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': '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': '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': '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 mobj:
  90             return mobj.group('url')
  91
  92     def _real_extract(self, url):
  93         mobj = re.match(self._VALID_URL, url)
  94         video_id = mobj.group('sid') or mobj.group('id')
  95
  96         video = self._download_xml(
  97             'http://videomore.ru/video/tracks/%s.xml' % video_id,
  98             video_id, 'Downloading video XML')
  99
 100         item = xpath_element(video, './/playlist/item', fatal=True)
 101
 102         title = xpath_text(
 103             item, ('./title', './episode_name'), 'title', fatal=True)
 104
 105         video_url = xpath_text(item, './video_url', 'video url', fatal=True)
 106         formats = self._extract_f4m_formats(video_url, video_id, f4m_id='hds')
 107         self._sort_formats(formats)
 108
 109         thumbnail = xpath_text(item, './thumbnail_url')
 110         duration = int_or_none(xpath_text(item, './duration'))
 111         view_count = int_or_none(xpath_text(item, './views'))
 112         comment_count = int_or_none(xpath_text(item, './count_comments'))
 113         age_limit = int_or_none(xpath_text(item, './min_age'))
 114
 115         series = xpath_text(item, './project_name')
 116         episode = xpath_text(item, './episode_name')
 117
 118         return {
 119             'id': video_id,
 120             'title': title,
 121             'series': series,
 122             'episode': episode,
 123             'thumbnail': thumbnail,
 124             'duration': duration,
 125             'view_count': view_count,
 126             'comment_count': comment_count,
 127             'age_limit': age_limit,
 128             'formats': formats,
 129         }
 130
 131
 132 class VideomoreVideoIE(InfoExtractor):
 133     IE_NAME = 'videomore:video'
 134     _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$'
 135     _TESTS = [{
 136         # single video with og:video:iframe
 137         'url': 'http://videomore.ru/elki_3',
 138         'info_dict': {
 139             'id': '364623',
 140             'ext': 'flv',
 141             'title': 'Ёлки 3',
 142             'description': '',
 143             'thumbnail': 're:^https?://.*\.jpg',
 144             'duration': 5579,
 145             'age_limit': 6,
 146             'view_count': int,
 147         },
 148         'params': {
 149             'skip_download': True,
 150         },
 151     }, {
 152         # season single series with og:video:iframe
 153         'url': 'http://videomore.ru/poslednii_ment/1_sezon/14_seriya',
 154         'only_matching': True,
 155     }, {
 156         'url': 'http://videomore.ru/sejchas_v_seti/serii_221-240/226_vypusk',
 157         'only_matching': True,
 158     }, {
 159         # single video without og:video:iframe
 160         'url': 'http://videomore.ru/marin_i_ego_druzya',
 161         'info_dict': {
 162             'id': '359073',
 163             'ext': 'flv',
 164             'title': '1 серия. Здравствуй, Аквавилль!',
 165             'description': 'md5:c6003179538b5d353e7bcd5b1372b2d7',
 166             'thumbnail': 're:^https?://.*\.jpg',
 167             'duration': 754,
 168             'age_limit': 6,
 169             'view_count': int,
 170         },
 171         'params': {
 172             'skip_download': True,
 173         },
 174     }]
 175
 176     @classmethod
 177     def suitable(cls, url):
 178         return False if VideomoreIE.suitable(url) else super(VideomoreVideoIE, cls).suitable(url)
 179
 180     def _real_extract(self, url):
 181         display_id = self._match_id(url)
 182
 183         webpage = self._download_webpage(url, display_id)
 184
 185         video_url = self._og_search_property(
 186             'video:iframe', webpage, 'video url', default=None)
 187
 188         if not video_url:
 189             video_id = self._search_regex(
 190                 (r'config\s*:\s*["\']https?://videomore\.ru/video/tracks/(\d+)\.xml',
 191                  r'track-id=["\'](\d+)',
 192                  r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id')
 193             video_url = 'videomore:%s' % video_id
 194
 195         return self.url_result(video_url, VideomoreIE.ie_key())
 196
 197
 198 class VideomoreSeasonIE(InfoExtractor):
 199     IE_NAME = 'videomore:season'
 200     _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$'
 201     _TESTS = [{
 202         'url': 'http://videomore.ru/molodezhka/sezon_promo',
 203         'info_dict': {
 204             'id': 'molodezhka/sezon_promo',
 205             'title': 'Молодежка Промо',
 206         },
 207         'playlist_mincount': 12,
 208     }]
 209
 210     def _real_extract(self, url):
 211         display_id = self._match_id(url)
 212
 213         webpage = self._download_webpage(url, display_id)
 214
 215         title = self._og_search_title(webpage)
 216
 217         entries = [
 218             self.url_result(item) for item in re.findall(
 219                 r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"'
 220                 % display_id, webpage)]
 221
 222         return self.playlist_result(entries, display_id, title)