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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     xpath_element,
  10     xpath_text,
  11 )
  12
  13
  14 class VideomoreIE(InfoExtractor):
  15     IE_NAME = 'videomore'
  16     _VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)'
  17     _TESTS = [{
  18         'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617',
  19         'md5': '44455a346edc0d509ac5b5a5b531dc35',
  20         'info_dict': {
  21             'id': '367617',
  22             'ext': 'flv',
  23             'title': 'Кино в деталях 5 сезон В гостях Алексей Чумаков и Юлия Ковальчук',
  24             'series': 'Кино в деталях',
  25             'episode': 'В гостях Алексей Чумаков и Юлия Ковальчук',
  26             'thumbnail': r're:^https?://.*\.jpg',
  27             'duration': 2910,
  28             'view_count': int,
  29             'comment_count': int,
  30             'age_limit': 16,
  31         },
  32     }, {
  33         'url': 'http://videomore.ru/embed/259974',
  34         'info_dict': {
  35             'id': '259974',
  36             'ext': 'flv',
  37             'title': 'Молодежка 2 сезон 40 серия',
  38             'series': 'Молодежка',
  39             'episode': '40 серия',
  40             'thumbnail': r're:^https?://.*\.jpg',
  41             'duration': 2809,
  42             'view_count': int,
  43             'comment_count': int,
  44             'age_limit': 16,
  45         },
  46         'params': {
  47             'skip_download': True,
  48         },
  49     }, {
  50         'url': 'http://videomore.ru/molodezhka/sezon_promo/341073',
  51         'info_dict': {
  52             'id': '341073',
  53             'ext': 'flv',
  54             'title': 'Промо Команда проиграла из-за Бакина?',
  55             'episode': 'Команда проиграла из-за Бакина?',
  56             'thumbnail': r're:^https?://.*\.jpg',
  57             'duration': 29,
  58             'age_limit': 16,
  59             'view_count': int,
  60         },
  61         'params': {
  62             'skip_download': True,
  63         },
  64     }, {
  65         'url': 'http://videomore.ru/elki_3?track_id=364623',
  66         'only_matching': True,
  67     }, {
  68         'url': 'http://videomore.ru/embed/364623',
  69         'only_matching': True,
  70     }, {
  71         'url': 'http://videomore.ru/video/tracks/364623.xml',
  72         'only_matching': True,
  73     }, {
  74         'url': 'http://videomore.ru/video/tracks/364623.json',
  75         'only_matching': True,
  76     }, {
  77         'url': 'http://videomore.ru/video/tracks/158031/quotes/33248',
  78         'only_matching': True,
  79     }, {
  80         'url': 'videomore:367617',
  81         'only_matching': True,
  82     }]
  83
  84     @staticmethod
  85     def _extract_url(webpage):
  86         mobj = re.search(
  87             r'<object[^>]+data=(["\'])https?://videomore\.ru/player\.swf\?.*config=(?P<url>https?://videomore\.ru/(?:[^/]+/)+\d+\.xml).*\1',
  88             webpage)
  89         if not mobj:
  90             mobj = re.search(
  91                 r'<iframe[^>]+src=([\'"])(?P<url>https?://videomore\.ru/embed/\d+)',
  92                 webpage)
  93
  94         if mobj:
  95             return mobj.group('url')
  96
  97     def _real_extract(self, url):
  98         mobj = re.match(self._VALID_URL, url)
  99         video_id = mobj.group('sid') or mobj.group('id')
 100
 101         video = self._download_xml(
 102             'http://videomore.ru/video/tracks/%s.xml' % video_id,
 103             video_id, 'Downloading video XML')
 104
 105         item = xpath_element(video, './/playlist/item', fatal=True)
 106
 107         title = xpath_text(
 108             item, ('./title', './episode_name'), 'title', fatal=True)
 109
 110         video_url = xpath_text(item, './video_url', 'video url', fatal=True)
 111         formats = self._extract_f4m_formats(video_url, video_id, f4m_id='hds')
 112         self._sort_formats(formats)
 113
 114         thumbnail = xpath_text(item, './thumbnail_url')
 115         duration = int_or_none(xpath_text(item, './duration'))
 116         view_count = int_or_none(xpath_text(item, './views'))
 117         comment_count = int_or_none(xpath_text(item, './count_comments'))
 118         age_limit = int_or_none(xpath_text(item, './min_age'))
 119
 120         series = xpath_text(item, './project_name')
 121         episode = xpath_text(item, './episode_name')
 122
 123         return {
 124             'id': video_id,
 125             'title': title,
 126             'series': series,
 127             'episode': episode,
 128             'thumbnail': thumbnail,
 129             'duration': duration,
 130             'view_count': view_count,
 131             'comment_count': comment_count,
 132             'age_limit': age_limit,
 133             'formats': formats,
 134         }
 135
 136
 137 class VideomoreVideoIE(InfoExtractor):
 138     IE_NAME = 'videomore:video'
 139     _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$'
 140     _TESTS = [{
 141         # single video with og:video:iframe
 142         'url': 'http://videomore.ru/elki_3',
 143         'info_dict': {
 144             'id': '364623',
 145             'ext': 'flv',
 146             'title': 'Ёлки 3',
 147             'description': '',
 148             'thumbnail': r're:^https?://.*\.jpg',
 149             'duration': 5579,
 150             'age_limit': 6,
 151             'view_count': int,
 152         },
 153         'params': {
 154             'skip_download': True,
 155         },
 156     }, {
 157         # season single series with og:video:iframe
 158         'url': 'http://videomore.ru/poslednii_ment/1_sezon/14_seriya',
 159         'only_matching': True,
 160     }, {
 161         'url': 'http://videomore.ru/sejchas_v_seti/serii_221-240/226_vypusk',
 162         'only_matching': True,
 163     }, {
 164         # single video without og:video:iframe
 165         'url': 'http://videomore.ru/marin_i_ego_druzya',
 166         'info_dict': {
 167             'id': '359073',
 168             'ext': 'flv',
 169             'title': '1 серия. Здравствуй, Аквавилль!',
 170             'description': 'md5:c6003179538b5d353e7bcd5b1372b2d7',
 171             'thumbnail': r're:^https?://.*\.jpg',
 172             'duration': 754,
 173             'age_limit': 6,
 174             'view_count': int,
 175         },
 176         'params': {
 177             'skip_download': True,
 178         },
 179     }]
 180
 181     @classmethod
 182     def suitable(cls, url):
 183         return False if VideomoreIE.suitable(url) else super(VideomoreVideoIE, cls).suitable(url)
 184
 185     def _real_extract(self, url):
 186         display_id = self._match_id(url)
 187
 188         webpage = self._download_webpage(url, display_id)
 189
 190         video_url = self._og_search_property(
 191             'video:iframe', webpage, 'video url', default=None)
 192
 193         if not video_url:
 194             video_id = self._search_regex(
 195                 (r'config\s*:\s*["\']https?://videomore\.ru/video/tracks/(\d+)\.xml',
 196                  r'track-id=["\'](\d+)',
 197                  r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id')
 198             video_url = 'videomore:%s' % video_id
 199
 200         return self.url_result(video_url, VideomoreIE.ie_key())
 201
 202
 203 class VideomoreSeasonIE(InfoExtractor):
 204     IE_NAME = 'videomore:season'
 205     _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$'
 206     _TESTS = [{
 207         'url': 'http://videomore.ru/molodezhka/sezon_promo',
 208         'info_dict': {
 209             'id': 'molodezhka/sezon_promo',
 210             'title': 'Молодежка Промо',
 211         },
 212         'playlist_mincount': 12,
 213     }]
 214
 215     def _real_extract(self, url):
 216         display_id = self._match_id(url)
 217
 218         webpage = self._download_webpage(url, display_id)
 219
 220         title = self._og_search_title(webpage)
 221
 222         entries = [
 223             self.url_result(item) for item in re.findall(
 224                 r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"'
 225                 % display_id, webpage)]
 226
 227         return self.playlist_result(entries, display_id, title)