doc/utils/html2txt.sed

   1 # skip over header material
   2 # Copyright (C) 1999  Sandy Harris.
   3 #
   4 # This program is free software; you can redistribute it and/or modify it
   5 # under the terms of the GNU General Public License as published by the
   6 # Free Software Foundation; either version 2 of the License, or (at your
   7 # option) any later version.  See <http://www.fsf.org/copyleft/gpl.txt>.
   8 #
   9 # This program is distributed in the hope that it will be useful, but
  10 # WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
  11 # or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  12 # for more details.
  13 #
  14 # RCSID $Id: html2txt.sed,v 1.1 2004/03/15 20:35:24 as Exp $
  15 /<head>/,/<\/head>/d
  16 /<HEAD>/,/<\/HEAD>/d
  17 /<^body$>/d
  18 s/<body>//
  19 # eliminate possible DOS crud
  20 s/\015//
  21 #get rid of HTML comments
  22 s/<!--.*-->//
  23 /<!--/,/-->/d
  24 # citations & emphasis -> visible
  25 s/<cite>/"/g
  26 s/<\/cite>/"/g
  27 s/<em>/*/g
  28 s/<\/em>/*/g
  29 s/<strong>/!->/g
  30 s/<\/strong>/<-!/g
  31 s/<b>//g
  32 s/<\/b>//g
  33 s/<blockquote>/Quote -->/
  34 s/<\/blockquote>/<-- End Quote/
  35 # mark headers
  36 s/<h1>/Header 1:  /
  37 s/<h2>/Header 2:  /
  38 s/<h3>/Header 3:  /
  39 s/<h4>/Header 4:  /
  40 s/<h5>/Header 5:  /
  41 s/<h6>/Header 6:  /
  42 # remove some cruft
  43 s/<\/h[1-6]>//
  44 /^<a name=[a-zA-Z0-9\.]*>$/d
  45 s/<a name=[a-zA-Z0-9\.]*>//
  46 # definition lists
  47 s/<dl>//
  48 s/<\/dl>//
  49 s/^<dt>$/-----------------------------------------/
  50 s/^<dt>/-----------------------------------------\
  51 /
  52 s/<dd>/\
  53 /
  54 # other types of lists
  55 s/<li>//
  56 s/<ol>//
  57 s/<ul>//
  58 s/<\/ol>//
  59 s/<\/ul>//
  60 # tables
  61 s/<table>//
  62 s/<\/table>//
  63 s/<tr>//
  64 s/<td>/ /g
  65 # line break and paragraph markers
  66 # different subst depending where they are in line
  67 s/^<br>//
  68 s/<br>$//
  69 s/<br>/\
  70 /
  71 s/^<p>$//
  72 s/<p>$/\
  73 /
  74 s/^<p>/\
  75 /
  76 s/<p>/\
  77 \
  78 /
  79 s/<\/p>//
  80 # remove more cruft
  81 s/<pre>//
  82 s/<\/pre>//
  83 s/<\/body>//
  84 s/<\/html//
  85 s/<\/BODY>//
  86 s/<\/HTML>//