jenkins-bot has submitted this change and it was merged.
Change subject: Remove old unneeded URL exclusion rules ......................................................................
Remove old unneeded URL exclusion rules
No problems are experienced now accessing these URLs using requests.
Bug: T124015 Change-Id: I1f33969058fc67f8437f2f92325faba636a9c81c --- M scripts/weblinkchecker.py 1 file changed, 1 insertion(+), 12 deletions(-)
Approvals: MtDu: Looks good to me, but someone else must approve Xqt: Looks good to me, approved jenkins-bot: Verified
diff --git a/scripts/weblinkchecker.py b/scripts/weblinkchecker.py index 51bce05..ed22c3c 100755 --- a/scripts/weblinkchecker.py +++ b/scripts/weblinkchecker.py @@ -133,7 +133,6 @@
import requests
-# TODO: Convert to httlib2 if sys.version_info[0] > 2: import http.client as httplib import urllib.parse as urlparse @@ -164,20 +163,10 @@ re.compile(r'.*[./@]example.org(/.*)?'),
# Other special cases - # bot somehow can't handle their redirects: - re.compile(r'.*[./@]gso.gbv.de(/.*)?'), re.compile(r'.*[./@]berlinonline.de(/.*)?'), # above entry to be manually fixed per request at [[de:Benutzer:BLueFiSH.as/BZ]] # bot can't handle their redirects: - re.compile(r'.*[./@]bodo.kommune.no(/.*)?'), - re.compile(r'.*[./@]jpl.nasa.gov(/.*)?'), # bot rejected on the site - re.compile(r'.*[./@]itis.gov(/.*)?'), # bot rejected on the site - re.compile(r'.*[./@]cev.lu(/.*)?'), # bot rejected on the site - # very slow response resulting in bot error: - re.compile(r'.*[./@]science.ksc.nasa.gov(/.*)?'), - re.compile(r'.*[./@]britannica.com(/.*)?'), # HTTP redirect loop - # bot rejected on the site: - re.compile(r'.*[./@]quickfacts.census.gov(/.*)?'), + # bot rejected on the site, already archived re.compile(r'.*[./@]web.archive.org(/.*)?'), ]