Raphaël G. Git Repositories - youtubedl/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': 'flv',
  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     }]
  83
  84     @staticmethod
  85     def find_video_info(collection, slug):
  86         for video in collection.get('videos'):
  87             if video.get('slug') == slug:
  88                 return video
  89
  90     @staticmethod
  91     def find_collection_by_linkURL(collections, linkURL):
  92         for collection in collections:
  93             if collection.get('linkURL') == linkURL:
  94                 return collection
  95
  96     @staticmethod
  97     def find_collection_containing_video(collections, slug):
  98         for collection in collections:
  99             for video in collection.get('videos'):
 100                 if video.get('slug') == slug:
 101                     return collection, video
 102         return None, None
 103
 104     def _real_extract(self, url):
 105         mobj = re.match(self._VALID_URL, url)
 106         show_path = mobj.group('show_path')
 107         episode_path = mobj.group('episode_path')
 108         is_playlist = True if mobj.group('is_playlist') else False
 109
 110         webpage = self._download_webpage(url, episode_path)
 111
 112         # Extract the value of `bootstrappedData` from the Javascript in the page.
 113         bootstrapped_data = self._parse_json(self._search_regex(
 114             r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
 115
 116         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
 117         # NOTE: We are only downloading one video (the current one) not the playlist
 118         if is_playlist:
 119             collections = bootstrapped_data['playlists']['collections']
 120             collection = self.find_collection_by_linkURL(collections, show_path)
 121             video_info = self.find_video_info(collection, episode_path)
 122
 123             show_title = video_info['showTitle']
 124             segment_ids = [video_info['videoPlaybackID']]
 125         else:
 126             collections = bootstrapped_data['show']['collections']
 127             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 128             # Video wasn't found in the collections, let's try `slugged_video`.
 129             if video_info is None:
 130                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
 131                     video_info = bootstrapped_data['slugged_video']
 132                 else:
 133                     raise ExtractorError('Unable to find video info')
 134
 135             show = bootstrapped_data['show']
 136             show_title = show['title']
 137             stream = video_info.get('stream')
 138             clips = [stream] if stream else video_info.get('clips')
 139             if not clips:
 140                 raise ExtractorError(
 141                     'This video is only available via cable service provider subscription that'
 142                     ' is not currently supported. You may want to use --cookies.'
 143                     if video_info.get('auth') is True else 'Unable to find stream or clips',
 144                     expected=True)
 145             segment_ids = [clip['videoPlaybackID'] for clip in clips]
 146
 147         episode_id = video_info['id']
 148         episode_title = video_info['title']
 149         episode_description = video_info['description']
 150         episode_duration = video_info.get('duration')
 151
 152         entries = []
 153         for part_num, segment_id in enumerate(segment_ids):
 154             segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
 155
 156             segment_title = '%s - %s' % (show_title, episode_title)
 157             if len(segment_ids) > 1:
 158                 segment_title += ' Part %d' % (part_num + 1)
 159
 160             idoc = self._download_xml(
 161                 segment_url, segment_title,
 162                 'Downloading segment information', 'Unable to download segment information')
 163
 164             segment_duration = float_or_none(
 165                 xpath_text(idoc, './/trt', 'segment duration').strip())
 166
 167             formats = []
 168             file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
 169
 170             unique_urls = []
 171             unique_file_els = []
 172             for file_el in file_els:
 173                 media_url = file_el.text
 174                 if not media_url or determine_ext(media_url) == 'f4m':
 175                     continue
 176                 if file_el.text not in unique_urls:
 177                     unique_urls.append(file_el.text)
 178                     unique_file_els.append(file_el)
 179
 180             for file_el in unique_file_els:
 181                 bitrate = file_el.attrib.get('bitrate')
 182                 ftype = file_el.attrib.get('type')
 183                 media_url = file_el.text
 184                 if determine_ext(media_url) == 'm3u8':
 185                     formats.extend(self._extract_m3u8_formats(
 186                         media_url, segment_title, 'mp4', preference=0, m3u8_id='hls'))
 187                 else:
 188                     formats.append({
 189                         'format_id': '%s_%s' % (bitrate, ftype),
 190                         'url': file_el.text.strip(),
 191                         # The bitrate may not be a number (for example: 'iphone')
 192                         'tbr': int(bitrate) if bitrate.isdigit() else None,
 193                     })
 194
 195             self._sort_formats(formats)
 196
 197             entries.append({
 198                 'id': segment_id,
 199                 'title': segment_title,
 200                 'formats': formats,
 201                 'duration': segment_duration,
 202                 'description': episode_description
 203             })
 204
 205         return {
 206             '_type': 'playlist',
 207             'id': episode_id,
 208             'display_id': episode_path,
 209             'entries': entries,
 210             'title': '%s - %s' % (show_title, episode_title),
 211             'description': episode_description,
 212             'duration': episode_duration
 213         }