youtube_dl/extractor/adultswim.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10 )
  11
  12
  13 class AdultSwimIE(InfoExtractor):
  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             'title': 'Rick and Morty - Pilot',
  40             'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
  41         }
  42     }, {
  43         'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
  44         'playlist': [
  45             {
  46                 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
  47                 'info_dict': {
  48                     'id': '-t8CamQlQ2aYZ49ItZCFog-0',
  49                     'ext': 'flv',
  50                     'title': 'American Dad - Putting Francine Out of Business',
  51                     'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  52                 },
  53             }
  54         ],
  55         'info_dict': {
  56             'title': 'American Dad - Putting Francine Out of Business',
  57             'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  58         },
  59     }]
  60
  61     @staticmethod
  62     def find_video_info(collection, slug):
  63         for video in collection.get('videos'):
  64             if video.get('slug') == slug:
  65                 return video
  66
  67     @staticmethod
  68     def find_collection_by_linkURL(collections, linkURL):
  69         for collection in collections:
  70             if collection.get('linkURL') == linkURL:
  71                 return collection
  72
  73     @staticmethod
  74     def find_collection_containing_video(collections, slug):
  75         for collection in collections:
  76             for video in collection.get('videos'):
  77                 if video.get('slug') == slug:
  78                     return collection, video
  79
  80     def _real_extract(self, url):
  81         mobj = re.match(self._VALID_URL, url)
  82         show_path = mobj.group('show_path')
  83         episode_path = mobj.group('episode_path')
  84         is_playlist = True if mobj.group('is_playlist') else False
  85
  86         webpage = self._download_webpage(url, episode_path)
  87
  88         # Extract the value of `bootstrappedData` from the Javascript in the page.
  89         bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
  90
  91         try:
  92             bootstrappedData = json.loads(bootstrappedDataJS)
  93         except ValueError as ve:
  94             errmsg = '%s: Failed to parse JSON ' % episode_path
  95             raise ExtractorError(errmsg, cause=ve)
  96
  97         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
  98         # NOTE: We are only downloading one video (the current one) not the playlist
  99         if is_playlist:
 100             collections = bootstrappedData['playlists']['collections']
 101             collection = self.find_collection_by_linkURL(collections, show_path)
 102             video_info = self.find_video_info(collection, episode_path)
 103
 104             show_title = video_info['showTitle']
 105             segment_ids = [video_info['videoPlaybackID']]
 106         else:
 107             collections = bootstrappedData['show']['collections']
 108             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 109
 110             show = bootstrappedData['show']
 111             show_title = show['title']
 112             segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
 113
 114         episode_id = video_info['id']
 115         episode_title = video_info['title']
 116         episode_description = video_info['description']
 117         episode_duration = video_info.get('duration')
 118
 119         entries = []
 120         for part_num, segment_id in enumerate(segment_ids):
 121             segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
 122
 123             segment_title = '%s - %s' % (show_title, episode_title)
 124             if len(segment_ids) > 1:
 125                 segment_title += ' Part %d' % (part_num + 1)
 126
 127             idoc = self._download_xml(
 128                 segment_url, segment_title,
 129                 'Downloading segment information', 'Unable to download segment information')
 130
 131             segment_duration = idoc.find('.//trt').text.strip()
 132
 133             formats = []
 134             file_els = idoc.findall('.//files/file')
 135
 136             for file_el in file_els:
 137                 bitrate = file_el.attrib.get('bitrate')
 138                 ftype = file_el.attrib.get('type')
 139
 140                 formats.append({
 141                     'format_id': '%s_%s' % (bitrate, ftype),
 142                     'url': file_el.text.strip(),
 143                     # The bitrate may not be a number (for example: 'iphone')
 144                     'tbr': int(bitrate) if bitrate.isdigit() else None,
 145                     'quality': 1 if ftype == 'hd' else -1
 146                 })
 147
 148             self._sort_formats(formats)
 149
 150             entries.append({
 151                 'id': segment_id,
 152                 'title': segment_title,
 153                 'formats': formats,
 154                 'duration': segment_duration,
 155                 'description': episode_description
 156             })
 157
 158         return {
 159             '_type': 'playlist',
 160             'id': episode_id,
 161             'display_id': episode_path,
 162             'entries': entries,
 163             'title': '%s - %s' % (show_title, episode_title),
 164             'description': episode_description,
 165             'duration': episode_duration
 166         }