youtube_dl/extractor/crackle.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals, division
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_HTTPError,
  10 )
  11 from ..utils import (
  12     determine_ext,
  13     float_or_none,
  14     int_or_none,
  15     parse_age_limit,
  16     parse_duration,
  17     ExtractorError
  18 )
  19
  20
  21 class CrackleIE(InfoExtractor):
  22     _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
  23     _TEST = {
  24         # geo restricted to CA
  25         'url': 'https://www.crackle.com/andromeda/2502343',
  26         'info_dict': {
  27             'id': '2502343',
  28             'ext': 'mp4',
  29             'title': 'Under The Night',
  30             'description': 'md5:d2b8ca816579ae8a7bf28bfff8cefc8a',
  31             'duration': 2583,
  32             'view_count': int,
  33             'average_rating': 0,
  34             'age_limit': 14,
  35             'genre': 'Action, Sci-Fi',
  36             'creator': 'Allan Kroeker',
  37             'artist': 'Keith Hamilton Cobb, Kevin Sorbo, Lisa Ryder, Lexa Doig, Robert Hewitt Wolfe',
  38             'release_year': 2000,
  39             'series': 'Andromeda',
  40             'episode': 'Under The Night',
  41             'season_number': 1,
  42             'episode_number': 1,
  43         },
  44         'params': {
  45             # m3u8 download
  46             'skip_download': True,
  47         }
  48     }
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52
  53         country_code = self._downloader.params.get('geo_bypass_country', None)
  54         countries = [country_code] if country_code else (
  55             'US', 'AU', 'CA', 'AS', 'FM', 'GU', 'MP', 'PR', 'PW', 'MH', 'VI')
  56
  57         last_e = None
  58
  59         for country in countries:
  60             try:
  61                 media = self._download_json(
  62                     'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s'
  63                     % (video_id, country), video_id,
  64                     'Downloading media JSON as %s' % country,
  65                     'Unable to download media JSON', query={
  66                         'disableProtocols': 'true',
  67                         'format': 'json'
  68                     })
  69             except ExtractorError as e:
  70                 # 401 means geo restriction, trying next country
  71                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
  72                     last_e = e
  73                     continue
  74                 raise
  75
  76             media_urls = media.get('MediaURLs')
  77             if not media_urls or not isinstance(media_urls, list):
  78                 continue
  79
  80             title = media['Title']
  81
  82             formats = []
  83             for e in media['MediaURLs']:
  84                 if e.get('UseDRM') is True:
  85                     continue
  86                 format_url = e.get('Path')
  87                 if not format_url or not isinstance(format_url, compat_str):
  88                     continue
  89                 ext = determine_ext(format_url)
  90                 if ext == 'm3u8':
  91                     formats.extend(self._extract_m3u8_formats(
  92                         format_url, video_id, 'mp4', entry_protocol='m3u8_native',
  93                         m3u8_id='hls', fatal=False))
  94                 elif ext == 'mpd':
  95                     formats.extend(self._extract_mpd_formats(
  96                         format_url, video_id, mpd_id='dash', fatal=False))
  97             self._sort_formats(formats)
  98
  99             description = media.get('Description')
 100             duration = int_or_none(media.get(
 101                 'DurationInSeconds')) or parse_duration(media.get('Duration'))
 102             view_count = int_or_none(media.get('CountViews'))
 103             average_rating = float_or_none(media.get('UserRating'))
 104             age_limit = parse_age_limit(media.get('Rating'))
 105             genre = media.get('Genre')
 106             release_year = int_or_none(media.get('ReleaseYear'))
 107             creator = media.get('Directors')
 108             artist = media.get('Cast')
 109
 110             if media.get('MediaTypeDisplayValue') == 'Full Episode':
 111                 series = media.get('ShowName')
 112                 episode = title
 113                 season_number = int_or_none(media.get('Season'))
 114                 episode_number = int_or_none(media.get('Episode'))
 115             else:
 116                 series = episode = season_number = episode_number = None
 117
 118             subtitles = {}
 119             cc_files = media.get('ClosedCaptionFiles')
 120             if isinstance(cc_files, list):
 121                 for cc_file in cc_files:
 122                     if not isinstance(cc_file, dict):
 123                         continue
 124                     cc_url = cc_file.get('Path')
 125                     if not cc_url or not isinstance(cc_url, compat_str):
 126                         continue
 127                     lang = cc_file.get('Locale') or 'en'
 128                     subtitles.setdefault(lang, []).append({'url': cc_url})
 129
 130             thumbnails = []
 131             images = media.get('Images')
 132             if isinstance(images, list):
 133                 for image_key, image_url in images.items():
 134                     mobj = re.search(r'Img_(\d+)[xX](\d+)', image_key)
 135                     if not mobj:
 136                         continue
 137                     thumbnails.append({
 138                         'url': image_url,
 139                         'width': int(mobj.group(1)),
 140                         'height': int(mobj.group(2)),
 141                     })
 142
 143             return {
 144                 'id': video_id,
 145                 'title': title,
 146                 'description': description,
 147                 'duration': duration,
 148                 'view_count': view_count,
 149                 'average_rating': average_rating,
 150                 'age_limit': age_limit,
 151                 'genre': genre,
 152                 'creator': creator,
 153                 'artist': artist,
 154                 'release_year': release_year,
 155                 'series': series,
 156                 'episode': episode,
 157                 'season_number': season_number,
 158                 'episode_number': episode_number,
 159                 'thumbnails': thumbnails,
 160                 'subtitles': subtitles,
 161                 'formats': formats,
 162             }
 163
 164         raise last_e