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