diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-04-30 21:25:17 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-04-30 21:25:17 +0600 |
commit | cd298882cd6f8ed2571dd372f684ec17e992fd9d (patch) | |
tree | 3c28b63bb391f89a54188086ad884f19dc7d7c3c /youtube_dl/extractor/vporn.py | |
parent | e01c56f9e12d7abb2e3b548818a689146092806e (diff) |
[vporn] Fix metadata extraction (#5560)
Diffstat (limited to 'youtube_dl/extractor/vporn.py')
-rw-r--r-- | youtube_dl/extractor/vporn.py | 22 |
1 files changed, 10 insertions, 12 deletions
diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py index 2d23effcc..04ed0b381 100644 --- a/youtube_dl/extractor/vporn.py +++ b/youtube_dl/extractor/vporn.py @@ -64,29 +64,29 @@ class VpornIE(InfoExtractor): title = self._html_search_regex( r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() description = self._html_search_regex( - r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False) + r'class="(?:descr|description_txt)">(.*?)</div>', + webpage, 'description', fatal=False) thumbnail = self._html_search_regex( r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None) if thumbnail: thumbnail = 'http://www.vporn.com' + thumbnail uploader = self._html_search_regex( - r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>', + r'(?s)Uploaded by:.*?<a href="/user/[^"]+">([^<]+)</a>', webpage, 'uploader', fatal=False) categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage) duration = parse_duration(self._search_regex( - r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False)) + r'Runtime:\s*</span>\s*(\d+ min \d+ sec)', + webpage, 'duration', fatal=False)) - view_count = str_to_int(self._html_search_regex( - r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False)) - like_count = str_to_int(self._html_search_regex( - r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False)) - dislike_count = str_to_int(self._html_search_regex( - r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False)) + view_count = str_to_int(self._search_regex( + r'class="views">([\d,\.]+) [Vv]iews<', + webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( - r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False)) + r"'Comments \(([\d,\.]+)\)'", + webpage, 'comment count', default=None)) formats = [] @@ -117,8 +117,6 @@ class VpornIE(InfoExtractor): 'categories': categories, 'duration': duration, 'view_count': view_count, - 'like_count': like_count, - 'dislike_count': dislike_count, 'comment_count': comment_count, 'age_limit': 18, 'formats': formats, |