diff options
| author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-04-30 23:33:49 +0800 |
|---|---|---|
| committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-04-30 23:33:49 +0800 |
| commit | ffbc3901d276a4fafc9423c51dc2c6aa5d108d91 (patch) | |
| tree | 5664b7378b212560710f76cc0c6ed2897787e7e1 /youtube_dl/extractor | |
| parent | 482a1258de6af0a15b6e7859d244f9125cadef47 (diff) | |
| parent | 7a03280df4555998fc99399907062b62383db2c4 (diff) | |
Merge remote-tracking branch 'upstream/master'
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/vporn.py | 30 |
1 files changed, 11 insertions, 19 deletions
diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py index 2d23effcc..92c90e517 100644 --- a/youtube_dl/extractor/vporn.py +++ b/youtube_dl/extractor/vporn.py @@ -27,9 +27,6 @@ class VpornIE(InfoExtractor): 'duration': 393, 'age_limit': 18, 'view_count': int, - 'like_count': int, - 'dislike_count': int, - 'comment_count': int, } }, { @@ -47,9 +44,6 @@ class VpornIE(InfoExtractor): 'duration': 588, 'age_limit': 18, 'view_count': int, - 'like_count': int, - 'dislike_count': int, - 'comment_count': int, } }, ] @@ -64,29 +58,29 @@ 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) + 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 +111,6 @@ 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, |