X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fredtube.py;h=879bcf81d8136ff4bb1f90a9312ff5c7812fdfb8;hb=4c76aa06665621c7689938afd7bbdbc797b5c7ea;hp=f70a75256c638f4a3ce9cda3b9577176e49f3cca;hpb=880fa66f4ffa9afcfce91b5ce39f05909050da67;p=youtube-dl diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index f70a75256..879bcf81d 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -16,12 +16,12 @@ class RedTubeIE(InfoExtractor): _VALID_URL = r'https?://(?:(?:www\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P[0-9]+)' _TESTS = [{ 'url': 'http://www.redtube.com/66418', - 'md5': '7b8c22b5e7098a3e1c09709df1126d2d', + 'md5': 'fc08071233725f26b8f014dba9590005', 'info_dict': { 'id': '66418', 'ext': 'mp4', 'title': 'Sucked on a toilet', - 'upload_date': '20120831', + 'upload_date': '20110811', 'duration': 596, 'view_count': int, 'age_limit': 18, @@ -46,9 +46,10 @@ class RedTubeIE(InfoExtractor): raise ExtractorError('Video %s has been removed' % video_id, expected=True) title = self._html_search_regex( - (r'

(?P.+?)</h1>', - r'videoTitle\s*:\s*(["\'])(?P<title>)\1'), - webpage, 'title', group='title') + (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>', + r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',), + webpage, 'title', group='title', + default=None) or self._og_search_title(webpage) formats = [] sources = self._parse_json( @@ -87,12 +88,14 @@ class RedTubeIE(InfoExtractor): thumbnail = self._og_search_thumbnail(webpage) upload_date = unified_strdate(self._search_regex( - r'<span[^>]+class="added-time"[^>]*>ADDED ([^<]+)<', + r'<span[^>]+>ADDED ([^<]+)<', webpage, 'upload date', fatal=False)) - duration = int_or_none(self._search_regex( - r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None)) + duration = int_or_none(self._og_search_property( + 'video:duration', webpage, default=None) or self._search_regex( + r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None)) view_count = str_to_int(self._search_regex( - r'<span[^>]*>VIEWS</span></td>\s*<td>([\d,.]+)', + (r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)', + r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)'), webpage, 'view count', fatal=False)) # No self-labeling, but they describe themselves as