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     ExtractorError,
   9     float_or_none,
  10     xpath_text,
  11 )
  12
  13
  14 class AdultSwimIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
  16
  17     _TESTS = [{
  18         'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
  19         'playlist': [
  20             {
  21                 'md5': '247572debc75c7652f253c8daa51a14d',
  22                 'info_dict': {
  23                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
  24                     'ext': 'flv',
  25                     'title': 'Rick and Morty - Pilot Part 1',
  26                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  27                 },
  28             },
  29             {
  30                 'md5': '77b0e037a4b20ec6b98671c4c379f48d',
  31                 'info_dict': {
  32                     'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
  33                     'ext': 'flv',
  34                     'title': 'Rick and Morty - Pilot Part 4',
  35                     'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  36                 },
  37             },
  38         ],
  39         'info_dict': {
  40             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
  41             'title': 'Rick and Morty - Pilot',
  42             'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  43         }
  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': 'flv',
  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     }]
  81
  82     @staticmethod
  83     def find_video_info(collection, slug):
  84         for video in collection.get('videos'):
  85             if video.get('slug') == slug:
  86                 return video
  87
  88     @staticmethod
  89     def find_collection_by_linkURL(collections, linkURL):
  90         for collection in collections:
  91             if collection.get('linkURL') == linkURL:
  92                 return collection
  93
  94     @staticmethod
  95     def find_collection_containing_video(collections, slug):
  96         for collection in collections:
  97             for video in collection.get('videos'):
  98                 if video.get('slug') == slug:
  99                     return collection, video
 100         return None, None
 101
 102     def _real_extract(self, url):
 103         mobj = re.match(self._VALID_URL, url)
 104         show_path = mobj.group('show_path')
 105         episode_path = mobj.group('episode_path')
 106         is_playlist = True if mobj.group('is_playlist') else False
 107
 108         webpage = self._download_webpage(url, episode_path)
 109
 110         # Extract the value of `bootstrappedData` from the Javascript in the page.
 111         bootstrapped_data = self._parse_json(self._search_regex(
 112             r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
 113
 114         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
 115         # NOTE: We are only downloading one video (the current one) not the playlist
 116         if is_playlist:
 117             collections = bootstrapped_data['playlists']['collections']
 118             collection = self.find_collection_by_linkURL(collections, show_path)
 119             video_info = self.find_video_info(collection, episode_path)
 120
 121             show_title = video_info['showTitle']
 122             segment_ids = [video_info['videoPlaybackID']]
 123         else:
 124             collections = bootstrapped_data['show']['collections']
 125             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 126
 127             # Video wasn't found in the collections, let's try `slugged_video`.
 128             if video_info is None:
 129                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
 130                     video_info = bootstrapped_data['slugged_video']
 131                 else:
 132                     raise ExtractorError('Unable to find video info')
 133
 134             show = bootstrapped_data['show']
 135             show_title = show['title']
 136             segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
 137
 138         episode_id = video_info['id']
 139         episode_title = video_info['title']
 140         episode_description = video_info['description']
 141         episode_duration = video_info.get('duration')
 142
 143         entries = []
 144         for part_num, segment_id in enumerate(segment_ids):
 145             segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
 146
 147             segment_title = '%s - %s' % (show_title, episode_title)
 148             if len(segment_ids) > 1:
 149                 segment_title += ' Part %d' % (part_num + 1)
 150
 151             idoc = self._download_xml(
 152                 segment_url, segment_title,
 153                 'Downloading segment information', 'Unable to download segment information')
 154
 155             segment_duration = float_or_none(
 156                 xpath_text(idoc, './/trt', 'segment duration').strip())
 157
 158             formats = []
 159             file_els = idoc.findall('.//files/file')
 160
 161             for file_el in file_els:
 162                 bitrate = file_el.attrib.get('bitrate')
 163                 ftype = file_el.attrib.get('type')
 164
 165                 formats.append({
 166                     'format_id': '%s_%s' % (bitrate, ftype),
 167                     'url': file_el.text.strip(),
 168                     # The bitrate may not be a number (for example: 'iphone')
 169                     'tbr': int(bitrate) if bitrate.isdigit() else None,
 170                     'quality': 1 if ftype == 'hd' else -1
 171                 })
 172
 173             self._sort_formats(formats)
 174
 175             entries.append({
 176                 'id': segment_id,
 177                 'title': segment_title,
 178                 'formats': formats,
 179                 'duration': segment_duration,
 180                 'description': episode_description
 181             })
 182
 183         return {
 184             '_type': 'playlist',
 185             'id': episode_id,
 186             'display_id': episode_path,
 187             'entries': entries,
 188             'title': '%s - %s' % (show_title, episode_title),
 189             'description': episode_description,
 190             'duration': episode_duration
 191         }