diff options
| author | Sergey M․ <dstftw@gmail.com> | 2014-09-27 22:29:27 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2014-09-27 22:29:27 +0700 |
| commit | 497339fa0e633c8b1dcebf3f70670f6d96ee2d62 (patch) | |
| tree | 326ae5fd1971d8316b8a8bce5e36af3437ed933c | |
| parent | 8e6f8051f084f445015140f1f88ac770f3c0f43d (diff) | |
[anysex] Fix extraction
| -rw-r--r-- | youtube_dl/extractor/anysex.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/youtube_dl/extractor/anysex.py b/youtube_dl/extractor/anysex.py index bc64423a3..ad86d6e58 100644 --- a/youtube_dl/extractor/anysex.py +++ b/youtube_dl/extractor/anysex.py @@ -35,7 +35,7 @@ class AnySexIE(InfoExtractor): title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') description = self._html_search_regex( - r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) + r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False) thumbnail = self._html_search_regex( r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) @@ -43,7 +43,7 @@ class AnySexIE(InfoExtractor): r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) duration = parse_duration(self._search_regex( - r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False)) + r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) |