Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ivi.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     int_or_none,
  11     qualities,
  12 )
  13
  14
  15 class IviIE(InfoExtractor):
  16     IE_DESC = 'ivi.ru'
  17     IE_NAME = 'ivi'
  18     _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
  19     _GEO_BYPASS = False
  20     _GEO_COUNTRIES = ['RU']
  21
  22     _TESTS = [
  23         # Single movie
  24         {
  25             'url': 'http://www.ivi.ru/watch/53141',
  26             'md5': '6ff5be2254e796ed346251d117196cf4',
  27             'info_dict': {
  28                 'id': '53141',
  29                 'ext': 'mp4',
  30                 'title': 'Иван Васильевич меняет профессию',
  31                 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
  32                 'duration': 5498,
  33                 'thumbnail': r're:^https?://.*\.jpg$',
  34             },
  35             'skip': 'Only works from Russia',
  36         },
  37         # Serial's series
  38         {
  39             'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
  40             'md5': '221f56b35e3ed815fde2df71032f4b3e',
  41             'info_dict': {
  42                 'id': '9549',
  43                 'ext': 'mp4',
  44                 'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
  45                 'series': 'Двое из ларца',
  46                 'season': 'Сезон 1',
  47                 'season_number': 1,
  48                 'episode': 'Дело Гольдберга (1 часть)',
  49                 'episode_number': 1,
  50                 'duration': 2655,
  51                 'thumbnail': r're:^https?://.*\.jpg$',
  52             },
  53             'skip': 'Only works from Russia',
  54         },
  55         {
  56             # with MP4-HD720 format
  57             'url': 'http://www.ivi.ru/watch/146500',
  58             'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
  59             'info_dict': {
  60                 'id': '146500',
  61                 'ext': 'mp4',
  62                 'title': 'Кукла',
  63                 'description': 'md5:ffca9372399976a2d260a407cc74cce6',
  64                 'duration': 5599,
  65                 'thumbnail': r're:^https?://.*\.jpg$',
  66             },
  67             'skip': 'Only works from Russia',
  68         },
  69         {
  70             'url': 'https://www.ivi.tv/watch/33560/',
  71             'only_matching': True,
  72         },
  73     ]
  74
  75     # Sorted by quality
  76     _KNOWN_FORMATS = (
  77         'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
  78         'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')
  79
  80     def _real_extract(self, url):
  81         video_id = self._match_id(url)
  82
  83         data = {
  84             'method': 'da.content.get',
  85             'params': [
  86                 video_id, {
  87                     'site': 's183',
  88                     'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
  89                     'contentid': video_id
  90                 }
  91             ]
  92         }
  93
  94         video_json = self._download_json(
  95             'http://api.digitalaccess.ru/api/json/', video_id,
  96             'Downloading video JSON', data=json.dumps(data))
  97
  98         if 'error' in video_json:
  99             error = video_json['error']
 100             origin = error['origin']
 101             if origin == 'NotAllowedForLocation':
 102                 self.raise_geo_restricted(
 103                     msg=error['message'], countries=self._GEO_COUNTRIES)
 104             elif origin == 'NoRedisValidData':
 105                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 106             raise ExtractorError(
 107                 'Unable to download video %s: %s' % (video_id, error['message']),
 108                 expected=True)
 109
 110         result = video_json['result']
 111
 112         quality = qualities(self._KNOWN_FORMATS)
 113
 114         formats = [{
 115             'url': x['url'],
 116             'format_id': x.get('content_format'),
 117             'quality': quality(x.get('content_format')),
 118         } for x in result['files'] if x.get('url')]
 119
 120         self._sort_formats(formats)
 121
 122         title = result['title']
 123
 124         duration = int_or_none(result.get('duration'))
 125         compilation = result.get('compilation')
 126         episode = title if compilation else None
 127
 128         title = '%s - %s' % (compilation, title) if compilation is not None else title
 129
 130         thumbnails = [{
 131             'url': preview['url'],
 132             'id': preview.get('content_format'),
 133         } for preview in result.get('preview', []) if preview.get('url')]
 134
 135         webpage = self._download_webpage(url, video_id)
 136
 137         season = self._search_regex(
 138             r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
 139             webpage, 'season', default=None)
 140         season_number = int_or_none(self._search_regex(
 141             r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
 142             webpage, 'season number', default=None))
 143
 144         episode_number = int_or_none(self._search_regex(
 145             r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
 146             webpage, 'episode number', default=None))
 147
 148         description = self._og_search_description(webpage, default=None) or self._html_search_meta(
 149             'description', webpage, 'description', default=None)
 150
 151         return {
 152             'id': video_id,
 153             'title': title,
 154             'series': compilation,
 155             'season': season,
 156             'season_number': season_number,
 157             'episode': episode,
 158             'episode_number': episode_number,
 159             'thumbnails': thumbnails,
 160             'description': description,
 161             'duration': duration,
 162             'formats': formats,
 163         }
 164
 165
 166 class IviCompilationIE(InfoExtractor):
 167     IE_DESC = 'ivi.ru compilations'
 168     IE_NAME = 'ivi:compilation'
 169     _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
 170     _TESTS = [{
 171         'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
 172         'info_dict': {
 173             'id': 'dvoe_iz_lartsa',
 174             'title': 'Двое из ларца (2006 - 2008)',
 175         },
 176         'playlist_mincount': 24,
 177     }, {
 178         'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
 179         'info_dict': {
 180             'id': 'dvoe_iz_lartsa/season1',
 181             'title': 'Двое из ларца (2006 - 2008) 1 сезон',
 182         },
 183         'playlist_mincount': 12,
 184     }]
 185
 186     def _extract_entries(self, html, compilation_id):
 187         return [
 188             self.url_result(
 189                 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
 190             for serie in re.findall(
 191                 r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]
 192
 193     def _real_extract(self, url):
 194         mobj = re.match(self._VALID_URL, url)
 195         compilation_id = mobj.group('compilationid')
 196         season_id = mobj.group('seasonid')
 197
 198         if season_id is not None:  # Season link
 199             season_page = self._download_webpage(
 200                 url, compilation_id, 'Downloading season %s web page' % season_id)
 201             playlist_id = '%s/season%s' % (compilation_id, season_id)
 202             playlist_title = self._html_search_meta('title', season_page, 'title')
 203             entries = self._extract_entries(season_page, compilation_id)
 204         else:  # Compilation link
 205             compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
 206             playlist_id = compilation_id
 207             playlist_title = self._html_search_meta('title', compilation_page, 'title')
 208             seasons = re.findall(
 209                 r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
 210             if not seasons:  # No seasons in this compilation
 211                 entries = self._extract_entries(compilation_page, compilation_id)
 212             else:
 213                 entries = []
 214                 for season_id in seasons:
 215                     season_page = self._download_webpage(
 216                         'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
 217                         compilation_id, 'Downloading season %s web page' % season_id)
 218                     entries.extend(self._extract_entries(season_page, compilation_id))
 219
 220         return self.playlist_result(entries, playlist_id, playlist_title)