_ 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
   8 class AdultSwimIE(InfoExtractor):
   9     _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$'
  10     _TEST = {
  11         'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title',
  12         'md5': '4a90c63a07537ec9383175b330dfeab4',
  13         'info_dict': {
  14             'id': '8a250ba1450996e901453d7e9caf02f3',
  15             'title': 'Rick and Morty Close Rick-Counters of the Rick Kind',
  16             'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
  17         }
  18     }
  19
  20     _available_formats = ['150', '640', '3500']
  21
  22     _video_extensions = {
  23         '3500': 'flv',
  24         '640': 'mp4',
  25         '150': 'mp4',
  26         'ipad': 'm3u8',
  27         'iphone': 'm3u8'
  28     }
  29     _video_dimensions = {
  30         '3500': (1280, 720),
  31         '640': (480, 270),
  32         '150': (320, 180)
  33     }
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_path = mobj.group('path')
  38
  39         webpage = self._download_webpage(url, video_path)
  40         episode_id = self._html_search_regex(r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>', webpage, 'episode_id')
  41         title = self._html_search_regex(r'<meta property="og:title" content="\s*(.*?)\s*"\s*/?\s*>', webpage, 'title')
  42
  43         index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id
  44         idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index')
  45
  46         episode_el = idoc.find('.//episode')
  47         show_title = episode_el.attrib.get('collectionTitle')
  48         episode_title = episode_el.attrib.get('title')
  49         thumbnail = episode_el.attrib.get('thumbnailUrl')
  50         description = episode_el.find('./description').text.strip()
  51
  52         entries = []
  53         segment_els = episode_el.findall('./segments/segment')
  54
  55         for part_num, segment_el in enumerate(segment_els):
  56             segment_id = segment_el.attrib.get('id')
  57             segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1)
  58             thumbnail = segment_el.attrib.get('thumbnailUrl')
  59             duration = segment_el.attrib.get('duration')
  60
  61             segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
  62             idoc = self._download_xml(segment_url, segment_title, 'Downloading segment information', 'Unable to download segment information')
  63
  64             formats = []
  65             file_els = idoc.findall('.//files/file')
  66
  67             for file_el in file_els:
  68                 bitrate = file_el.attrib.get('bitrate')
  69                 type = file_el.attrib.get('type')
  70                 width, height = self._video_dimensions.get(bitrate, (None, None))
  71                 formats.append({
  72                     'format_id': '%s-%s' % (bitrate, type),
  73                     'url': file_el.text,
  74                     'ext': self._video_extensions.get(bitrate, 'mp4'),
  75                     'tbr': bitrate,
  76                     'height': height,
  77                     'width': width
  78                 })
  79
  80             self._sort_formats(formats)
  81
  82             entries.append({
  83                 'id': segment_id,
  84                 'title': segment_title,
  85                 'formats': formats,
  86                 'uploader': show_title,
  87                 'thumbnail': thumbnail,
  88                 'duration': duration,
  89                 'description': description
  90             })
  91
  92         return {
  93             '_type': 'playlist',
  94             'id': episode_id,
  95             'display_id': video_path,
  96             'entries': entries,
  97             'title': '%s %s' % (show_title, episode_title),
  98             'description': description,
  99             'thumbnail': thumbnail
 100         }