From bb9741193c329d4432499621751a4ec70c2556ba Mon Sep 17 00:00:00 2001 From: Henrik Levkowetz Date: Mon, 28 Nov 2016 13:38:31 +0000 Subject: [PATCH] Added an url to skip (from an uploaded html agenda). - Legacy-Id: 12400 --- bin/test-crawl | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/bin/test-crawl b/bin/test-crawl index cc993f845..156c8f444 100755 --- a/bin/test-crawl +++ b/bin/test-crawl @@ -189,13 +189,17 @@ def check_html_valid(url, response, args): (pos, code)) warnings += 1 +@debug.trace def skip_url(url): + debug.show('url') for pattern in ( "^/community/[0-9]+/remove_document/", "^/community/personal/", # Skip most of the slow pdf composite generation urls and svg urls "^/meeting/[0-9]+/agenda/[0-9b-z].*-drafts\\.pdf", "^/wg/[a-z0-9-]+/deps/svg/", + # This bad url occurs in an uploaded html agenda: + r"/site/ietfdhcwg/_/rsrc/1311005436000/system/app/css/overlay.css\?cb=simple100%250150goog-ws-left", ): if re.search(pattern, url): return True