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 (
   8     ExtractorError,
   9     int_or_none,
  10 )
  11
  12
  13 class AdultSwimIE(TurnerBaseIE):
  14     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
  15
  16     _TESTS = [{
  17         'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
  18         'playlist': [
  19             {
  20                 'md5': '247572debc75c7652f253c8daa51a14d',
  21                 'info_dict': {
  22                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
  23                     'ext': 'flv',
  24                     'title': 'Rick and Morty - Pilot Part 1',
  25                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  26                 },
  27             },
  28             {
  29                 'md5': '77b0e037a4b20ec6b98671c4c379f48d',
  30                 'info_dict': {
  31                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
  32                     'ext': 'flv',
  33                     'title': 'Rick and Morty - Pilot Part 4',
  34                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  35                 },
  36             },
  37         ],
  38         'info_dict': {
  39             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
  40             'title': 'Rick and Morty - Pilot',
  41             'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  42         },
  43         'skip': 'This video is only available for registered users',
  44     }, {
  45         'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
  46         'playlist': [
  47             {
  48                 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
  49                 'info_dict': {
  50                     'id': '-t8CamQlQ2aYZ49ItZCFog-0',
  51                     'ext': 'flv',
  52                     'title': 'American Dad - Putting Francine Out of Business',
  53                     'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  54                 },
  55             }
  56         ],
  57         'info_dict': {
  58             'id': '-t8CamQlQ2aYZ49ItZCFog',
  59             'title': 'American Dad - Putting Francine Out of Business',
  60             'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  61         },
  62     }, {
  63         'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
  64         'playlist': [
  65             {
  66                 'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
  67                 'info_dict': {
  68                     'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
  69                     'ext': 'mp4',
  70                     'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
  71                     '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',
  72                 },
  73             }
  74         ],
  75         'info_dict': {
  76             'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
  77             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
  78             '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',
  79         },
  80         'params': {
  81             # m3u8 download
  82             'skip_download': True,
  83         }
  84     }, {
  85         # heroMetadata.trailer
  86         'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
  87         'info_dict': {
  88             'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
  89             'ext': 'mp4',
  90             'title': 'Decker - Inside Decker: A New Hero',
  91             'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
  92             'duration': 249.008,
  93         },
  94         'params': {
  95             # m3u8 download
  96             'skip_download': True,
  97         },
  98         'expected_warnings': ['Unable to download f4m manifest'],
  99     }]
 100
 101     @staticmethod
 102     def find_video_info(collection, slug):
 103         for video in collection.get('videos'):
 104             if video.get('slug') == slug:
 105                 return video
 106
 107     @staticmethod
 108     def find_collection_by_linkURL(collections, linkURL):
 109         for collection in collections:
 110             if collection.get('linkURL') == linkURL:
 111                 return collection
 112
 113     @staticmethod
 114     def find_collection_containing_video(collections, slug):
 115         for collection in collections:
 116             for video in collection.get('videos'):
 117                 if video.get('slug') == slug:
 118                     return collection, video
 119         return None, None
 120
 121     def _real_extract(self, url):
 122         mobj = re.match(self._VALID_URL, url)
 123         show_path = mobj.group('show_path')
 124         episode_path = mobj.group('episode_path')
 125         is_playlist = True if mobj.group('is_playlist') else False
 126
 127         webpage = self._download_webpage(url, episode_path)
 128
 129         # Extract the value of `bootstrappedData` from the Javascript in the page.
 130         bootstrapped_data = self._parse_json(self._search_regex(
 131             r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
 132
 133         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
 134         # NOTE: We are only downloading one video (the current one) not the playlist
 135         if is_playlist:
 136             collections = bootstrapped_data['playlists']['collections']
 137             collection = self.find_collection_by_linkURL(collections, show_path)
 138             video_info = self.find_video_info(collection, episode_path)
 139
 140             show_title = video_info['showTitle']
 141             segment_ids = [video_info['videoPlaybackID']]
 142         else:
 143             collections = bootstrapped_data['show']['collections']
 144             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 145             # Video wasn't found in the collections, let's try `slugged_video`.
 146             if video_info is None:
 147                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
 148                     video_info = bootstrapped_data['slugged_video']
 149             if not video_info:
 150                 video_info = bootstrapped_data.get(
 151                     'heroMetadata', {}).get('trailer', {}).get('video')
 152             if not video_info:
 153                 video_info = bootstrapped_data.get('onlineOriginals', [None])[0]
 154             if not video_info:
 155                 raise ExtractorError('Unable to find video info')
 156
 157             show = bootstrapped_data['show']
 158             show_title = show['title']
 159             stream = video_info.get('stream')
 160             if stream and stream.get('videoPlaybackID'):
 161                 segment_ids = [stream['videoPlaybackID']]
 162             elif video_info.get('clips'):
 163                 segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
 164             elif video_info.get('videoPlaybackID'):
 165                 segment_ids = [video_info['videoPlaybackID']]
 166             else:
 167                 if video_info.get('auth') is True:
 168                     raise ExtractorError(
 169                         'This video is only available via cable service provider subscription that'
 170                         ' is not currently supported. You may want to use --cookies.', expected=True)
 171                 else:
 172                     raise ExtractorError('Unable to find stream or clips')
 173
 174         episode_id = video_info['id']
 175         episode_title = video_info['title']
 176         episode_description = video_info.get('description')
 177         episode_duration = int_or_none(video_info.get('duration'))
 178         view_count = int_or_none(video_info.get('views'))
 179
 180         entries = []
 181         for part_num, segment_id in enumerate(segment_ids):
 182             segement_info = self._extract_cvp_info(
 183                 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
 184                 segment_id, {
 185                     'secure': {
 186                         'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
 187                         'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
 188                     },
 189                 })
 190             segment_title = '%s - %s' % (show_title, episode_title)
 191             if len(segment_ids) > 1:
 192                 segment_title += ' Part %d' % (part_num + 1)
 193             segement_info.update({
 194                 'id': segment_id,
 195                 'title': segment_title,
 196                 'description': episode_description,
 197             })
 198             entries.append(segement_info)
 199
 200         return {
 201             '_type': 'playlist',
 202             'id': episode_id,
 203             'display_id': episode_path,
 204             'entries': entries,
 205             'title': '%s - %s' % (show_title, episode_title),
 206             'description': episode_description,
 207             'duration': episode_duration,
 208             'view_count': view_count,
 209         }