_ Git - youtube-dl/blob - youtube_dl/extractor/cbsnews.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .cbs import CBSIE
   6 from ..utils import (
   7     parse_duration,
   8 )
   9
  10
  11 class CBSNewsIE(CBSIE):
  12     IE_DESC = 'CBS News'
  13     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
  14
  15     _TESTS = [
  16         {
  17             'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
  18             'info_dict': {
  19                 'id': 'tesla-and-spacex-elon-musks-industrial-empire',
  20                 'ext': 'flv',
  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',
  23                 'duration': 791,
  24             },
  25             'params': {
  26                 # rtmp download
  27                 'skip_download': True,
  28             },
  29             'skip': 'Subscribers only',
  30         },
  31         {
  32             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
  33             'info_dict': {
  34                 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
  35                 'ext': 'mp4',
  36                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  37                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
  38                 'upload_date': '20140404',
  39                 'timestamp': 1396650660,
  40                 'uploader': 'CBSI-NEW',
  41                 'thumbnail': 're:^https?://.*\.jpg$',
  42                 'duration': 205,
  43                 'subtitles': {
  44                     'en': [{
  45                         'ext': 'ttml',
  46                     }],
  47                 },
  48             },
  49             'params': {
  50                 # m3u8 download
  51                 'skip_download': True,
  52             },
  53         },
  54     ]
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58
  59         webpage = self._download_webpage(url, video_id)
  60
  61         video_info = self._parse_json(self._html_search_regex(
  62             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
  63             webpage, 'video JSON info'), video_id)
  64
  65         item = video_info['item'] if 'item' in video_info else video_info
  66         guid = item['mpxRefId']
  67         return self._extract_video_info(guid)
  68
  69
  70 class CBSNewsLiveVideoIE(InfoExtractor):
  71     IE_DESC = 'CBS News Live Videos'
  72     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
  73
  74     # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
  75     _TEST = {
  76         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
  77         'info_dict': {
  78             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
  79             'ext': 'flv',
  80             'title': 'Clinton, Sanders Prepare To Face Off In NH',
  81             'duration': 334,
  82         },
  83         'skip': 'Video gone',
  84     }
  85
  86     def _real_extract(self, url):
  87         video_id = self._match_id(url)
  88
  89         webpage = self._download_webpage(url, video_id)
  90
  91         video_info = self._parse_json(self._html_search_regex(
  92             r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
  93
  94         hdcore_sign = 'hdcore=3.3.1'
  95         f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
  96         if f4m_formats:
  97             for entry in f4m_formats:
  98                 # URLs without the extra param induce an 404 error
  99                 entry.update({'extra_param_to_segment_url': hdcore_sign})
 100         self._sort_formats(f4m_formats)
 101
 102         return {
 103             'id': video_id,
 104             'title': video_info['headline'],
 105             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
 106             'duration': parse_duration(video_info.get('segmentDur')),
 107             'formats': f4m_formats,
 108         }