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 ..compat import compat_str
   8 from ..utils import (
   9     int_or_none,
  10     orderedSet,
  11     parse_duration,
  12     str_or_none,
  13     unified_strdate,
  14     url_or_none,
  15     xpath_element,
  16     xpath_text,
  17 )
  18
  19
  20 class VideomoreIE(InfoExtractor):
  21     IE_NAME = 'videomore'
  22     _VALID_URL = r'''(?x)
  23                     videomore:(?P<sid>\d+)$|
  24                     https?://(?:player\.)?videomore\.ru/
  25                         (?:
  26                             (?:
  27                                 embed|
  28                                 [^/]+/[^/]+
  29                             )/|
  30                             [^/]*\?.*?\btrack_id=
  31                         )
  32                         (?P<id>\d+)
  33                         (?:[/?#&]|\.(?:xml|json)|$)
  34                     '''
  35     _TESTS = [{
  36         'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617',
  37         'md5': '44455a346edc0d509ac5b5a5b531dc35',
  38         'info_dict': {
  39             'id': '367617',
  40             'ext': 'flv',
  41             'title': 'Кино в деталях 5 сезон В гостях Алексей Чумаков и Юлия Ковальчук',
  42             'series': 'Кино в деталях',
  43             'episode': 'В гостях Алексей Чумаков и Юлия Ковальчук',
  44             'thumbnail': r're:^https?://.*\.jpg',
  45             'duration': 2910,
  46             'view_count': int,
  47             'comment_count': int,
  48             'age_limit': 16,
  49         },
  50     }, {
  51         'url': 'http://videomore.ru/embed/259974',
  52         'info_dict': {
  53             'id': '259974',
  54             'ext': 'flv',
  55             'title': 'Молодежка 2 сезон 40 серия',
  56             'series': 'Молодежка',
  57             'episode': '40 серия',
  58             'thumbnail': r're:^https?://.*\.jpg',
  59             'duration': 2809,
  60             'view_count': int,
  61             'comment_count': int,
  62             'age_limit': 16,
  63         },
  64         'params': {
  65             'skip_download': True,
  66         },
  67     }, {
  68         'url': 'http://videomore.ru/molodezhka/sezon_promo/341073',
  69         'info_dict': {
  70             'id': '341073',
  71             'ext': 'flv',
  72             'title': 'Промо Команда проиграла из-за Бакина?',
  73             'episode': 'Команда проиграла из-за Бакина?',
  74             'thumbnail': r're:^https?://.*\.jpg',
  75             'duration': 29,
  76             'age_limit': 16,
  77             'view_count': int,
  78         },
  79         'params': {
  80             'skip_download': True,
  81         },
  82     }, {
  83         'url': 'http://videomore.ru/elki_3?track_id=364623',
  84         'only_matching': True,
  85     }, {
  86         'url': 'http://videomore.ru/embed/364623',
  87         'only_matching': True,
  88     }, {
  89         'url': 'http://videomore.ru/video/tracks/364623.xml',
  90         'only_matching': True,
  91     }, {
  92         'url': 'http://videomore.ru/video/tracks/364623.json',
  93         'only_matching': True,
  94     }, {
  95         'url': 'http://videomore.ru/video/tracks/158031/quotes/33248',
  96         'only_matching': True,
  97     }, {
  98         'url': 'videomore:367617',
  99         'only_matching': True,
 100     }, {
 101         'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=',
 102         'only_matching': True,
 103     }]
 104
 105     @staticmethod
 106     def _extract_url(webpage):
 107         mobj = re.search(
 108             r'<object[^>]+data=(["\'])https?://videomore\.ru/player\.swf\?.*config=(?P<url>https?://videomore\.ru/(?:[^/]+/)+\d+\.xml).*\1',
 109             webpage)
 110         if not mobj:
 111             mobj = re.search(
 112                 r'<iframe[^>]+src=([\'"])(?P<url>https?://videomore\.ru/embed/\d+)',
 113                 webpage)
 114
 115         if mobj:
 116             return mobj.group('url')
 117
 118     def _real_extract(self, url):
 119         mobj = re.match(self._VALID_URL, url)
 120         video_id = mobj.group('sid') or mobj.group('id')
 121
 122         video = self._download_xml(
 123             'http://videomore.ru/video/tracks/%s.xml' % video_id,
 124             video_id, 'Downloading video XML')
 125
 126         item = xpath_element(video, './/playlist/item', fatal=True)
 127
 128         title = xpath_text(
 129             item, ('./title', './episode_name'), 'title', fatal=True)
 130
 131         video_url = xpath_text(item, './video_url', 'video url', fatal=True)
 132         formats = self._extract_f4m_formats(video_url, video_id, f4m_id='hds')
 133         self._sort_formats(formats)
 134
 135         thumbnail = xpath_text(item, './thumbnail_url')
 136         duration = int_or_none(xpath_text(item, './duration'))
 137         view_count = int_or_none(xpath_text(item, './views'))
 138         comment_count = int_or_none(xpath_text(item, './count_comments'))
 139         age_limit = int_or_none(xpath_text(item, './min_age'))
 140
 141         series = xpath_text(item, './project_name')
 142         episode = xpath_text(item, './episode_name')
 143
 144         return {
 145             'id': video_id,
 146             'title': title,
 147             'series': series,
 148             'episode': episode,
 149             'thumbnail': thumbnail,
 150             'duration': duration,
 151             'view_count': view_count,
 152             'comment_count': comment_count,
 153             'age_limit': age_limit,
 154             'formats': formats,
 155         }
 156
 157
 158 class VideomoreVideoIE(InfoExtractor):
 159     IE_NAME = 'videomore:video'
 160     _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)(?:/*|[?#&].*?)$'
 161     _TESTS = [{
 162         # single video with og:video:iframe
 163         'url': 'http://videomore.ru/elki_3',
 164         'info_dict': {
 165             'id': '364623',
 166             'ext': 'flv',
 167             'title': 'Ёлки 3',
 168             'description': '',
 169             'thumbnail': r're:^https?://.*\.jpg',
 170             'duration': 5579,
 171             'age_limit': 6,
 172             'view_count': int,
 173         },
 174         'params': {
 175             'skip_download': True,
 176         },
 177     }, {
 178         # season single series with og:video:iframe
 179         'url': 'http://videomore.ru/poslednii_ment/1_sezon/14_seriya',
 180         'only_matching': True,
 181     }, {
 182         'url': 'http://videomore.ru/sejchas_v_seti/serii_221-240/226_vypusk',
 183         'only_matching': True,
 184     }, {
 185         # single video without og:video:iframe
 186         'url': 'http://videomore.ru/marin_i_ego_druzya',
 187         'info_dict': {
 188             'id': '359073',
 189             'ext': 'flv',
 190             'title': '1 серия. Здравствуй, Аквавилль!',
 191             'description': 'md5:c6003179538b5d353e7bcd5b1372b2d7',
 192             'thumbnail': r're:^https?://.*\.jpg',
 193             'duration': 754,
 194             'age_limit': 6,
 195             'view_count': int,
 196         },
 197         'params': {
 198             'skip_download': True,
 199         },
 200     }, {
 201         'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so',
 202         'only_matching': True,
 203     }]
 204
 205     @classmethod
 206     def suitable(cls, url):
 207         return False if VideomoreIE.suitable(url) else super(VideomoreVideoIE, cls).suitable(url)
 208
 209     def _real_extract(self, url):
 210         display_id = self._match_id(url)
 211
 212         webpage = self._download_webpage(url, display_id)
 213
 214         video_url = self._og_search_property(
 215             'video:iframe', webpage, 'video url', default=None)
 216
 217         if not video_url:
 218             video_id = self._search_regex(
 219                 (r'config\s*:\s*["\']https?://videomore\.ru/video/tracks/(\d+)\.xml',
 220                  r'track-id=["\'](\d+)',
 221                  r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id')
 222             video_url = 'videomore:%s' % video_id
 223         else:
 224             video_id = None
 225
 226         return self.url_result(
 227             video_url, ie=VideomoreIE.ie_key(), video_id=video_id)
 228
 229
 230 class VideomoreSeasonIE(InfoExtractor):
 231     IE_NAME = 'videomore:season'
 232     _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$'
 233     _TESTS = [{
 234         'url': 'http://videomore.ru/molodezhka/sezon_promo',
 235         'info_dict': {
 236             'id': 'molodezhka/sezon_promo',
 237             'title': 'Молодежка Промо',
 238         },
 239         'playlist_mincount': 12,
 240     }, {
 241         'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so',
 242         'only_matching': True,
 243     }]
 244
 245     @classmethod
 246     def suitable(cls, url):
 247         return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url))
 248                 else super(VideomoreSeasonIE, cls).suitable(url))
 249
 250     def _real_extract(self, url):
 251         display_id = self._match_id(url)
 252
 253         webpage = self._download_webpage(url, display_id)
 254
 255         title = self._og_search_title(webpage)
 256
 257         data = self._parse_json(
 258             self._html_search_regex(
 259                 r'\bclass=["\']seasons-tracks["\'][^>]+\bdata-custom-data=(["\'])(?P<value>{.+?})\1',
 260                 webpage, 'data', default='{}', group='value'),
 261             display_id, fatal=False)
 262
 263         entries = []
 264
 265         if data:
 266             episodes = data.get('episodes')
 267             if isinstance(episodes, list):
 268                 for ep in episodes:
 269                     if not isinstance(ep, dict):
 270                         continue
 271                     ep_id = int_or_none(ep.get('id'))
 272                     ep_url = url_or_none(ep.get('url'))
 273                     if ep_id:
 274                         e = {
 275                             'url': 'videomore:%s' % ep_id,
 276                             'id': compat_str(ep_id),
 277                         }
 278                     elif ep_url:
 279                         e = {'url': ep_url}
 280                     else:
 281                         continue
 282                     e.update({
 283                         '_type': 'url',
 284                         'ie_key': VideomoreIE.ie_key(),
 285                         'title': str_or_none(ep.get('title')),
 286                         'thumbnail': url_or_none(ep.get('image')),
 287                         'duration': parse_duration(ep.get('duration')),
 288                         'episode_number': int_or_none(ep.get('number')),
 289                         'upload_date': unified_strdate(ep.get('date')),
 290                     })
 291                     entries.append(e)
 292
 293         if not entries:
 294             entries = [
 295                 self.url_result(
 296                     'videomore:%s' % video_id, ie=VideomoreIE.ie_key(),
 297                     video_id=video_id)
 298                 for video_id in orderedSet(re.findall(
 299                     r':(?:id|key)=["\'](\d+)["\']', webpage))]
 300
 301         if not entries:
 302             entries = [
 303                 self.url_result(item) for item in re.findall(
 304                     r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"'
 305                     % display_id, webpage)]
 306
 307         return self.playlist_result(entries, display_id, title)