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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .turner import TurnerBaseIE
   7 from ..utils import ExtractorError
   8
   9
  10 class AdultSwimIE(TurnerBaseIE):
  11     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
  12
  13     _TESTS = [{
  14         'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
  15         'playlist': [
  16             {
  17                 'md5': '247572debc75c7652f253c8daa51a14d',
  18                 'info_dict': {
  19                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
  20                     'ext': 'flv',
  21                     'title': 'Rick and Morty - Pilot Part 1',
  22                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  23                 },
  24             },
  25             {
  26                 'md5': '77b0e037a4b20ec6b98671c4c379f48d',
  27                 'info_dict': {
  28                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
  29                     'ext': 'flv',
  30                     'title': 'Rick and Morty - Pilot Part 4',
  31                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  32                 },
  33             },
  34         ],
  35         'info_dict': {
  36             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
  37             'title': 'Rick and Morty - Pilot',
  38             'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  39         },
  40         'skip': 'This video is only available for registered users',
  41     }, {
  42         'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
  43         'playlist': [
  44             {
  45                 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
  46                 'info_dict': {
  47                     'id': '-t8CamQlQ2aYZ49ItZCFog-0',
  48                     'ext': 'flv',
  49                     'title': 'American Dad - Putting Francine Out of Business',
  50                     'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  51                 },
  52             }
  53         ],
  54         'info_dict': {
  55             'id': '-t8CamQlQ2aYZ49ItZCFog',
  56             'title': 'American Dad - Putting Francine Out of Business',
  57             'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  58         },
  59     }, {
  60         'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
  61         'playlist': [
  62             {
  63                 'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
  64                 'info_dict': {
  65                     'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
  66                     'ext': 'mp4',
  67                     'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
  68                     'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
  69                 },
  70             }
  71         ],
  72         'info_dict': {
  73             'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
  74             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
  75             'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
  76         },
  77         'params': {
  78             # m3u8 download
  79             'skip_download': True,
  80         }
  81     }, {
  82         # heroMetadata.trailer
  83         'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
  84         'info_dict': {
  85             'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
  86             'ext': 'mp4',
  87             'title': 'Decker - Inside Decker: A New Hero',
  88             'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
  89             'duration': 249.008,
  90         },
  91         'params': {
  92             # m3u8 download
  93             'skip_download': True,
  94         },
  95         'expected_warnings': ['Unable to download f4m manifest'],
  96     }]
  97
  98     @staticmethod
  99     def find_video_info(collection, slug):
 100         for video in collection.get('videos'):
 101             if video.get('slug') == slug:
 102                 return video
 103
 104     @staticmethod
 105     def find_collection_by_linkURL(collections, linkURL):
 106         for collection in collections:
 107             if collection.get('linkURL') == linkURL:
 108                 return collection
 109
 110     @staticmethod
 111     def find_collection_containing_video(collections, slug):
 112         for collection in collections:
 113             for video in collection.get('videos'):
 114                 if video.get('slug') == slug:
 115                     return collection, video
 116         return None, None
 117
 118     def _real_extract(self, url):
 119         mobj = re.match(self._VALID_URL, url)
 120         show_path = mobj.group('show_path')
 121         episode_path = mobj.group('episode_path')
 122         is_playlist = True if mobj.group('is_playlist') else False
 123
 124         webpage = self._download_webpage(url, episode_path)
 125
 126         # Extract the value of `bootstrappedData` from the Javascript in the page.
 127         bootstrapped_data = self._parse_json(self._search_regex(
 128             r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
 129
 130         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
 131         # NOTE: We are only downloading one video (the current one) not the playlist
 132         if is_playlist:
 133             collections = bootstrapped_data['playlists']['collections']
 134             collection = self.find_collection_by_linkURL(collections, show_path)
 135             video_info = self.find_video_info(collection, episode_path)
 136
 137             show_title = video_info['showTitle']
 138             segment_ids = [video_info['videoPlaybackID']]
 139         else:
 140             collections = bootstrapped_data['show']['collections']
 141             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 142             # Video wasn't found in the collections, let's try `slugged_video`.
 143             if video_info is None:
 144                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
 145                     video_info = bootstrapped_data['slugged_video']
 146             if not video_info:
 147                 video_info = bootstrapped_data.get('heroMetadata', {}).get('trailer').get('video')
 148             if not video_info:
 149                 raise ExtractorError('Unable to find video info')
 150
 151             show = bootstrapped_data['show']
 152             show_title = show['title']
 153             stream = video_info.get('stream')
 154             if stream and stream.get('videoPlaybackID'):
 155                 segment_ids = [stream['videoPlaybackID']]
 156             elif video_info.get('clips'):
 157                 segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
 158             elif video_info.get('videoPlaybackID'):
 159                 segment_ids = [video_info['videoPlaybackID']]
 160             else:
 161                 if video_info.get('auth') is True:
 162                     raise ExtractorError(
 163                         'This video is only available via cable service provider subscription that'
 164                         ' is not currently supported. You may want to use --cookies.', expected=True)
 165                 else:
 166                     raise ExtractorError('Unable to find stream or clips')
 167
 168         episode_id = video_info['id']
 169         episode_title = video_info['title']
 170         episode_description = video_info['description']
 171         episode_duration = video_info.get('duration')
 172
 173         entries = []
 174         for part_num, segment_id in enumerate(segment_ids):
 175             segement_info = self._extract_cvp_info(
 176                 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
 177                 segment_id, {
 178                     'secure': {
 179                         'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
 180                         'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
 181                     },
 182                 })
 183             segment_title = '%s - %s' % (show_title, episode_title)
 184             if len(segment_ids) > 1:
 185                 segment_title += ' Part %d' % (part_num + 1)
 186             segement_info.update({
 187                 'id': segment_id,
 188                 'title': segment_title,
 189                 'description': episode_description,
 190             })
 191             entries.append(segement_info)
 192
 193         return {
 194             '_type': 'playlist',
 195             'id': episode_id,
 196             'display_id': episode_path,
 197             'entries': entries,
 198             'title': '%s - %s' % (show_title, episode_title),
 199             'description': episode_description,
 200             'duration': episode_duration
 201         }