diff options
Diffstat (limited to 'youtube_dl/extractor/cbsnews.py')
| -rw-r--r-- | youtube_dl/extractor/cbsnews.py | 52 |
1 files changed, 39 insertions, 13 deletions
diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 17bb9af4f..51df15fac 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -15,19 +15,23 @@ class CBSNewsIE(CBSIE): _TESTS = [ { - 'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/', + # 60 minutes + 'url': 'http://www.cbsnews.com/news/artificial-intelligence-positioned-to-be-a-game-changer/', 'info_dict': { - 'id': 'tesla-and-spacex-elon-musks-industrial-empire', - 'ext': 'flv', - 'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire', - 'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg', - 'duration': 791, + 'id': '_B6Ga3VJrI4iQNKsir_cdFo9Re_YJHE_', + 'ext': 'mp4', + 'title': 'Artificial Intelligence', + 'description': 'md5:8818145f9974431e0fb58a1b8d69613c', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 1606, + 'uploader': 'CBSI-NEW', + 'timestamp': 1498431900, + 'upload_date': '20170625', }, 'params': { - # rtmp download + # m3u8 download 'skip_download': True, }, - 'skip': 'Subscribers only', }, { 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/', @@ -52,6 +56,22 @@ class CBSNewsIE(CBSIE): 'skip_download': True, }, }, + { + # 48 hours + 'url': 'http://www.cbsnews.com/news/maria-ridulph-murder-will-the-nations-oldest-cold-case-to-go-to-trial-ever-get-solved/', + 'info_dict': { + 'id': 'QpM5BJjBVEAUFi7ydR9LusS69DPLqPJ1', + 'ext': 'mp4', + 'title': 'Cold as Ice', + 'description': 'Can a childhood memory of a friend\'s murder solve a 1957 cold case? "48 Hours" correspondent Erin Moriarty has the latest.', + 'upload_date': '20170604', + 'timestamp': 1496538000, + 'uploader': 'CBSI-NEW', + }, + 'params': { + 'skip_download': True, + }, + }, ] def _real_extract(self, url): @@ -60,12 +80,18 @@ class CBSNewsIE(CBSIE): webpage = self._download_webpage(url, video_id) video_info = self._parse_json(self._html_search_regex( - r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'', - webpage, 'video JSON info'), video_id) + r'(?:<ul class="media-list items" id="media-related-items"[^>]*><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'', + webpage, 'video JSON info', default='{}'), video_id, fatal=False) + + if video_info: + item = video_info['item'] if 'item' in video_info else video_info + else: + state = self._parse_json(self._search_regex( + r'data-cbsvideoui-options=(["\'])(?P<json>{.+?})\1', webpage, + 'playlist JSON info', group='json'), video_id)['state'] + item = state['playlist'][state['pid']] - item = video_info['item'] if 'item' in video_info else video_info - guid = item['mpxRefId'] - return self._extract_video_info(guid) + return self._extract_video_info(item['mpxRefId'], 'cbsnews') class CBSNewsLiveVideoIE(InfoExtractor): |