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 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     xpath_text,
  11     float_or_none,
  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     }, {
  46         'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
  47         'playlist': [
  48             {
  49                 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
  50                 'info_dict': {
  51                     'id': '-t8CamQlQ2aYZ49ItZCFog-0',
  52                     'ext': 'flv',
  53                     'title': 'American Dad - Putting Francine Out of Business',
  54                     'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  55                 },
  56             }
  57         ],
  58         'info_dict': {
  59             'id': '-t8CamQlQ2aYZ49ItZCFog',
  60             'title': 'American Dad - Putting Francine Out of Business',
  61             'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
  62         },
  63     }]
  64
  65     @staticmethod
  66     def find_video_info(collection, slug):
  67         for video in collection.get('videos'):
  68             if video.get('slug') == slug:
  69                 return video
  70
  71     @staticmethod
  72     def find_collection_by_linkURL(collections, linkURL):
  73         for collection in collections:
  74             if collection.get('linkURL') == linkURL:
  75                 return collection
  76
  77     @staticmethod
  78     def find_collection_containing_video(collections, slug):
  79         for collection in collections:
  80             for video in collection.get('videos'):
  81                 if video.get('slug') == slug:
  82                     return collection, video
  83
  84     def _real_extract(self, url):
  85         mobj = re.match(self._VALID_URL, url)
  86         show_path = mobj.group('show_path')
  87         episode_path = mobj.group('episode_path')
  88         is_playlist = True if mobj.group('is_playlist') else False
  89
  90         webpage = self._download_webpage(url, episode_path)
  91
  92         # Extract the value of `bootstrappedData` from the Javascript in the page.
  93         bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
  94
  95         try:
  96             bootstrappedData = json.loads(bootstrappedDataJS)
  97         except ValueError as ve:
  98             errmsg = '%s: Failed to parse JSON ' % episode_path
  99             raise ExtractorError(errmsg, cause=ve)
 100
 101         # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
 102         # NOTE: We are only downloading one video (the current one) not the playlist
 103         if is_playlist:
 104             collections = bootstrappedData['playlists']['collections']
 105             collection = self.find_collection_by_linkURL(collections, show_path)
 106             video_info = self.find_video_info(collection, episode_path)
 107
 108             show_title = video_info['showTitle']
 109             segment_ids = [video_info['videoPlaybackID']]
 110         else:
 111             collections = bootstrappedData['show']['collections']
 112             collection, video_info = self.find_collection_containing_video(collections, episode_path)
 113
 114             show = bootstrappedData['show']
 115             show_title = show['title']
 116             segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
 117
 118         episode_id = video_info['id']
 119         episode_title = video_info['title']
 120         episode_description = video_info['description']
 121         episode_duration = video_info.get('duration')
 122
 123         entries = []
 124         for part_num, segment_id in enumerate(segment_ids):
 125             segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
 126
 127             segment_title = '%s - %s' % (show_title, episode_title)
 128             if len(segment_ids) > 1:
 129                 segment_title += ' Part %d' % (part_num + 1)
 130
 131             idoc = self._download_xml(
 132                 segment_url, segment_title,
 133                 'Downloading segment information', 'Unable to download segment information')
 134
 135             segment_duration = float_or_none(
 136                 xpath_text(idoc, './/trt', 'segment duration').strip())
 137
 138             formats = []
 139             file_els = idoc.findall('.//files/file')
 140
 141             for file_el in file_els:
 142                 bitrate = file_el.attrib.get('bitrate')
 143                 ftype = file_el.attrib.get('type')
 144
 145                 formats.append({
 146                     'format_id': '%s_%s' % (bitrate, ftype),
 147                     'url': file_el.text.strip(),
 148                     # The bitrate may not be a number (for example: 'iphone')
 149                     'tbr': int(bitrate) if bitrate.isdigit() else None,
 150                     'quality': 1 if ftype == 'hd' else -1
 151                 })
 152
 153             self._sort_formats(formats)
 154
 155             entries.append({
 156                 'id': segment_id,
 157                 'title': segment_title,
 158                 'formats': formats,
 159                 'duration': segment_duration,
 160                 'description': episode_description
 161             })
 162
 163         return {
 164             '_type': 'playlist',
 165             'id': episode_id,
 166             'display_id': episode_path,
 167             'entries': entries,
 168             'title': '%s - %s' % (show_title, episode_title),
 169             'description': episode_description,
 170             'duration': episode_duration
 171         }