recipetool: Handle unclean response in go resolver

It appears that some go modules repond with a 404 error when trying to
resolve them dynamically. The response body may still contain the
go-import meta tag. An example for such behaviour is gonum.org/v1/gonum.

Signed-off-by: Sven Schwermer <sven.schwermer@disruptive-technologies.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>

diff --git a/scripts/lib/recipetool/create_go.py b/scripts/lib/recipetool/create_go.py
index c56083144296a3c577d726a9bd14d980024a719e..0fb7115e26dbb2ca017aa809b82b379398a8c551 100644 (file)
--- a/scripts/lib/recipetool/create_go.py
+++ b/scripts/lib/recipetool/create_go.py
@@ -16,7 +16,7 @@ from html.parser import HTMLParser
 from recipetool.create import RecipeHandler, handle_license_vars
 from recipetool.create import guess_license, tidy_licenses, fixup_license
 from recipetool.create import determine_from_url
-from urllib.error import URLError
+from urllib.error import URLError, HTTPError
 
 import bb.utils
 import json
@@ -251,15 +251,18 @@ class GoRecipeHandler(RecipeHandler):
         req = urllib.request.Request(url)
 
         try:
-            resp = urllib.request.urlopen(req)
-
+            body = urllib.request.urlopen(req).read()
+        except HTTPError as http_err:
+            logger.warning(
+                "Unclean status when fetching page from [%s]: %s", url, str(http_err))
+            body = http_err.fp.read()
         except URLError as url_err:
             logger.warning(
                 "Failed to fetch page from [%s]: %s", url, str(url_err))
             return None
 
         parser = GoImportHTMLParser()
-        parser.feed(resp.read().decode('utf-8'))
+        parser.feed(body.decode('utf-8'))
         parser.close()
 
         return GoImport(parser.import_prefix, parser.vcs, parser.repourl, None)