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