diff --git a/youtube_dl/extractor/firsttv.py b/youtube_dl/extractor/firsttv.py index 08ceee4ed..6e015ca16 100644 --- a/youtube_dl/extractor/firsttv.py +++ b/youtube_dl/extractor/firsttv.py @@ -8,45 +8,66 @@ from ..utils import int_or_none class FirstTVIE(InfoExtractor): - IE_NAME = 'firsttv' - IE_DESC = 'Видеоархив - Первый канал' - _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P\d+)' + IE_NAME = '1tv' + IE_DESC = 'Первый канал' + _VALID_URL = r'http://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P.+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.1tv.ru/videoarchive/73390', - 'md5': '3de6390cf0cca4a5eae1d1d83895e5ad', + 'md5': '777f525feeec4806130f4f764bc18a4f', 'info_dict': { 'id': '73390', 'ext': 'mp4', 'title': 'Олимпийские канатные дороги', - 'description': 'md5:cc730d2bf4215463e37fff6a1e277b13', - 'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$', 'duration': 149, + 'like_count': int, + 'dislike_count': int, }, 'skip': 'Only works from Russia', - } + }, { + 'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930', + 'md5': 'a1b6b60d530ebcf8daacf4565762bbaf', + 'info_dict': { + 'id': '35930', + 'ext': 'mp4', + 'title': 'Наедине со всеми. Людмила Сенчина', + 'description': 'md5:89553aed1d641416001fe8d450f06cb9', + 'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$', + 'duration': 2694, + }, + 'skip': 'Only works from Russia', + }] 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, 'Downloading page') video_url = self._html_search_regex( - r'''(?s)jwplayer\('flashvideoportal_1'\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video URL') + r'''(?s)(?:jwplayer\('flashvideoportal_1'\)\.setup\({|var\s+playlistObj\s*=).*?'file'\s*:\s*'([^']+)'.*?}\);''', + webpage, 'video URL') title = self._html_search_regex( - r'
\s*

([^<]*)', webpage, 'title') + [r'
\s*

([^<]*)', + r"'title'\s*:\s*'([^']+)'"], webpage, 'title') description = self._html_search_regex( - r'
\s*
 
\s*

([^<]*)

', webpage, 'description', fatal=False) + r'
\s*
 
\s*

([^<]*)

', + webpage, 'description', default=None) or self._html_search_meta( + 'description', webpage, 'description') thumbnail = self._og_search_thumbnail(webpage) - duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False) + duration = self._og_search_property( + 'video:duration', webpage, + 'video duration', fatal=False) - like_count = self._html_search_regex(r'title="Понравилось".*?/> \[(\d+)\]', - webpage, 'like count', fatal=False) - dislike_count = self._html_search_regex(r'title="Не понравилось".*?/> \[(\d+)\]', - webpage, 'dislike count', fatal=False) + like_count = self._html_search_regex( + r'title="Понравилось".*?/> \[(\d+)\]', + webpage, 'like count', default=None) + dislike_count = self._html_search_regex( + r'title="Не понравилось".*?/> \[(\d+)\]', + webpage, 'dislike count', default=None) return { 'id': video_id,