youtube_dl/extractor/cbsnews.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import remove_start
   9
  10
  11 class CBSNewsIE(InfoExtractor):
  12     IE_DESC = 'CBS News'
  13     _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?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         },
  30         {
  31             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
  32             'info_dict': {
  33                 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
  34                 'ext': 'flv',
  35                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  36                 'thumbnail': 're:^https?://.*\.jpg$',
  37                 'duration': 205,
  38             },
  39             'params': {
  40                 # rtmp download
  41                 'skip_download': True,
  42             },
  43         },
  44     ]
  45
  46     def _real_extract(self, url):
  47         mobj = re.match(self._VALID_URL, url)
  48         video_id = mobj.group('id')
  49
  50         webpage = self._download_webpage(url, video_id)
  51
  52         video_info = json.loads(self._html_search_regex(
  53             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
  54             webpage, 'video JSON info'))
  55
  56         item = video_info['item'] if 'item' in video_info else video_info
  57         title = item.get('articleTitle') or item.get('hed')
  58         duration = item.get('duration')
  59         thumbnail = item.get('mediaImage') or item.get('thumbnail')
  60
  61         formats = []
  62         for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
  63             uri = item.get('media' + format_id + 'URI')
  64             if not uri:
  65                 continue
  66             uri = remove_start(uri, '{manifest:none}')
  67             fmt = {
  68                 'url': uri,
  69                 'format_id': format_id,
  70             }
  71             if uri.startswith('rtmp'):
  72                 play_path = re.sub(
  73                     r'{slistFilePath}', '',
  74                     uri.split('<break>')[-1].split('{break}')[-1])
  75                 play_path = re.sub(
  76                     r'{manifest:.+}.*$', '', play_path)
  77                 fmt.update({
  78                     'app': 'ondemand?auth=cbs',
  79                     'play_path': 'mp4:' + play_path,
  80                     'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
  81                     'page_url': 'http://www.cbsnews.com',
  82                     'ext': 'flv',
  83                 })
  84             elif uri.endswith('.m3u8'):
  85                 fmt['ext'] = 'mp4'
  86             formats.append(fmt)
  87
  88         return {
  89             'id': video_id,
  90             'title': title,
  91             'thumbnail': thumbnail,
  92             'duration': duration,
  93             'formats': formats,
  94         }