Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ivi.py

   1 # encoding: 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     sanitized_Request,
  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
  55     # Sorted by quality
  56     _KNOWN_FORMATS = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
  57
  58     def _real_extract(self, url):
  59         video_id = self._match_id(url)
  60
  61         data = {
  62             'method': 'da.content.get',
  63             'params': [
  64                 video_id, {
  65                     'site': 's183',
  66                     'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
  67                     'contentid': video_id
  68                 }
  69             ]
  70         }
  71
  72         request = sanitized_Request(
  73             'http://api.digitalaccess.ru/api/json/', json.dumps(data))
  74         video_json = self._download_json(
  75             request, video_id, 'Downloading video JSON')
  76
  77         if 'error' in video_json:
  78             error = video_json['error']
  79             if error['origin'] == 'NoRedisValidData':
  80                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  81             raise ExtractorError(
  82                 'Unable to download video %s: %s' % (video_id, error['message']),
  83                 expected=True)
  84
  85         result = video_json['result']
  86
  87         formats = [{
  88             'url': x['url'],
  89             'format_id': x['content_format'],
  90             'preference': self._KNOWN_FORMATS.index(x['content_format']),
  91         } for x in result['files'] if x['content_format'] in self._KNOWN_FORMATS]
  92
  93         self._sort_formats(formats)
  94
  95         title = result['title']
  96
  97         duration = int_or_none(result.get('duration'))
  98         compilation = result.get('compilation')
  99         episode = title if compilation else None
 100
 101         title = '%s - %s' % (compilation, title) if compilation is not None else title
 102
 103         thumbnails = [{
 104             'url': preview['url'],
 105             'id': preview.get('content_format'),
 106         } for preview in result.get('preview', []) if preview.get('url')]
 107
 108         webpage = self._download_webpage(url, video_id)
 109
 110         season = self._search_regex(
 111             r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
 112             webpage, 'season', default=None)
 113         season_number = int_or_none(self._search_regex(
 114             r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
 115             webpage, 'season number', default=None))
 116
 117         episode_number = int_or_none(self._search_regex(
 118             r'<meta[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
 119             webpage, 'episode number', default=None))
 120
 121         description = self._og_search_description(webpage, default=None) or self._html_search_meta(
 122             'description', webpage, 'description', default=None)
 123
 124         return {
 125             'id': video_id,
 126             'title': title,
 127             'series': compilation,
 128             'season': season,
 129             'season_number': season_number,
 130             'episode': episode,
 131             'episode_number': episode_number,
 132             'thumbnails': thumbnails,
 133             'description': description,
 134             'duration': duration,
 135             'formats': formats,
 136         }
 137
 138
 139 class IviCompilationIE(InfoExtractor):
 140     IE_DESC = 'ivi.ru compilations'
 141     IE_NAME = 'ivi:compilation'
 142     _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
 143     _TESTS = [{
 144         'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
 145         'info_dict': {
 146             'id': 'dvoe_iz_lartsa',
 147             'title': 'Двое из ларца (2006 - 2008)',
 148         },
 149         'playlist_mincount': 24,
 150     }, {
 151         'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
 152         'info_dict': {
 153             'id': 'dvoe_iz_lartsa/season1',
 154             'title': 'Двое из ларца (2006 - 2008) 1 сезон',
 155         },
 156         'playlist_mincount': 12,
 157     }]
 158
 159     def _extract_entries(self, html, compilation_id):
 160         return [
 161             self.url_result(
 162                 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
 163             for serie in re.findall(
 164                 r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]
 165
 166     def _real_extract(self, url):
 167         mobj = re.match(self._VALID_URL, url)
 168         compilation_id = mobj.group('compilationid')
 169         season_id = mobj.group('seasonid')
 170
 171         if season_id is not None:  # Season link
 172             season_page = self._download_webpage(
 173                 url, compilation_id, 'Downloading season %s web page' % season_id)
 174             playlist_id = '%s/season%s' % (compilation_id, season_id)
 175             playlist_title = self._html_search_meta('title', season_page, 'title')
 176             entries = self._extract_entries(season_page, compilation_id)
 177         else:  # Compilation link
 178             compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
 179             playlist_id = compilation_id
 180             playlist_title = self._html_search_meta('title', compilation_page, 'title')
 181             seasons = re.findall(
 182                 r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
 183             if not seasons:  # No seasons in this compilation
 184                 entries = self._extract_entries(compilation_page, compilation_id)
 185             else:
 186                 entries = []
 187                 for season_id in seasons:
 188                     season_page = self._download_webpage(
 189                         'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
 190                         compilation_id, 'Downloading season %s web page' % season_id)
 191                     entries.extend(self._extract_entries(season_page, compilation_id))
 192
 193         return self.playlist_result(entries, playlist_id, playlist_title)