useragent: TitIn/0.2\r
+robot-language: perl5, c\r
+robot-description:\r
+ The TitIn is used to index all titles of Web server in\r
+ .hr domain.\r
+robot-history:\r
+ It was done as result of desperate need for central index of\r
+ Croatian web servers in December 1996.\r
+robot-environment: research\r
+modified-date: Thu, 12 Dec 1996 16:06:42 MET\r
+modified-by: Dobrica Pavlinusic\r
+\r
+robot-id: titan\r
+robot-name: TITAN\r
+robot-cover-url: http://isserv.tas.ntt.jp/chisho/titan-e.html\r
+robot-details-url: http://isserv.tas.ntt.jp/chisho/titan-help/eng/titan-help-e.html\r
+robot-owner-name: Yoshihiko HAYASHI\r
+robot-owner-url: \r
+robot-owner-email: hayashi@nttnly.isl.ntt.jp\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: SunOS 4.1.4\r
+robot-availability: no\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: nlptitan.isl.ntt.jp\r
+robot-from: yes\r
+robot-useragent: TITAN/0.1\r
+robot-language: perl 4\r
+robot-description: Its purpose is to generate a Resource Discovery\r
+ database, and copy document trees. Our primary goal is to develop\r
+ an advanced method for indexing the WWW documents. Uses libwww-perl\r
+robot-history: \r
+robot-environment:\r
+modified-date: Mon Jun 24 17:20:44 PDT 1996\r
+modified-by: Yoshihiko HAYASHI\r
+\r
+robot-id: tkwww\r
+robot-name: The TkWWW Robot\r
+robot-cover-url: http://fang.cs.sunyit.edu/Robots/tkwww.html\r
+robot-details-url:\r
+robot-owner-name: Scott Spetka\r
+robot-owner-url: http://fang.cs.sunyit.edu/scott/scott.html\r
+robot-owner-email: scott@cs.sunyit.edu\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: It is designed to search Web neighborhoods to find pages\r
+ that may be logically related. The Robot returns a list of\r
+ links that looks like a hot list. The search can be by key\r
+ word or all links at a distance of one or two hops may be\r
+ returned. The TkWWW Robot is described in a paper presented\r
+ at the WWW94 Conference in Chicago.\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: tlspider\r
+robot-name:TLSpider\r
+robot-cover-url: n/a\r
+robot-details-url: n/a\r
+robot-owner-name: topiclink.com\r
+robot-owner-url: topiclink.com\r
+robot-owner-email: tlspider@outtel.com\r
+robot-status: not activated\r
+robot-purpose: to get web sites and add them to the topiclink future directory\r
+robot-type:development: robot under development\r
+robot-platform:linux\r
+robot-availability:none\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:topiclink\r
+robot-noindex:no\r
+robot-host: tlspider.topiclink.com (not avalible yet)\r
+robot-from:no\r
+robot-useragent:TLSpider/1.1\r
+robot-language:perl5\r
+robot-description:This robot runs 2 days a week getting information for\r
+ TopicLink.com\r
+robot-history:This robot was created to server for the internet search engine\r
+ TopicLink.com\r
+robot-environment:service\r
+modified-date:September,10,1999 17:28 GMT\r
+modified-by: TopicLink Spider Team\r
+\r
+robot-id: ucsd\r
+robot-name: UCSD Crawl\r
+robot-cover-url: http://www.mib.org/~ucsdcrawl\r
+robot-details-url:\r
+robot-owner-name: Adam Tilghman\r
+robot-owner-url: http://www.mib.org/~atilghma\r
+robot-owner-email: atilghma@mib.org\r
+robot-status:\r
+robot-purpose: indexing, statistics\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: nuthaus.mib.org scilib.ucsd.edu\r
+robot-from: yes\r
+robot-useragent: UCSD-Crawler\r
+robot-language: Perl 4\r
+robot-description: Should hit ONLY within UC San Diego - trying to count\r
+ servers here.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sat Jan 27 09:21:40 1996.\r
+modified-by:\r
+\r
+robot-id: udmsearch\r
+robot-name: UdmSearch\r
+robot-details-url: http://mysearch.udm.net/\r
+robot-cover-url: http://mysearch.udm.net/\r
+robot-owner-name: Alexander Barkov\r
+robot-owner-url: http://mysearch.udm.net/\r
+robot-owner-email: bar@izhcom.ru\r
+robot-status: active\r
+robot-purpose: indexing, validation\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source, binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: UdmSearch\r
+robot-noindex: yes\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: UdmSearch/2.1.1\r
+robot-language: c\r
+robot-description: UdmSearch is a free web search engine software for\r
+ intranet/small domain internet servers\r
+robot-history: Developed since 1998, origin purpose is a search engine\r
+ over republic of Udmurtia http://search.udm.net\r
+robot-environment: hobby\r
+modified-date: Mon, 6 Sep 1999 10:28:52 GMT\r
+\r
+robot-id: urlck\r
+robot-name: URL Check\r
+robot-cover-url: http://www.cutternet.com/products/webcheck.html\r
+robot-details-url: http://www.cutternet.com/products/urlck.html\r
+robot-owner-name: Dave Finnegan\r
+robot-owner-url: http://www.cutternet.com\r
+robot-owner-email: dave@cutternet.com\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: urlck\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: urlck/1.2.3\r
+robot-language: c\r
+robot-description: The robot is used to manage, maintain, and modify\r
+ web sites. It builds a database detailing the\r
+ site, builds HTML reports describing the site, and\r
+ can be used to up-load pages to the site or to\r
+ modify existing pages and URLs within the site. It\r
+ can also be used to mirror whole or partial sites.\r
+ It supports HTTP, File, FTP, and Mailto schemes.\r
+robot-history: Originally designed to validate URLs.\r
+robot-environment: commercial\r
+modified-date: July 9, 1997\r
+modified-by: Dave Finnegan\r
+\r
+robot-id: us\r
+robot-name: URL Spider Pro\r
+robot-cover-url: http://www.innerprise.net\r
+robot-details-url: http://www.innerprise.net/us.htm\r
+robot-owner-name: Innerprise\r
+robot-owner-url: http://www.innerprise.net\r
+robot-owner-email: greg@innerprise.net\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Windows9x/NT\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: *\r
+robot-noindex: yes\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: URL Spider Pro\r
+robot-language: delphi\r
+robot-description: Used for building a database of web pages.\r
+robot-history: Project started July 1998.\r
+robot-environment: commercial\r
+modified-date: Mon, 12 Jul 1999 17:50:30 GMT\r
+modified-by: Innerprise\r
+\r
+robot-id: valkyrie\r
+robot-name: Valkyrie\r
+robot-cover-url: http://kichijiro.c.u-tokyo.ac.jp/odin/\r
+robot-details-url: http://kichijiro.c.u-tokyo.ac.jp/odin/robot.html\r
+robot-owner-name: Masanori Harada\r
+robot-owner-url: http://www.graco.c.u-tokyo.ac.jp/~harada/\r
+robot-owner-email: harada@graco.c.u-tokyo.ac.jp\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Valkyrie libwww-perl\r
+robot-noindex: no\r
+robot-host: *.c.u-tokyo.ac.jp\r
+robot-from: yes\r
+robot-useragent: Valkyrie/1.0 libwww-perl/0.40\r
+robot-language: perl4\r
+robot-description: used to collect resources from Japanese Web sites for ODIN search engine.\r
+robot-history: This robot has been used since Oct. 1995 for author's research.\r
+robot-environment: service research\r
+modified-date: Thu Mar 20 19:09:56 JST 1997\r
+modified-by: harada@graco.c.u-tokyo.ac.jp\r
+\r
+robot-id: victoria\r
+robot-name: Victoria\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Adrian Howard\r
+robot-owner-url:\r
+robot-owner-email: adrianh@oneworld.co.uk\r
+robot-status: development\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Victoria\r
+robot-noindex: yes\r
+robot-host:\r
+robot-from:\r
+robot-useragent: Victoria/1.0\r
+robot-language: perl,c\r
+robot-description: Victoria is part of a groupware produced\r
+ by Victoria Real Ltd. (voice: +44 [0]1273 774469,\r
+ fax: +44 [0]1273 779960 email: victoria@pavilion.co.uk).\r
+ Victoria is used to monitor changes in W3 documents,\r
+ both intranet and internet based.\r
+ Contact Victoria Real for more information.\r
+robot-history:\r
+robot-environment: commercial\r
+modified-date: Fri, 22 Nov 1996 16:45 GMT\r
+modified-by: victoria@pavilion.co.uk\r
+\r
+robot-id: visionsearch\r
+robot-name: vision-search\r
+robot-cover-url: http://www.ius.cs.cmu.edu/cgi-bin/vision-search\r
+robot-details-url:\r
+robot-owner-name: Henry A. Rowley\r
+robot-owner-url: http://www.cs.cmu.edu/~har\r
+robot-owner-email: har@cs.cmu.edu\r
+robot-status:\r
+robot-purpose: indexing.\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: dylan.ius.cs.cmu.edu\r
+robot-from: no\r
+robot-useragent: vision-search/3.0'\r
+robot-language: Perl 5\r
+robot-description: Intended to be an index of computer vision pages, containing\r
+ all pages within <em>n</em> links (for some small\r
+ <em>n</em>) of the Vision Home Page\r
+robot-history:\r
+robot-environment:\r
+modified-date: Fri Mar 8 16:03:04 1996\r
+modified-by:\r
+\r
+robot-id: voyager\r
+robot-name: Voyager\r
+robot-cover-url: http://www.lisa.co.jp/voyager/\r
+robot-details-url:\r
+robot-owner-name: Voyager Staff\r
+robot-owner-url: http://www.lisa.co.jp/voyager/\r
+robot-owner-email: voyager@lisa.co.jp\r
+robot-status: development\r
+robot-purpose: indexing, maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Voyager \r
+robot-noindex: no\r
+robot-host: *.lisa.co.jp\r
+robot-from: yes\r
+robot-useragent: Voyager/0.0\r
+robot-language: perl5 \r
+robot-description: This robot is used to build the database for the\r
+ Lisa Search service. The robot manually launch \r
+ and visits sites in a random order.\r
+robot-history:\r
+robot-environment: service\r
+modified-date: Mon, 30 Nov 1998 08:00:00 GMT\r
+modified-by: Hideyuki Ezaki\r
+\r
+robot-id: vwbot\r
+robot-name: VWbot\r
+robot-cover-url: http://vancouver-webpages.com/VWbot/\r
+robot-details-url: http://vancouver-webpages.com/VWbot/aboutK.shtml\r
+robot-owner-name: Andrew Daviel\r
+robot-owner-url: http://vancouver-webpages.com/~admin/\r
+robot-owner-email: andrew@vancouver-webpages.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: VWbot_K\r
+robot-noindex: yes\r
+robot-host: vancouver-webpages.com\r
+robot-from: yes\r
+robot-useragent: VWbot_K/4.2\r
+robot-language: perl4\r
+robot-description: Used to index BC sites for the searchBC database. Runs daily.\r
+robot-history: Originally written fall 1995. Actively maintained.\r
+robot-environment: service commercial research\r
+modified-date: Tue, 4 Mar 1997 20:00:00 GMT\r
+modified-by: Andrew Daviel\r
+\r
+robot-id: w3index\r
+robot-name: The NWI Robot\r
+robot-cover-url: http://www.ub2.lu.se/NNC/projects/NWI/the_nwi_robot.html\r
+robot-owner-name: Sigfrid Lundberg, Lund university, Sweden\r
+robot-owner-url: http://nwi.ub2.lu.se/~siglun\r
+robot-owner-email: siglun@munin.ub2.lu.se\r
+robot-status: active\r
+robot-purpose: discovery,statistics\r
+robot-type: standalone\r
+robot-platform: UNIX\r
+robot-availability: none (at the moment)\r
+robot-exclusion: yes\r
+robot-noindex: No\r
+robot-host: nwi.ub2.lu.se, mars.dtv.dk and a few others\r
+robot-from: yes\r
+robot-useragent: w3index\r
+robot-language: perl5\r
+robot-description: A resource discovery robot, used primarily for\r
+ the indexing of the Scandinavian Web\r
+robot-history: It is about a year or so old.\r
+ Written by Anders Ard\96, Mattias Borrell, \r
+ HÂkan Ard\96 and myself.\r
+robot-environment: service,research\r
+modified-date: Wed Jun 26 13:58:04 MET DST 1996\r
+modified-by: Sigfrid Lundberg\r
+\r
+robot-id: w3m2\r
+robot-name: W3M2\r
+robot-cover-url: http://tronche.com/W3M2\r
+robot-details-url:\r
+robot-owner-name: Christophe Tronche\r
+robot-owner-url: http://tronche.com/\r
+robot-owner-email: tronche@lri.fr\r
+robot-status: \r
+robot-purpose: indexing, maintenance, statistics\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: W3M2/x.xxx\r
+robot-language: Perl 4, Perl 5, and C++\r
+robot-description: to generate a Resource Discovery database, validate links,\r
+ validate HTML, and generate statistics\r
+robot-history: \r
+robot-environment:\r
+modified-date: Fri May 5 17:48:48 1995\r
+modified-by:\r
+\r
+robot-id: wanderer\r
+robot-name: the World Wide Web Wanderer\r
+robot-cover-url: http://www.mit.edu/people/mkgray/net/\r
+robot-details-url:\r
+robot-owner-name: Matthew Gray\r
+robot-owner-url: http://www.mit.edu:8001/people/mkgray/mkgray.html\r
+robot-owner-email: mkgray@mit.edu\r
+robot-status: active\r
+robot-purpose: statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: data\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *.mit.edu\r
+robot-from: \r
+robot-useragent: WWWWanderer v3.0\r
+robot-language: perl4\r
+robot-description: Run initially in June 1993, its aim is to measure\r
+ the growth in the web.\r
+robot-history: \r
+robot-environment: research\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id:webbandit\r
+robot-name:WebBandit Web Spider\r
+robot-cover-url:http://pw2.netcom.com/~wooger/\r
+robot-details-url:http://pw2.netcom.com/~wooger/\r
+robot-owner-name:Jerry Walsh\r
+robot-owner-url:http://pw2.netcom.com/~wooger/\r
+robot-owner-email:wooger@ix.netcom.com\r
+robot-status:active\r
+robot-purpose:Resource Gathering / Server Benchmarking\r
+robot-type:standalone application\r
+robot-platform:Intel - windows95\r
+robot-availability:source, binary\r
+robot-exclusion:no\r
+robot-exclusion-useragent:WebBandit/1.0\r
+robot-noindex:no\r
+robot-host:ix.netcom.com\r
+robot-from:no\r
+robot-useragent:WebBandit/1.0\r
+robot-language:C++\r
+robot-description:multithreaded, hyperlink-following,\r
+ resource finding webspider \r
+robot-history:Inspired by reading of\r
+ Internet Programming book by Jamsa/Cope \r
+robot-environment:commercial \r
+modified-date:11/21/96\r
+modified-by:Jerry Walsh\r
+\r
+robot-id: webcatcher\r
+robot-name: WebCatcher\r
+robot-cover-url: http://oscar.lang.nagoya-u.ac.jp\r
+robot-details-url:\r
+robot-owner-name: Reiji SUZUKI\r
+robot-owner-url: http://oscar.lang.nagoya-u.ac.jp/~reiji/index.html\r
+robot-owner-email: reiji@infonia.ne.jp\r
+robot-owner-name2: Masatoshi SUGIURA\r
+robot-owner-url2: http://oscar.lang.nagoya-u.ac.jp/~sugiura/index.html\r
+robot-owner-email2: sugiura@lang.nagoya-u.ac.jp\r
+robot-status: development\r
+robot-purpose: indexing \r
+robot-type: standalone \r
+robot-platform: unix, windows, mac\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: webcatcher\r
+robot-noindex: no\r
+robot-host: oscar.lang.nagoya-u.ac.jp\r
+robot-from: no\r
+robot-useragent: WebCatcher/1.0\r
+robot-language: perl5\r
+robot-description: WebCatcher gathers web pages\r
+ that Japanese collage students want to visit.\r
+robot-history: This robot finds its roots in a research project \r
+ at Nagoya University in 1998.\r
+robot-environment: research\r
+modified-date: Fri, 16 Oct 1998 17:28:52 JST\r
+modified-by: "Reiji SUZUKI" <reiji@infonia.ne.jp>\r
+\r
+robot-id: webcopy\r
+robot-name: WebCopy\r
+robot-cover-url: http://www.inf.utfsm.cl/~vparada/webcopy.html\r
+robot-details-url:\r
+robot-owner-name: Victor Parada\r
+robot-owner-url: http://www.inf.utfsm.cl/~vparada/\r
+robot-owner-email: vparada@inf.utfsm.cl\r
+robot-status: \r
+robot-purpose: mirroring\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: WebCopy/(version)\r
+robot-language: perl 4 or perl 5\r
+robot-description: Its purpose is to perform mirroring. WebCopy can retrieve\r
+ files recursively using HTTP protocol.It can be used as a\r
+ delayed browser or as a mirroring tool. It cannot jump from\r
+ one site to another.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Sun Jul 2 15:27:04 1995\r
+modified-by:\r
+\r
+robot-id: webfetcher\r
+robot-name: webfetcher\r
+robot-cover-url: http://www.ontv.com/\r
+robot-details-url:\r
+robot-owner-name:\r
+robot-owner-url: http://www.ontv.com/\r
+robot-owner-email: webfetch@ontv.com\r
+robot-status:\r
+robot-purpose: mirroring\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: WebFetcher/0.8, \r
+robot-language: C++\r
+robot-description: don't wait! OnTV's WebFetcher mirrors whole sites down to\r
+ your hard disk on a TV-like schedule. Catch w3\r
+ documentation. Catch discovery.com without waiting! A fully\r
+ operational web robot for NT/95 today, most UNIX soon, MAC\r
+ tomorrow.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Sat Jan 27 10:31:43 1996.\r
+modified-by:\r
+\r
+robot-id: webfoot\r
+robot-name: The Webfoot Robot\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Lee McLoughlin\r
+robot-owner-url: http://web.doc.ic.ac.uk/f?/lmjm\r
+robot-owner-email: L.McLoughlin@doc.ic.ac.uk\r
+robot-status: \r
+robot-purpose: \r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: \r
+robot-host: phoenix.doc.ic.ac.uk\r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: \r
+robot-history: First spotted in Mid February 1994\r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: weblayers\r
+robot-name: weblayers\r
+robot-cover-url: http://www.univ-paris8.fr/~loic/weblayers/\r
+robot-details-url:\r
+robot-owner-name: Loic Dachary\r
+robot-owner-url: http://www.univ-paris8.fr/~loic/\r
+robot-owner-email: loic@afp.com\r
+robot-status: \r
+robot-purpose: maintainance\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: \r
+robot-useragent: weblayers/0.0\r
+robot-language: perl 5\r
+robot-description: Its purpose is to validate, cache and maintain links. It is\r
+ designed to maintain the cache generated by the emacs emacs\r
+ w3 mode (N*tscape replacement) and to support annotated\r
+ documents (keep them in sync with the original document via\r
+ diff/patch).\r
+robot-history: \r
+robot-environment:\r
+modified-date: Fri Jun 23 16:30:42 FRE 1995\r
+modified-by:\r
+\r
+robot-id: weblinker\r
+robot-name: WebLinker\r
+robot-cover-url: http://www.cern.ch/WebLinker/\r
+robot-details-url:\r
+robot-owner-name: James Casey\r
+robot-owner-url: http://www.maths.tcd.ie/hyplan/jcasey/jcasey.html\r
+robot-owner-email: jcasey@maths.tcd.ie\r
+robot-status: \r
+robot-purpose: maintenance\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: \r
+robot-host: \r
+robot-from: \r
+robot-useragent: WebLinker/0.0 libwww-perl/0.1\r
+robot-language: \r
+robot-description: it traverses a section of web, doing URN->URL conversion.\r
+ It will be used as a post-processing tool on documents created\r
+ by automatic converters such as LaTeX2HTML or WebMaker. At\r
+ the moment it works at full speed, but is restricted to\r
+ localsites. External GETs will be added, but these will be\r
+ running slowly. WebLinker is meant to be run locally, so if\r
+ you see it elsewhere let the author know!\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: webmirror\r
+robot-name: WebMirror\r
+robot-cover-url: http://www.winsite.com/pc/win95/netutil/wbmiror1.zip\r
+robot-details-url:\r
+robot-owner-name: Sui Fung Chan\r
+robot-owner-url: http://www.geocities.com/NapaVally/1208\r
+robot-owner-email: sfchan@mailhost.net\r
+robot-status:\r
+robot-purpose: mirroring\r
+robot-type: standalone\r
+robot-platform: Windows95\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: no\r
+robot-useragent: no\r
+robot-language: C++\r
+robot-description: It download web pages to hard drive for off-line\r
+ browsing.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Mon Apr 29 08:52:25 1996.\r
+modified-by:\r
+\r
+robot-id: webmoose\r
+robot-name: The Web Moose\r
+robot-cover-url: \r
+robot-details-url: http://www.nwlink.com/~mikeblas/webmoose/\r
+robot-owner-name: Mike Blaszczak\r
+robot-owner-url: http://www.nwlink.com/~mikeblas/\r
+robot-owner-email: mikeblas@nwlink.com\r
+robot-status: development\r
+robot-purpose: statistics, maintenance\r
+robot-type: standalone\r
+robot-platform: Windows NT\r
+robot-availability: data\r
+robot-exclusion: no\r
+robot-exclusion-useragent: WebMoose\r
+robot-noindex: no\r
+robot-host: msn.com\r
+robot-from: no\r
+robot-useragent: WebMoose/0.0.0000\r
+robot-language: C++\r
+robot-description: This robot collects statistics and verifies links.\r
+ It \r
+ builds an graph of its visit path.\r
+robot-history: This robot is under development.\r
+ It will support ROBOTS.TXT soon.\r
+robot-environment: hobby\r
+modified-date: Fri, 30 Aug 1996 00:00:00 GMT\r
+modified-by: Mike Blaszczak\r
+\r
+robot-id:webquest\r
+robot-name:WebQuest\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name:TaeYoung Choi\r
+robot-owner-url:http://www.cosmocyber.co.kr:8080/~cty/index.html\r
+robot-owner-email:cty@cosmonet.co.kr\r
+robot-status:development\r
+robot-purpose:indexing\r
+robot-type:standalone\r
+robot-platform:unix\r
+robot-availability:none\r
+robot-exclusion:yes\r
+robot-exclusion-useragent:webquest\r
+robot-noindex:no\r
+robot-host:210.121.146.2, 210.113.104.1, 210.113.104.2\r
+robot-from:yes\r
+robot-useragent:WebQuest/1.0\r
+robot-language:perl5\r
+robot-description:WebQuest will be used to build the databases for various web\r
+ search service sites which will be in service by early 1998. Until the end of\r
+ Jan. 1998, WebQuest will run from time to time. Since then, it will run\r
+ daily(for few hours and very slowly).\r
+robot-history:The developent of WebQuest was motivated by the need for a\r
+ customized robot in various projects of COSMO Information & Communication Co.,\r
+ Ltd. in Korea.\r
+robot-environment:service \r
+modified-date:Tue, 30 Dec 1997 09:27:20 GMT\r
+modified-by:TaeYoung Choi\r
+\r
+robot-id: webreader\r
+robot-name: Digimarc MarcSpider\r
+robot-cover-url: http://www.digimarc.com/prod_fam.html\r
+robot-details-url: http://www.digimarc.com/prod_fam.html\r
+robot-owner-name: Digimarc Corporation\r
+robot-owner-url: http://www.digimarc.com\r
+robot-owner-email: wmreader@digimarc.com\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: windowsNT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: 206.102.3.*\r
+robot-from: yes\r
+robot-useragent: Digimarc WebReader/1.2\r
+robot-language: c++\r
+robot-description: Examines image files for watermarks. \r
+ In order to not waste internet bandwidth with yet\r
+ another crawler, we have contracted with one of the major crawlers/seach\r
+ engines to provide us with a list of specific URLs of interest to us. If an\r
+ URL is to an image, we may read the image, but we do not crawl to any other\r
+ URLs. If an URL is to a page of interest (ususally due to CGI), then we\r
+ access the page to get the image URLs from it, but we do not crawl to any\r
+ other pages.\r
+robot-history: First operation in August 1997.\r
+robot-environment: service\r
+modified-date: Mon, 20 Oct 1997 16:44:29 GMT\r
+modified-by: Brian MacIntosh\r
+\r
+robot-id: webreaper\r
+robot-name: WebReaper\r
+robot-cover-url: http://www.otway.com/webreaper\r
+robot-details-url:\r
+robot-owner-name: Mark Otway\r
+robot-owner-url: http://www.otway.com\r
+robot-owner-email: webreaper@otway.com\r
+robot-status: active\r
+robot-purpose: indexing/offline browsing\r
+robot-type: standalone\r
+robot-platform: windows95, windowsNT\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: webreaper\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: no\r
+robot-useragent: WebReaper [webreaper@otway.com]\r
+robot-language: c++\r
+robot-description: Freeware app which downloads and saves sites locally for\r
+ offline browsing.\r
+robot-history: Written for personal use, and then distributed to the public\r
+ as freeware.\r
+robot-environment: hobby\r
+modified-date: Thu, 25 Mar 1999 15:00:00 GMT\r
+modified-by: Mark Otway\r
+\r
+robot-id: webs\r
+robot-name: webs\r
+robot-cover-url: http://webdew.rnet.or.jp/\r
+robot-details-url: http://webdew.rnet.or.jp/service/shank/NAVI/SEARCH/info2.html#robot\r
+robot-owner-name: Recruit Co.Ltd,\r
+robot-owner-url: \r
+robot-owner-email: dew@wwwadmin.rnet.or.jp\r
+robot-status: active\r
+robot-purpose: statistics\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: webs\r
+robot-noindex: no\r
+robot-host: lemon.recruit.co.jp\r
+robot-from: yes\r
+robot-useragent: webs@recruit.co.jp\r
+robot-language: perl5\r
+robot-description: The webs robot is used to gather WWW servers'\r
+ top pages last modified date data. Collected\r
+ statistics reflects the priority of WWW server\r
+ data collection for webdew indexing service.\r
+ Indexing in webdew is done by manually.\r
+robot-history:\r
+robot-environment: service\r
+modified-date: Fri, 6 Sep 1996 10:00:00 GMT\r
+modified-by:\r
+\r
+robot-id: websnarf\r
+robot-name: Websnarf\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Charlie Stross\r
+robot-owner-url: \r
+robot-owner-email: charles@fma.com\r
+robot-status: retired\r
+robot-purpose: \r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: \r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: webspider\r
+robot-name: WebSpider\r
+robot-details-url: http://www.csi.uottawa.ca/~u610468\r
+robot-cover-url:\r
+robot-owner-name: Nicolas Fraiji\r
+robot-owner-email: u610468@csi.uottawa.ca\r
+robot-status: active, under further enhancement.\r
+robot-purpose: maintenance, link diagnostics\r
+robot-type: standalone\r
+robot-exclusion: yes\r
+robot-noindex: no\r
+robot-exclusion-useragent: webspider\r
+robot-host: several\r
+robot-from: Yes\r
+robot-language: Perl4\r
+robot-history: developped as a course project at the University of\r
+ Ottawa, Canada in 1996.\r
+robot-environment: Educational use and Research\r
+\r
+robot-id: webvac\r
+robot-name: WebVac\r
+robot-cover-url: http://www.federated.com/~tim/webvac.html\r
+robot-details-url:\r
+robot-owner-name: Tim Jensen\r
+robot-owner-url: http://www.federated.com/~tim\r
+robot-owner-email: tim@federated.com\r
+robot-status:\r
+robot-purpose: mirroring\r
+robot-type: standalone\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: no\r
+robot-useragent: webvac/1.0\r
+robot-language: C++\r
+robot-description:\r
+robot-history:\r
+robot-environment:\r
+modified-date: Mon May 13 03:19:17 1996.\r
+modified-by:\r
+\r
+robot-id: webwalk\r
+robot-name: webwalk\r
+robot-cover-url: \r
+robot-details-url:\r
+robot-owner-name: Rich Testardi\r
+robot-owner-url: \r
+robot-owner-email: \r
+robot-status: retired\r
+robot-purpose: indexing, maintentance, mirroring, statistics\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: yes\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: yes\r
+robot-useragent: webwalk\r
+robot-language: c\r
+robot-description: Its purpose is to generate a Resource Discovery database,\r
+ validate links, validate HTML, perform mirroring, copy\r
+ document trees, and generate statistics. Webwalk is easily\r
+ extensible to perform virtually any maintenance function\r
+ which involves web traversal, in a way much like the '-exec'\r
+ option of the find(1) command. Webwalk is usually used\r
+ behind the HP firewall\r
+robot-history: \r
+robot-environment:\r
+modified-date: Wed Nov 15 09:51:59 PST 1995\r
+modified-by:\r
+\r
+robot-id: webwalker\r
+robot-name: WebWalker\r
+robot-cover-url:\r
+robot-details-url:\r
+robot-owner-name: Fah-Chun Cheong\r
+robot-owner-url: http://www.cs.berkeley.edu/~fccheong/\r
+robot-owner-email: fccheong@cs.berkeley.edu\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: WebWalker\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: WebWalker/1.10\r
+robot-language: perl4\r
+robot-description: WebWalker performs WWW traversal for individual\r
+ sites and tests for the integrity of all hyperlinks\r
+ to external sites. \r
+robot-history: A Web maintenance robot for expository purposes,\r
+ first published in the book "Internet Agents: Spiders,\r
+ Wanderers, Brokers, and Bots" by the robot's author.\r
+robot-environment: hobby\r
+modified-date: Thu, 25 Jul 1996 16:00:52 PDT\r
+modified-by: Fah-Chun Cheong\r
+\r
+robot-id: webwatch\r
+robot-name: WebWatch\r
+robot-cover-url: http://www.specter.com/users/janos/specter\r
+robot-details-url:\r
+robot-owner-name: Joseph Janos\r
+robot-owner-url: http://www.specter.com/users/janos/specter\r
+robot-owner-email: janos@specter.com\r
+robot-status: \r
+robot-purpose: maintainance, statistics\r
+robot-type: standalone\r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: no\r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: \r
+robot-from: no\r
+robot-useragent: WebWatch\r
+robot-language: c++\r
+robot-description: Its purpose is to validate HTML, and generate statistics.\r
+ Check URLs modified since a given date.\r
+robot-history: \r
+robot-environment:\r
+modified-date: Wed Jul 26 13:36:32 1995\r
+modified-by:\r
+\r
+robot-id: wget\r
+robot-name: Wget\r
+robot-cover-url: ftp://gnjilux.cc.fer.hr/pub/unix/util/wget/\r
+robot-details-url:\r
+robot-owner-name: Hrvoje Niksic\r
+robot-owner-url:\r
+robot-owner-email: hniksic@srce.hr\r
+robot-status: development\r
+robot-purpose: mirroring, maintenance\r
+robot-type: standalone\r
+robot-platform: unix\r
+robot-availability: source\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: wget\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: Wget/1.4.0\r
+robot-language: C\r
+robot-description:\r
+ Wget is a utility for retrieving files using HTTP and FTP protocols.\r
+ It works non-interactively, and can retrieve HTML pages and FTP\r
+ trees recursively. It can be used for mirroring Web pages and FTP\r
+ sites, or for traversing the Web gathering data. It is run by the\r
+ end user or archive maintainer.\r
+robot-history:\r
+robot-environment: hobby, research\r
+modified-date: Mon, 11 Nov 1996 06:00:44 MET\r
+modified-by: Hrvoje Niksic\r
+\r
+robot-id: whowhere\r
+robot-name: WhoWhere Robot\r
+robot-cover-url: http://www.whowhere.com\r
+robot-details-url: \r
+robot-owner-name: Rupesh Kapoor\r
+robot-owner-url: \r
+robot-owner-email: rupesh@whowhere.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: Sun Unix\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: whowhere\r
+robot-noindex: no\r
+robot-host: spica.whowhere.com\r
+robot-from: no\r
+robot-useragent: \r
+robot-language: C/Perl\r
+robot-description: Gathers data for email directory from web pages\r
+robot-history: \r
+robot-environment: commercial\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: wmir\r
+robot-name: w3mir\r
+robot-cover-url: http://www.ifi.uio.no/~janl/w3mir.html\r
+robot-details-url:\r
+robot-owner-name: Nicolai Langfeldt\r
+robot-owner-url: http://www.ifi.uio.no/~janl/w3mir.html\r
+robot-owner-email: w3mir-core@usit.uio.no\r
+robot-status:\r
+robot-purpose: mirroring.\r
+robot-type: standalone\r
+robot-platform: UNIX, WindowsNT\r
+robot-availability:\r
+robot-exclusion: no.\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: w3mir\r
+robot-language: Perl\r
+robot-description: W3mir uses the If-Modified-Since HTTP header and recurses\r
+ only the directory and subdirectories of it's start\r
+ document. Known to work on U*ixes and Windows\r
+ NT.\r
+robot-history:\r
+robot-environment:\r
+modified-date: Wed Apr 24 13:23:42 1996.\r
+modified-by:\r
+\r
+robot-id: wolp\r
+robot-name: WebStolperer\r
+robot-cover-url: http://www.suchfibel.de/maschinisten\r
+robot-details-url: http://www.suchfibel.de/maschinisten/text/werkzeuge.htm (in German)\r
+robot-owner-name: Marius Dahler\r
+robot-owner-url: http://www.suchfibel.de/maschinisten\r
+robot-owner-email: mda@suchfibel.de\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix, NT\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: WOLP\r
+robot-noindex: yes\r
+robot-host: www.suchfibel.de\r
+robot-from: yes\r
+robot-useragent: WOLP/1.0 mda/1.0\r
+robot-language: perl5\r
+robot-description: The robot gathers information about specified\r
+ web-projects and generates knowledge bases in Javascript or an own\r
+ format\r
+robot-environment: hobby\r
+modified-date: 22 Jul 1998\r
+modified-by: Marius Dahler\r
+\r
+robot-id: wombat\r
+robot-name: The Web Wombat \r
+robot-cover-url: http://www.intercom.com.au/wombat/\r
+robot-details-url:\r
+robot-owner-name: Internet Communications\r
+robot-owner-url: http://www.intercom.com.au/\r
+robot-owner-email: phill@intercom.com.au\r
+robot-status:\r
+robot-purpose: indexing, statistics.\r
+robot-type:\r
+robot-platform:\r
+robot-availability:\r
+robot-exclusion: no.\r
+robot-exclusion-useragent:\r
+robot-noindex:\r
+robot-host: qwerty.intercom.com.au\r
+robot-from: no\r
+robot-useragent: no\r
+robot-language: IBM Rexx/VisualAge C++ under OS/2.\r
+robot-description: The robot is the basis of the Web Wombat search engine\r
+ (Australian/New Zealand content ONLY).\r
+robot-history:\r
+robot-environment:\r
+modified-date: Thu Feb 29 00:39:49 1996.\r
+modified-by:\r
+\r
+robot-id: worm\r
+robot-name: The World Wide Web Worm\r
+robot-cover-url: http://www.cs.colorado.edu/home/mcbryan/WWWW.html\r
+robot-details-url:\r
+robot-owner-name: Oliver McBryan\r
+robot-owner-url: http://www.cs.colorado.edu/home/mcbryan/Home.html\r
+robot-owner-email: mcbryan@piper.cs.colorado.edu\r
+robot-status: \r
+robot-purpose: indexing\r
+robot-type: \r
+robot-platform: \r
+robot-availability: \r
+robot-exclusion: \r
+robot-exclusion-useragent:\r
+robot-noindex: no\r
+robot-host: piper.cs.colorado.edu\r
+robot-from: \r
+robot-useragent: \r
+robot-language: \r
+robot-description: indexing robot, actually has quite flexible search\r
+ options\r
+robot-history: \r
+robot-environment:\r
+modified-date: \r
+modified-by:\r
+\r
+robot-id: wwwc\r
+robot-name: WWWC Ver 0.2.5\r
+robot-cover-url: http://www.kinet.or.jp/naka/tomo/wwwc.html\r
+robot-details-url:\r
+robot-owner-name: Tomoaki Nakashima.\r
+robot-owner-url: http://www.kinet.or.jp/naka/tomo/\r
+robot-owner-email: naka@kinet.or.jp\r
+robot-status: active\r
+robot-purpose: maintenance\r
+robot-type: standalone\r
+robot-platform: windows, windows95, windowsNT\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: WWWC\r
+robot-noindex: no\r
+robot-host:\r
+robot-from: yes\r
+robot-useragent: WWWC/0.25 (Win95)\r
+robot-language: c\r
+robot-description:\r
+robot-history: 1997\r
+robot-environment: hobby\r
+modified-date: Tuesday, 18 Feb 1997 06:02:47 GMT\r
+modified-by: Tomoaki Nakashima (naka@kinet.or.jp)\r
+\r
+robot-id: wz101\r
+robot-name: WebZinger\r
+robot-details-url: http://www.imaginon.com/wzindex.html\r
+robot-cover-url: http://www.imaginon.com\r
+robot-owner-name: ImaginOn, Inc\r
+robot-owner-url: http://www.imaginon.com\r
+robot-owner-email: info@imaginon.com\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: windows95, windowsNT 4, mac, solaris, unix\r
+robot-availability: binary\r
+robot-exclusion: no\r
+robot-exclusion-useragent: none\r
+robot-noindex: no\r
+robot-host: http://www.imaginon.com/wzindex.html *\r
+robot-from: no\r
+robot-useragent: none\r
+robot-language: java\r
+robot-description: commercial Web Bot that accepts plain text queries, uses\r
+ webcrawler, lycos or excite to get URLs, then visits sites. If the user's\r
+ filter parameters are met, downloads one picture and a paragraph of test.\r
+ Playsback slide show format of one text paragraph plus image from each site.\r
+robot-history: developed by ImaginOn in 1996 and 1997\r
+robot-environment: commercial\r
+modified-date: Wed, 11 Sep 1997 02:00:00 GMT\r
+modified-by: schwartz@imaginon.com\r
+\r
+robot-id: xget\r
+robot-name: XGET\r
+robot-cover-url: http://www2.117.ne.jp/~moremore/x68000/soft/soft.html\r
+robot-details-url: http://www2.117.ne.jp/~moremore/x68000/soft/soft.html\r
+robot-owner-name: Hiroyuki Shigenaga\r
+robot-owner-url: http://www2.117.ne.jp/~moremore/\r
+robot-owner-email: shige@mh1.117.ne.jp\r
+robot-status: active\r
+robot-purpose: mirroring\r
+robot-type: standalone\r
+robot-platform: X68000, X68030\r
+robot-availability: binary\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: XGET\r
+robot-noindex: no\r
+robot-host: *\r
+robot-from: yes\r
+robot-useragent: XGET/0.7\r
+robot-language: c\r
+robot-description: Its purpose is to retrieve updated files.It is run by the end userrobot-history: 1997\r
+robot-environment: hobby\r
+modified-date: Fri, 07 May 1998 17:00:00 GMT\r
+modified-by: Hiroyuki Shigenaga\r
+\r
+robot-id: Nederland.zoek\r
+robot-name: Nederland.zoek\r
+robot-cover-url: http://www.nederland.net/\r
+robot-details-url: \r
+robot-owner-name: System Operator Nederland.net\r
+robot-owner-url: \r
+robot-owner-email: zoek@nederland.net\r
+robot-status: active\r
+robot-purpose: indexing\r
+robot-type: standalone\r
+robot-platform: unix (Linux)\r
+robot-availability: none\r
+robot-exclusion: yes\r
+robot-exclusion-useragent: Nederland.zoek\r
+robot-noindex: no\r
+robot-host: 193.67.110.*\r
+robot-from: yes\r
+robot-useragent: Nederland.zoek\r
+robot-language: c\r
+robot-description: This robot indexes all .nl sites for the search-engine of Nederland.net\r
+robot-history: Developed at Computel Standby in Apeldoorn, The Netherlands\r
+robot-environment: service\r
+modified-date: Sat, 8 Feb 1997 01:10:00 CET\r
+modified-by: Sander Steffann <sander@nederland.net>\r
+\r
+\r
+\r
projects / thirdparty / AWStats.git / commitdiff
