]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/videomore.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_str
20 class VideomoreIE(InfoExtractor
):
23 videomore:(?P<sid>\d+)$|
24 https?://(?:player\.)?videomore\.ru/
33 (?:[/?#&]|\.(?:xml|json)|$)
36 'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617',
37 'md5': '44455a346edc0d509ac5b5a5b531dc35',
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',
51 'url': 'http://videomore.ru/embed/259974',
55 'title': 'Молодежка 2 сезон 40 серия',
56 'series': 'Молодежка',
57 'episode': '40 серия',
58 'thumbnail': r
're:^https?://.*\.jpg',
65 'skip_download': True,
68 'url': 'http://videomore.ru/molodezhka/sezon_promo/341073',
72 'title': 'Промо Команда проиграла из-за Бакина?',
73 'episode': 'Команда проиграла из-за Бакина?',
74 'thumbnail': r
're:^https?://.*\.jpg',
80 'skip_download': True,
83 'url': 'http://videomore.ru/elki_3?track_id=364623',
84 'only_matching': True,
86 'url': 'http://videomore.ru/embed/364623',
87 'only_matching': True,
89 'url': 'http://videomore.ru/video/tracks/364623.xml',
90 'only_matching': True,
92 'url': 'http://videomore.ru/video/tracks/364623.json',
93 'only_matching': True,
95 'url': 'http://videomore.ru/video/tracks/158031/quotes/33248',
96 'only_matching': True,
98 'url': 'videomore:367617',
99 'only_matching': True,
101 'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=',
102 'only_matching': True,
106 def _extract_url(webpage
):
108 r
'<object[^>]+data=(["\'])https?
://videomore\
.ru
/player\
.swf
\?.*config
=(?P
<url
>https?
://videomore\
.ru
/(?
:[^
/]+/)+\d
+\
.xml
).*\
1',
112 r'<iframe
[^
>]+src
=([\'"])(?P<url>https?://videomore\.ru/embed/\d+)',
116 return mobj.group('url')
118 def _real_extract(self, url):
119 mobj = re.match(self._VALID_URL, url)
120 video_id = mobj.group('sid') or mobj.group('id')
122 video = self._download_xml(
123 'http://videomore.ru/video/tracks/%s.xml' % video_id,
124 video_id, 'Downloading video XML')
126 item = xpath_element(video, './/playlist/item', fatal=True)
129 item, ('./title', './episode_name'), 'title', fatal=True)
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)
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'))
141 series = xpath_text(item, './project_name')
142 episode = xpath_text(item, './episode_name')
149 'thumbnail': thumbnail,
150 'duration': duration,
151 'view_count': view_count,
152 'comment_count': comment_count,
153 'age_limit': age_limit,
158 class VideomoreVideoIE(InfoExtractor):
159 IE_NAME = 'videomore:video'
160 _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)(?:/*|[?#&].*?)$'
162 # single video with og:video:iframe
163 'url': 'http://videomore.ru/elki_3',
169 'thumbnail': r're:^https?://.*\.jpg',
175 'skip_download': True,
178 # season single series with og:video:iframe
179 'url': 'http://videomore.ru/poslednii_ment/1_sezon/14_seriya',
180 'only_matching': True,
182 'url': 'http://videomore.ru/sejchas_v_seti/serii_221-240/226_vypusk',
183 'only_matching': True,
185 # single video without og:video:iframe
186 'url': 'http://videomore.ru/marin_i_ego_druzya',
190 'title': '1 серия. Здравствуй, Аквавилль!',
191 'description': 'md5:c6003179538b5d353e7bcd5b1372b2d7',
192 'thumbnail': r're:^https?://.*\.jpg',
198 'skip_download': True,
201 'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so',
202 'only_matching': True,
206 def suitable(cls, url):
207 return False if VideomoreIE.suitable(url) else super(VideomoreVideoIE, cls).suitable(url)
209 def _real_extract(self, url):
210 display_id = self._match_id(url)
212 webpage = self._download_webpage(url, display_id)
214 video_url = self._og_search_property(
215 'video:iframe', webpage, 'video url', default=None)
218 video_id = self._search_regex(
219 (r'config\s*:\s*["\']https?
://videomore\
.ru
/video
/tracks
/(\d
+)\
.xml
',
220 r'track
-id=["\'](\d+)',
221 r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id')
222 video_url = 'videomore:%s' % video_id
226 return self.url_result(
227 video_url, ie=VideomoreIE.ie_key(), video_id=video_id)
230 class VideomoreSeasonIE(InfoExtractor):
231 IE_NAME = 'videomore:season'
232 _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$'
234 'url': 'http://videomore.ru/molodezhka/sezon_promo',
236 'id': 'molodezhka/sezon_promo',
237 'title': 'Молодежка Промо',
239 'playlist_mincount': 12,
241 'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so',
242 'only_matching': True,
246 def suitable(cls, url):
247 return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url))
248 else super(VideomoreSeasonIE, cls).suitable(url))
250 def _real_extract(self, url):
251 display_id = self._match_id(url)
253 webpage = self._download_webpage(url, display_id)
255 title = self._og_search_title(webpage)
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)
266 episodes = data.get('episodes
')
267 if isinstance(episodes, list):
269 if not isinstance(ep, dict):
271 ep_id = int_or_none(ep.get('id'))
272 ep_url = url_or_none(ep.get('url
'))
275 'url
': 'videomore
:%s' % ep_id,
276 'id': compat_str(ep_id),
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
')),
296 'videomore
:%s' % video_id, ie=VideomoreIE.ie_key(),
298 for video_id in orderedSet(re.findall(
299 r':(?
:id|key
)=["\'](\d+)["\']', webpage))]
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)]
307 return self.playlist_result(entries, display_id, title)