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 (
   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)\.)?(?:sony)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
  23     _TESTS = [{
  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         'url': 'https://www.sonycrackle.com/andromeda/2502343',
  50         'only_matching': True,
  51     }]
  52
  53     def _real_extract(self, url):
  54         video_id = self._match_id(url)
  55
  56         country_code = self._downloader.params.get('geo_bypass_country', None)
  57         countries = [country_code] if country_code else (
  58             'US', 'AU', 'CA', 'AS', 'FM', 'GU', 'MP', 'PR', 'PW', 'MH', 'VI')
  59
  60         last_e = None
  61
  62         for country in countries:
  63             try:
  64                 media = self._download_json(
  65                     'https://web-api-us.crackle.com/Service.svc/details/media/%s/%s'
  66                     % (video_id, country), video_id,
  67                     'Downloading media JSON as %s' % country,
  68                     'Unable to download media JSON', query={
  69                         'disableProtocols': 'true',
  70                         'format': 'json'
  71                     })
  72             except ExtractorError as e:
  73                 # 401 means geo restriction, trying next country
  74                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
  75                     last_e = e
  76                     continue
  77                 raise
  78
  79             media_urls = media.get('MediaURLs')
  80             if not media_urls or not isinstance(media_urls, list):
  81                 continue
  82
  83             title = media['Title']
  84
  85             formats = []
  86             for e in media['MediaURLs']:
  87                 if e.get('UseDRM') is True:
  88                     continue
  89                 format_url = e.get('Path')
  90                 if not format_url or not isinstance(format_url, compat_str):
  91                     continue
  92                 ext = determine_ext(format_url)
  93                 if ext == 'm3u8':
  94                     formats.extend(self._extract_m3u8_formats(
  95                         format_url, video_id, 'mp4', entry_protocol='m3u8_native',
  96                         m3u8_id='hls', fatal=False))
  97                 elif ext == 'mpd':
  98                     formats.extend(self._extract_mpd_formats(
  99                         format_url, video_id, mpd_id='dash', fatal=False))
 100             self._sort_formats(formats)
 101
 102             description = media.get('Description')
 103             duration = int_or_none(media.get(
 104                 'DurationInSeconds')) or parse_duration(media.get('Duration'))
 105             view_count = int_or_none(media.get('CountViews'))
 106             average_rating = float_or_none(media.get('UserRating'))
 107             age_limit = parse_age_limit(media.get('Rating'))
 108             genre = media.get('Genre')
 109             release_year = int_or_none(media.get('ReleaseYear'))
 110             creator = media.get('Directors')
 111             artist = media.get('Cast')
 112
 113             if media.get('MediaTypeDisplayValue') == 'Full Episode':
 114                 series = media.get('ShowName')
 115                 episode = title
 116                 season_number = int_or_none(media.get('Season'))
 117                 episode_number = int_or_none(media.get('Episode'))
 118             else:
 119                 series = episode = season_number = episode_number = None
 120
 121             subtitles = {}
 122             cc_files = media.get('ClosedCaptionFiles')
 123             if isinstance(cc_files, list):
 124                 for cc_file in cc_files:
 125                     if not isinstance(cc_file, dict):
 126                         continue
 127                     cc_url = cc_file.get('Path')
 128                     if not cc_url or not isinstance(cc_url, compat_str):
 129                         continue
 130                     lang = cc_file.get('Locale') or 'en'
 131                     subtitles.setdefault(lang, []).append({'url': cc_url})
 132
 133             thumbnails = []
 134             images = media.get('Images')
 135             if isinstance(images, list):
 136                 for image_key, image_url in images.items():
 137                     mobj = re.search(r'Img_(\d+)[xX](\d+)', image_key)
 138                     if not mobj:
 139                         continue
 140                     thumbnails.append({
 141                         'url': image_url,
 142                         'width': int(mobj.group(1)),
 143                         'height': int(mobj.group(2)),
 144                     })
 145
 146             return {
 147                 'id': video_id,
 148                 'title': title,
 149                 'description': description,
 150                 'duration': duration,
 151                 'view_count': view_count,
 152                 'average_rating': average_rating,
 153                 'age_limit': age_limit,
 154                 'genre': genre,
 155                 'creator': creator,
 156                 'artist': artist,
 157                 'release_year': release_year,
 158                 'series': series,
 159                 'episode': episode,
 160                 'season_number': season_number,
 161                 'episode_number': episode_number,
 162                 'thumbnails': thumbnails,
 163                 'subtitles': subtitles,
 164                 'formats': formats,
 165             }
 166
 167         raise last_e