Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cbsnews.py

   1 # coding: 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_NAME = 'cbsnews'
  13     IE_DESC = 'CBS News'
  14     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
  15
  16     _TESTS = [
  17         {
  18             'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
  19             'info_dict': {
  20                 'id': 'tesla-and-spacex-elon-musks-industrial-empire',
  21                 'ext': 'flv',
  22                 'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire',
  23                 'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg',
  24                 'duration': 791,
  25             },
  26             'params': {
  27                 # rtmp download
  28                 'skip_download': True,
  29             },
  30             'skip': 'Subscribers only',
  31         },
  32         {
  33             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
  34             'info_dict': {
  35                 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
  36                 'ext': 'mp4',
  37                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  38                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
  39                 'upload_date': '20140404',
  40                 'timestamp': 1396650660,
  41                 'uploader': 'CBSI-NEW',
  42                 'thumbnail': r're:^https?://.*\.jpg$',
  43                 'duration': 205,
  44                 'subtitles': {
  45                     'en': [{
  46                         'ext': 'ttml',
  47                     }],
  48                 },
  49             },
  50             'params': {
  51                 # m3u8 download
  52                 'skip_download': True,
  53             },
  54         },
  55     ]
  56
  57     def _real_extract(self, url):
  58         video_id = self._match_id(url)
  59
  60         webpage = self._download_webpage(url, video_id)
  61
  62         video_info = self._parse_json(self._html_search_regex(
  63             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
  64             webpage, 'video JSON info'), video_id)
  65
  66         item = video_info['item'] if 'item' in video_info else video_info
  67         guid = item['mpxRefId']
  68         return self._extract_video_info(guid)
  69
  70
  71 class CBSNewsLiveVideoIE(InfoExtractor):
  72     IE_NAME = 'cbsnews:livevideo'
  73     IE_DESC = 'CBS News Live Videos'
  74     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[^/?#]+)'
  75
  76     # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
  77     _TEST = {
  78         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
  79         'info_dict': {
  80             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
  81             'ext': 'mp4',
  82             'title': 'Clinton, Sanders Prepare To Face Off In NH',
  83             'duration': 334,
  84         },
  85         'skip': 'Video gone',
  86     }
  87
  88     def _real_extract(self, url):
  89         display_id = self._match_id(url)
  90
  91         video_info = self._download_json(
  92             'http://feeds.cbsn.cbsnews.com/rundown/story', display_id, query={
  93                 'device': 'desktop',
  94                 'dvr_slug': display_id,
  95             })
  96
  97         formats = self._extract_akamai_formats(video_info['url'], display_id)
  98         self._sort_formats(formats)
  99
 100         return {
 101             'id': display_id,
 102             'display_id': display_id,
 103             'title': video_info['headline'],
 104             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
 105             'duration': parse_duration(video_info.get('segmentDur')),
 106             'formats': formats,
 107         }