2 from __future__ import unicode_literals
4 from .common import InfoExtractor
5 from .cbs import CBSBaseIE
11 class CBSNewsIE(CBSBaseIE):
13 _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
17 'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
19 'id': 'tesla-and-spacex-elon-musks-industrial-empire',
21 'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire',
22 'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg',
27 'skip_download': True,
29 'skip': 'Subscribers only',
32 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
34 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
36 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
37 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
38 'upload_date': '19700101',
39 'uploader': 'CBSI-NEW',
40 'thumbnail': 're:^https?://.*\.jpg$',
50 'skip_download': True,
55 def _real_extract(self, url):
56 video_id = self._match_id(url)
58 webpage = self._download_webpage(url, video_id)
60 video_info = self._parse_json(self._html_search_regex(
61 r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
62 webpage, 'video JSON info'), video_id)
64 item = video_info['item'] if 'item' in video_info else video_info
65 guid = item['mpxRefId']
66 return self._extract_video_info('byGuid=%s' % guid, guid)
69 class CBSNewsLiveVideoIE(InfoExtractor):
70 IE_DESC = 'CBS News Live Videos'
71 _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
74 'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
76 'id': 'clinton-sanders-prepare-to-face-off-in-nh',
78 'title': 'Clinton, Sanders Prepare To Face Off In NH',
81 'skip': 'Video gone, redirected to http://www.cbsnews.com/live/',
83 'url': 'http://www.cbsnews.com/live/video/video-shows-intense-paragliding-accident/',
85 'id': 'video-shows-intense-paragliding-accident',
87 'title': 'Video Shows Intense Paragliding Accident',
91 def _real_extract(self, url):
92 video_id = self._match_id(url)
94 webpage = self._download_webpage(url, video_id)
96 video_info = self._parse_json(self._html_search_regex(
97 r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
99 hdcore_sign = 'hdcore=3.3.1'
100 f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
102 for entry in f4m_formats:
103 # URLs without the extra param induce an 404 error
104 entry.update({'extra_param_to_segment_url': hdcore_sign})
105 self._sort_formats(f4m_formats)
109 'title': video_info['headline'],
110 'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
111 'duration': parse_duration(video_info.get('segmentDur')),
112 'formats': f4m_formats,