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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .jwplatform import JWPlatformBaseIE
   7 from ..utils import (
   8     float_or_none,
   9     parse_iso8601,
  10     update_url_query,
  11 )
  12
  13
  14 class SendtoNewsIE(JWPlatformBaseIE):
  15     _VALID_URL = r'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P<id>[0-9A-Za-z-]+)'
  16
  17     _TEST = {
  18         # From http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/
  19         'url': 'http://embed.sendtonews.com/player2/embedplayer.php?SC=GxfCe0Zo7D-175909-5588&type=single&autoplay=on&sound=YES',
  20         'info_dict': {
  21             'id': 'GxfCe0Zo7D-175909-5588'
  22         },
  23         'playlist_count': 9,
  24         # test the first video only to prevent lengthy tests
  25         'playlist': [{
  26             'info_dict': {
  27                 'id': '198180',
  28                 'ext': 'mp4',
  29                 'title': 'Recap: CLE 5, LAA 4',
  30                 'description': '8/14/16: Naquin, Almonte lead Indians in 5-4 win',
  31                 'duration': 57.343,
  32                 'thumbnail': r're:https?://.*\.jpg$',
  33                 'upload_date': '20160815',
  34                 'timestamp': 1471221961,
  35             },
  36         }],
  37         'params': {
  38             # m3u8 download
  39             'skip_download': True,
  40         },
  41     }
  42
  43     _URL_TEMPLATE = '//embed.sendtonews.com/player2/embedplayer.php?SC=%s'
  44
  45     @classmethod
  46     def _extract_url(cls, webpage):
  47         mobj = re.search(r'''(?x)<script[^>]+src=([\'"])
  48             (?:https?:)?//embed\.sendtonews\.com/player/responsiveembed\.php\?
  49                 .*\bSC=(?P<SC>[0-9a-zA-Z-]+).*
  50             \1>''', webpage)
  51         if mobj:
  52             sc = mobj.group('SC')
  53             return cls._URL_TEMPLATE % sc
  54
  55     def _real_extract(self, url):
  56         playlist_id = self._match_id(url)
  57
  58         data_url = update_url_query(
  59             url.replace('embedplayer.php', 'data_read.php'),
  60             {'cmd': 'loadInitial'})
  61         playlist_data = self._download_json(data_url, playlist_id)
  62
  63         entries = []
  64         for video in playlist_data['playlistData'][0]:
  65             info_dict = self._parse_jwplayer_data(
  66                 video['jwconfiguration'],
  67                 require_title=False, rtmp_params={'no_resume': True})
  68
  69             thumbnails = []
  70             if video.get('thumbnailUrl'):
  71                 thumbnails.append({
  72                     'id': 'normal',
  73                     'url': video['thumbnailUrl'],
  74                 })
  75             if video.get('smThumbnailUrl'):
  76                 thumbnails.append({
  77                     'id': 'small',
  78                     'url': video['smThumbnailUrl'],
  79                 })
  80             info_dict.update({
  81                 'title': video['S_headLine'],
  82                 'description': video.get('S_fullStory'),
  83                 'thumbnails': thumbnails,
  84                 'duration': float_or_none(video.get('SM_length')),
  85                 'timestamp': parse_iso8601(video.get('S_sysDate'), delimiter=' '),
  86             })
  87             entries.append(info_dict)
  88
  89         return self.playlist_result(entries, playlist_id)