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