X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsunporno.py;h=68051169b974d7bc748238566be1c31734eb8ed7;hb=HEAD;hp=7de3c9dd5014586a118ab3eb55365897d160945d;hpb=1b8477729a07f3b87f4c20175cf337335100341c;p=youtube-dl diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py index 7de3c9dd5..68051169b 100644 --- a/youtube_dl/extractor/sunporno.py +++ b/youtube_dl/extractor/sunporno.py @@ -12,43 +12,52 @@ from ..utils import ( class SunPornoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P\d+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www\.)?sunporno\.com/videos|embeds\.sunporno\.com/embed)/(?P\d+)' + _TESTS = [{ 'url': 'http://www.sunporno.com/videos/807778/', - 'md5': '6457d3c165fd6de062b99ef6c2ff4c86', + 'md5': '507887e29033502f29dba69affeebfc9', 'info_dict': { 'id': '807778', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'md5:0a400058e8105d39e35c35e7c5184164', 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 302, 'age_limit': 18, } - } + }, { + 'url': 'http://embeds.sunporno.com/embed/807778', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'http://www.sunporno.com/videos/%s' % video_id, video_id) - title = self._html_search_regex(r'([^<]+)', webpage, 'title') - description = self._html_search_meta('description', webpage, 'description') + title = self._html_search_regex( + r'([^<]+)', webpage, 'title') + description = self._html_search_meta( + 'description', webpage, 'description') thumbnail = self._html_search_regex( r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._search_regex( - r'Duration: (\d+:\d+)', webpage, 'duration', fatal=False)) + (r'itemprop="duration"[^>]*>\s*(\d+:\d+)\s*<', + r'>Duration:\s*]+>\s*(\d+:\d+)\s*<'), + webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( - r'(\d+)', webpage, 'view count', fatal=False)) + r'class="views">(?: