diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-02-07 01:52:59 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-02-07 01:52:59 +0700 |
| commit | f28aeff26416515fbaf46ce087e8332a15958c23 (patch) | |
| tree | 1ce66d7457d163466589575fdb25c484ae878999 | |
| parent | 242a14a1f6ea14b8e7de9aa1eddaf938de825e1e (diff) | |
| download | youtube-dl-f28aeff26416515fbaf46ce087e8332a15958c23.tar.gz youtube-dl-f28aeff26416515fbaf46ce087e8332a15958c23.tar.xz youtube-dl-f28aeff26416515fbaf46ce087e8332a15958c23.zip | |
[pornhub] Fix extraction (closes #11997)
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 3eaf56973..017f6c552 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -156,7 +156,12 @@ class PornHubIE(InfoExtractor): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') - video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage))) + video_urls = [] + for quote, video_url in re.findall( + r'player_quality_[0-9]{3,4}p\s*=\s*(["\'])(.+?)\1;', webpage): + video_urls.append(compat_urllib_parse_unquote(re.sub( + r'{0}\s*\+\s*{0}'.format(quote), '', video_url))) + if webpage.find('"encrypted":true') != -1: password = compat_urllib_parse_unquote_plus( self._search_regex(r'"video_title":"([^"]+)', webpage, 'password')) |