_ Git - youtube-dl/blob - 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$',
  37                 'duration': 205,
  38             },
  39             'params': {
  40                 # rtmp download
  41                 'skip_download': True,
  42             },
  43         },
  44         {
  45             'url': 'http://www.cbsnews.com/videos/mountain-lions-of-l-a/',
  46             'info_dict': {
  47                 'id': 'Mountain Lions of L.A.',
  48                 'ext': 'flv',
  49                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  50                 'thumbnail': 're:^http?://.*\.jpg$',
  51                 'subtitles': 're:^http?://.*\.xml$',
  52                 'duration': 787,
  53             },
  54             'params': {
  55                 # rtmp download
  56                 'skip_download': True,
  57             },
  58         },
  59     ]
  60
  61     def _real_extract(self, url):
  62         mobj = re.match(self._VALID_URL, url)
  63         video_id = mobj.group('id')
  64
  65         webpage = self._download_webpage(url, video_id)
  66
  67         video_info = json.loads(self._html_search_regex(
  68             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
  69             webpage, 'video JSON info'))
  70
  71         item = video_info['item'] if 'item' in video_info else video_info
  72         title = item.get('articleTitle') or item.get('hed')
  73         duration = item.get('duration')
  74         thumbnail = item.get('mediaImage') or item.get('thumbnail')
  75
  76         formats = []
  77         for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
  78             uri = item.get('media' + format_id + 'URI')
  79             if not uri:
  80                 continue
  81             uri = remove_start(uri, '{manifest:none}')
  82             fmt = {
  83                 'url': uri,
  84                 'format_id': format_id,
  85             }
  86             if uri.startswith('rtmp'):
  87                 play_path = re.sub(
  88                     r'{slistFilePath}', '',
  89                     uri.split('<break>')[-1].split('{break}')[-1])
  90                 play_path = re.sub(
  91                     r'{manifest:.+}.*$', '', play_path)
  92                 fmt.update({
  93                     'app': 'ondemand?auth=cbs',
  94                     'play_path': 'mp4:' + play_path,
  95                     'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
  96                     'page_url': 'http://www.cbsnews.com',
  97                     'ext': 'flv',
  98                 })
  99             elif uri.endswith('.m3u8'):
 100                 fmt['ext'] = 'mp4'
 101             formats.append(fmt)
 102
 103         if 'mpxRefId' in video_info:
 104             cap_url = 'http://www.cbsnews.com/videos/captions/%s.adb_xml' % video_info['mpxRefId']
 105             subtitles = {
 106                 'en': [{
 107                     'url': cap_url,
 108                     'ext': 'xml'
 109                 }], }
 110         else:
 111             subtitles = {}
 112
 113         return {
 114             'id': video_id,
 115             'title': title,
 116             'thumbnail': thumbnail,
 117             'duration': duration,
 118             'formats': formats,
 119             'subtitles': subtitles,
 120         }