From: Sergey M․ Date: Sun, 5 Feb 2017 17:20:30 +0000 (+0700) Subject: [extractor/common] Speed-up media tags regex (closes #11979) X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=2aec7256ae3ef877cc57f7d27f0fa171a7f25a98;p=youtube-dl [extractor/common] Speed-up media tags regex (closes #11979) --- diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 2c8ec1417..519188622 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1959,7 +1959,12 @@ class InfoExtractor(object): media_tags = [(media_tag, media_type, '') for media_tag, media_type in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)] - media_tags.extend(re.findall(r'(?s)(<(?Pvideo|audio)[^>]*>)(.*?)', webpage)) + media_tags.extend(re.findall( + # We only allow video|audio followed by a whitespace or '>'. + # Allowing more characters may end up in significant slow down (see + # https://github.com/rg3/youtube-dl/issues/11979, example URL: + # http://www.porntrex.com/maps/videositemap.xml). + r'(?s)(<(?Pvideo|audio)(?:\s+[^>]*)?>)(.*?)', webpage)) for media_tag, media_type, media_content in media_tags: media_info = { 'formats': [],