_ 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': '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                 if video.get('auth'):
  89                     raise ExtractorError('This video is only available for registered users', expected=True)
  90                 else:
  91                     return video
  92
  93     @staticmethod
  94     def find_collection_by_linkURL(collections, linkURL):
  95         for collection in collections:
  96             if collection.get('linkURL') == linkURL:
  97                 return collection
  98
  99     @staticmethod
 100     def find_collection_containing_video(collections, slug):
 101         for collection in collections:
 102             for video in collection.get('videos'):
 103                 if video.get('slug') == slug:
 104                     if video.get('auth'):
 105                         raise ExtractorError('This video is only available for registered users', expected=True)
 106                     else:
 107                         return collection, video
 108         return None, None
 109
 110     def _real_extract(self, url):
 111         mobj = re.match(self._VALID_URL, url)
 112         show_path = mobj.group('show_path')
 113         episode_path = mobj.group('episode_path')
 114         is_playlist = True if mobj.group('is_playlist') else False
 115
 116         webpage = self._download_webpage(url, episode_path)
 117
 118         # Extract the value of `bootstrappedData` from the Javascript in the page.
 119         bootstrapped_data = self._parse_json(self._search_regex(
 120             r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
 121
 122         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
 123         # NOTE: We are only downloading one video (the current one) not the playlist
 124         if is_playlist:
 125             collections = bootstrapped_data['playlists']['collections']
 126             collection = self.find_collection_by_linkURL(collections, show_path)
 127             video_info = self.find_video_info(collection, episode_path)
 128
 129             show_title = video_info['showTitle']
 130             segment_ids = [video_info['videoPlaybackID']]
 131         else:
 132             collections = bootstrapped_data['show']['collections']
 133             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 134             # Video wasn't found in the collections, let's try `slugged_video`.
 135             if video_info is None:
 136                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
 137                     video_info = bootstrapped_data['slugged_video']
 138                     if video_info.get('auth'):
 139                         raise ExtractorError('This video is only available for registered users', expected=True)
 140                 else:
 141                     raise ExtractorError('Unable to find video info')
 142
 143             show = bootstrapped_data['show']
 144             show_title = show['title']
 145             stream = video_info.get('stream')
 146             clips = [stream] if stream else video_info['clips']
 147             segment_ids = [clip['videoPlaybackID'] for clip in clips]
 148
 149         episode_id = video_info['id']
 150         episode_title = video_info['title']
 151         episode_description = video_info['description']
 152         episode_duration = video_info.get('duration')
 153
 154         entries = []
 155         for part_num, segment_id in enumerate(segment_ids):
 156             segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
 157
 158             segment_title = '%s - %s' % (show_title, episode_title)
 159             if len(segment_ids) > 1:
 160                 segment_title += ' Part %d' % (part_num + 1)
 161
 162             idoc = self._download_xml(
 163                 segment_url, segment_title,
 164                 'Downloading segment information', 'Unable to download segment information')
 165
 166             segment_duration = float_or_none(
 167                 xpath_text(idoc, './/trt', 'segment duration').strip())
 168
 169             formats = []
 170             file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
 171
 172             unique_urls = []
 173             unique_file_els = []
 174             for file_el in file_els:
 175                 media_url = file_el.text
 176                 if not media_url or determine_ext(media_url) == 'f4m':
 177                     continue
 178                 if file_el.text not in unique_urls:
 179                     unique_urls.append(file_el.text)
 180                     unique_file_els.append(file_el)
 181
 182             for file_el in unique_file_els:
 183                 bitrate = file_el.attrib.get('bitrate')
 184                 ftype = file_el.attrib.get('type')
 185                 media_url = file_el.text
 186                 if determine_ext(media_url) == 'm3u8':
 187                     formats.extend(self._extract_m3u8_formats(
 188                         media_url, segment_title, 'mp4', 'm3u8_native', preference=0, m3u8_id='hls'))
 189                 else:
 190                     formats.append({
 191                         'format_id': '%s_%s' % (bitrate, ftype),
 192                         'url': file_el.text.strip(),
 193                         # The bitrate may not be a number (for example: 'iphone')
 194                         'tbr': int(bitrate) if bitrate.isdigit() else None,
 195                     })
 196
 197             self._sort_formats(formats)
 198
 199             entries.append({
 200                 'id': segment_id,
 201                 'title': segment_title,
 202                 'formats': formats,
 203                 'duration': segment_duration,
 204                 'description': episode_description
 205             })
 206
 207         return {
 208             '_type': 'playlist',
 209             'id': episode_id,
 210             'display_id': episode_path,
 211             'entries': entries,
 212             'title': '%s - %s' % (show_title, episode_title),
 213             'description': episode_description,
 214             'duration': episode_duration
 215         }