diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-02-06 00:20:30 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-02-06 00:20:30 +0700 |
| commit | 2aec7256ae3ef877cc57f7d27f0fa171a7f25a98 (patch) | |
| tree | fe9af6df1494ab64ee079a6eadef1189647ab9a8 | |
| parent | 815482d4eb03c2b3ea319288cc66b38406dbb9d5 (diff) | |
| download | youtube-dl-2aec7256ae3ef877cc57f7d27f0fa171a7f25a98.tar.gz youtube-dl-2aec7256ae3ef877cc57f7d27f0fa171a7f25a98.tar.xz youtube-dl-2aec7256ae3ef877cc57f7d27f0fa171a7f25a98.zip | |
[extractor/common] Speed-up media tags regex (closes #11979)
| -rw-r--r-- | youtube_dl/extractor/common.py | 7 |
1 files changed, 6 insertions, 1 deletions
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)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', 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)(<(?P<tag>video|audio)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage)) for media_tag, media_type, media_content in media_tags: media_info = { 'formats': [], |