git.bitcoin.ninja 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 .common import InfoExtractor
   7 from ..utils import (
   8     determine_ext,
   9     ExtractorError,
  10     float_or_none,
  11     xpath_text,
  12 )
  13
  14
  15 class AdultSwimIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
  17
  18     _TESTS = [{
  19         'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
  20         'playlist': [
  21             {
  22                 'md5': '247572debc75c7652f253c8daa51a14d',
  23                 'info_dict': {
  24                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
  25                     'ext': 'flv',
  26                     'title': 'Rick and Morty - Pilot Part 1',
  27                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  28                 },
  29             },
  30             {
  31                 'md5': '77b0e037a4b20ec6b98671c4c379f48d',
  32                 'info_dict': {
  33                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
  34                     'ext': 'flv',
  35                     'title': 'Rick and Morty - Pilot Part 4',
  36                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  37                 },
  38             },
  39         ],
  40         'info_dict': {
  41             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
  42             'title': 'Rick and Morty - Pilot',
  43             'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  44         },
  45         'skip': 'This video is only available for registered users',
  46     }, {
  47         'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
  48         'playlist': [
  49             {
  50                 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
  51                 'info_dict': {
  52                     'id': '-t8CamQlQ2aYZ49ItZCFog-0',
  53                     'ext': 'flv',
  54                     'title': 'American Dad - Putting Francine Out of Business',
  55                     'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  56                 },
  57             }
  58         ],
  59         'info_dict': {
  60             'id': '-t8CamQlQ2aYZ49ItZCFog',
  61             'title': 'American Dad - Putting Francine Out of Business',
  62             'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  63         },
  64     }, {
  65         'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
  66         'playlist': [
  67             {
  68                 'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
  69                 'info_dict': {
  70                     'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
  71                     'ext': 'mp4',
  72                     'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
  73                     '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',
  74                 },
  75             }
  76         ],
  77         'info_dict': {
  78             'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
  79             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
  80             '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',
  81         },
  82         'params': {
  83             # m3u8 download
  84             'skip_download': True,
  85         }
  86     }]
  87
  88     @staticmethod
  89     def find_video_info(collection, slug):
  90         for video in collection.get('videos'):
  91             if video.get('slug') == slug:
  92                 return video
  93
  94     @staticmethod
  95     def find_collection_by_linkURL(collections, linkURL):
  96         for collection in collections:
  97             if collection.get('linkURL') == linkURL:
  98                 return collection
  99
 100     @staticmethod
 101     def find_collection_containing_video(collections, slug):
 102         for collection in collections:
 103             for video in collection.get('videos'):
 104                 if video.get('slug') == slug:
 105                     return collection, video
 106         return None, None
 107
 108     def _real_extract(self, url):
 109         mobj = re.match(self._VALID_URL, url)
 110         show_path = mobj.group('show_path')
 111         episode_path = mobj.group('episode_path')
 112         is_playlist = True if mobj.group('is_playlist') else False
 113
 114         webpage = self._download_webpage(url, episode_path)
 115
 116         # Extract the value of `bootstrappedData` from the Javascript in the page.
 117         bootstrapped_data = self._parse_json(self._search_regex(
 118             r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
 119
 120         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
 121         # NOTE: We are only downloading one video (the current one) not the playlist
 122         if is_playlist:
 123             collections = bootstrapped_data['playlists']['collections']
 124             collection = self.find_collection_by_linkURL(collections, show_path)
 125             video_info = self.find_video_info(collection, episode_path)
 126
 127             show_title = video_info['showTitle']
 128             segment_ids = [video_info['videoPlaybackID']]
 129         else:
 130             collections = bootstrapped_data['show']['collections']
 131             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 132             # Video wasn't found in the collections, let's try `slugged_video`.
 133             if video_info is None:
 134                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
 135                     video_info = bootstrapped_data['slugged_video']
 136                 else:
 137                     raise ExtractorError('Unable to find video info')
 138
 139             show = bootstrapped_data['show']
 140             show_title = show['title']
 141             stream = video_info.get('stream')
 142             clips = [stream] if stream else video_info.get('clips')
 143             if not clips:
 144                 raise ExtractorError(
 145                     'This video is only available via cable service provider subscription that'
 146                     ' is not currently supported. You may want to use --cookies.'
 147                     if video_info.get('auth') is True else 'Unable to find stream or clips',
 148                     expected=True)
 149             segment_ids = [clip['videoPlaybackID'] for clip in clips]
 150
 151         episode_id = video_info['id']
 152         episode_title = video_info['title']
 153         episode_description = video_info['description']
 154         episode_duration = video_info.get('duration')
 155
 156         entries = []
 157         for part_num, segment_id in enumerate(segment_ids):
 158             segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
 159
 160             segment_title = '%s - %s' % (show_title, episode_title)
 161             if len(segment_ids) > 1:
 162                 segment_title += ' Part %d' % (part_num + 1)
 163
 164             idoc = self._download_xml(
 165                 segment_url, segment_title,
 166                 'Downloading segment information', 'Unable to download segment information')
 167
 168             segment_duration = float_or_none(
 169                 xpath_text(idoc, './/trt', 'segment duration').strip())
 170
 171             formats = []
 172             file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
 173
 174             unique_urls = []
 175             unique_file_els = []
 176             for file_el in file_els:
 177                 media_url = file_el.text
 178                 if not media_url or determine_ext(media_url) == 'f4m':
 179                     continue
 180                 if file_el.text not in unique_urls:
 181                     unique_urls.append(file_el.text)
 182                     unique_file_els.append(file_el)
 183
 184             for file_el in unique_file_els:
 185                 bitrate = file_el.attrib.get('bitrate')
 186                 ftype = file_el.attrib.get('type')
 187                 media_url = file_el.text
 188                 if determine_ext(media_url) == 'm3u8':
 189                     formats.extend(self._extract_m3u8_formats(
 190                         media_url, segment_title, 'mp4', preference=0,
 191                         m3u8_id='hls', fatal=False))
 192                 else:
 193                     formats.append({
 194                         'format_id': '%s_%s' % (bitrate, ftype),
 195                         'url': file_el.text.strip(),
 196                         # The bitrate may not be a number (for example: 'iphone')
 197                         'tbr': int(bitrate) if bitrate.isdigit() else None,
 198                     })
 199
 200             self._sort_formats(formats)
 201
 202             entries.append({
 203                 'id': segment_id,
 204                 'title': segment_title,
 205                 'formats': formats,
 206                 'duration': segment_duration,
 207                 'description': episode_description
 208             })
 209
 210         return {
 211             '_type': 'playlist',
 212             'id': episode_id,
 213             'display_id': episode_path,
 214             'entries': entries,
 215             'title': '%s - %s' % (show_title, episode_title),
 216             'description': episode_description,
 217             'duration': episode_duration
 218         }