2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
12 compat_urllib_request
,
19 class SmotriIE(InfoExtractor
):
20 IE_DESC
= 'Smotri.com'
22 _VALID_URL
= r
'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
23 _NETRC_MACHINE
= 'smotri'
26 # real video id 2610366
28 'url': 'http://smotri.com/video/view/?id=v261036632ab',
29 'md5': '2a7b08249e6f5636557579c368040eb9',
33 'title': 'катастрофа с камер видеонаблюдения',
34 'uploader': 'rbc2008',
35 'uploader_id': 'rbc08',
36 'upload_date': '20131118',
37 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
42 'url': 'http://smotri.com/video/view/?id=v57591cb20',
43 'md5': '830266dfc21f077eac5afd1883091bcd',
48 'uploader': 'Support Photofile@photofile',
49 'uploader_id': 'support-photofile',
50 'upload_date': '20070704',
51 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
56 'url': 'http://smotri.com/video/view/?id=v1390466a13c',
57 'md5': 'f6331cef33cad65a0815ee482a54440b',
61 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
62 'uploader': 'timoxa40',
63 'uploader_id': 'timoxa40',
64 'upload_date': '20100404',
65 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
68 'videopassword': 'qwerty',
71 # age limit + video-password
73 'url': 'http://smotri.com/video/view/?id=v15408898bcf',
74 'md5': '91e909c9f0521adf5ee86fbe073aad70',
78 'title': 'этот ролик не покажут по ТВ',
80 'uploader_id': 'ueggb',
81 'upload_date': '20101001',
82 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
86 'videopassword': '333'
91 'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
92 'md5': '4d47034979d9390d14acdf59c4935bc2',
96 'title': 'Shakira - Don\'t Bother',
97 'uploader': 'HannahL',
98 'uploader_id': 'lisaha95',
99 'upload_date': '20090331',
100 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
106 def _extract_url(cls
, webpage
):
108 r
'<embed[^>]src=(["\'])(?P
<url
>http
://pics\
.smotri\
.com
/(?
:player|scrubber_custom8
)\
.swf
\?file=v
.+?\
1)',
111 return mobj.group('url
')
114 r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
115 <div\s+class="video_image">[^<]+</div>\s*
116 <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
118 return 'http
://smotri
.com
/video
/view
/?
id=%s' % mobj.group('id')
120 def _search_meta(self, name, html, display_name=None):
121 if display_name is None:
123 return self._html_search_regex(
124 r'<meta itemprop
="%s" content
="([^"]+)" />' % re.escape(name),
125 html, display_name, fatal=False)
126 return self._html_search_meta(name, html, display_name)
128 def _real_extract(self, url):
129 video_id = self._match_id(url)
135 'devid': 'LoadupFlashPlayer',
139 request = compat_urllib_request.Request(
140 'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
141 request.add_header('Content-Type', 'application/x-www-form-urlencoded')
143 video = self._download_json(request, video_id, 'Downloading video JSON')
145 if video.get('_moderate_no') or not video.get('moderated'):
146 raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True)
148 if video.get('error'):
149 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
151 video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
152 title = video['title']
153 thumbnail = video['_imgURL']
154 upload_date = unified_strdate(video['added'])
155 uploader = video['userNick']
156 uploader_id = video['userLogin']
157 duration = int_or_none(video['duration'])
159 # Video JSON does not provide enough meta data
160 # We will extract some from the video web page instead
161 webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
162 webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
164 # Warning if video is unavailable
165 warning = self._html_search_regex(
166 r'<div class="videoUnModer
">(.*?)</div>', webpage,
167 'warning message', default=None)
168 if warning is not None:
169 self._downloader.report_warning(
170 'Video %s may not be available; smotri said: %s ' %
174 if re.search('EroConfirmText">', webpage) is not None:
175 self.report_age_confirmation()
176 confirm_string = self._html_search_regex(
177 r'<a href
="/video/view/\?id=%s&confirm=([^"]+)" title="[^
"]+">' % video_id,
178 webpage, 'confirm string
')
179 confirm_url = webpage_url + '&confirm
=%s' % confirm_string
180 webpage = self._download_webpage(confirm_url, video_id, 'Downloading video
page (age confirmed
)')
183 adult_content = False
185 view_count = self._html_search_regex(
186 'Общее количество просмотров
.*?
<span
class="Number">(\\d
+)</span
>',
187 webpage, 'view count
', fatal=False, flags=re.MULTILINE | re.DOTALL)
193 'thumbnail
': thumbnail,
194 'uploader
': uploader,
195 'upload_date
': upload_date,
196 'uploader_id
': uploader_id,
197 'duration
': duration,
198 'view_count
': int_or_none(view_count),
199 'age_limit
': 18 if adult_content else 0,
203 class SmotriCommunityIE(InfoExtractor):
204 IE_DESC = 'Smotri
.com community videos
'
205 IE_NAME = 'smotri
:community
'
206 _VALID_URL = r'^https?
://(?
:www\
.)?smotri\
.com
/community
/video
/(?P
<communityid
>[0-9A
-Za
-z_
\'-]+)'
208 'url
': 'http
://smotri
.com
/community
/video
/kommuna
',
213 'playlist_mincount
': 4,
216 def _real_extract(self, url):
217 mobj = re.match(self._VALID_URL, url)
218 community_id = mobj.group('communityid
')
220 url = 'http
://smotri
.com
/export
/rss
/video
/by
/community
/-/%s/video
.xml
' % community_id
221 rss = self._download_xml(url, community_id, 'Downloading community RSS
')
223 entries = [self.url_result(video_url.text, 'Smotri
')
224 for video_url in rss.findall('./channel
/item
/link
')]
226 description_text = rss.find('./channel
/description
').text
227 community_title = self._html_search_regex(
228 '^Видео сообщества
"([^"]+)"$', description_text, 'community title')
230 return self.playlist_result(entries, community_id, community_title)
233 class SmotriUserIE(InfoExtractor):
234 IE_DESC = 'Smotri.com user videos'
235 IE_NAME = 'smotri:user'
236 _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
238 'url': 'http://smotri.com/user/inspector',
241 'title': 'Inspector',
243 'playlist_mincount': 9,
246 def _real_extract(self, url):
247 mobj = re.match(self._VALID_URL, url)
248 user_id = mobj.group('userid')
250 url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
251 rss = self._download_xml(url, user_id, 'Downloading user RSS')
253 entries = [self.url_result(video_url.text, 'Smotri')
254 for video_url in rss.findall('./channel/item/link')]
256 description_text = rss.find('./channel/description').text
257 user_nickname = self._html_search_regex(
258 '^Видео режиссера (.*)$', description_text,
261 return self.playlist_result(entries, user_id, user_nickname)
264 class SmotriBroadcastIE(InfoExtractor):
265 IE_DESC = 'Smotri.com broadcasts'
266 IE_NAME = 'smotri:broadcast'
267 _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
269 def _real_extract(self, url):
270 mobj = re.match(self._VALID_URL, url)
271 broadcast_id = mobj.group('broadcastid')
273 broadcast_url = 'http://' + mobj.group('url')
274 broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
276 if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
277 raise ExtractorError(
278 'Broadcast %s does not exist' % broadcast_id, expected=True)
281 if re.search('EroConfirmText">', broadcast_page) is not None:
283 (username, password) = self._get_login_info()
285 raise ExtractorError(
286 'Erotic broadcasts allowed only
for registered users
, '
287 'use
--username
and --password options to provide account credentials
.',
292 'confirm_erotic
': '1',
294 'password
': password,
297 request = compat_urllib_request.Request(
298 broadcast_url + '/?no_redirect
=1', compat_urllib_parse.urlencode(login_form))
299 request.add_header('Content
-Type
', 'application
/x
-www
-form
-urlencoded
')
300 broadcast_page = self._download_webpage(
301 request, broadcast_id, 'Logging
in and confirming age
')
303 if re.search('>Неверный логин или пароль
<', broadcast_page) is not None:
304 raise ExtractorError('Unable to log
in: bad username
or password
', expected=True)
308 adult_content = False
310 ticket = self._html_search_regex(
311 r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^
']+)'\
)",
312 broadcast_page, 'broadcast ticket')
314 url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
316 broadcast_password = self._downloader.params.get('videopassword', None)
317 if broadcast_password:
318 url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
320 broadcast_json_page = self._download_webpage(
321 url, broadcast_id, 'Downloading broadcast JSON')
324 broadcast_json = json.loads(broadcast_json_page)
326 protected_broadcast = broadcast_json['_pass_protected'] == 1
327 if protected_broadcast and not broadcast_password:
328 raise ExtractorError(
329 'This broadcast is protected by a password, use the --video-password option',
332 broadcast_offline = broadcast_json['is_play'] == 0
333 if broadcast_offline:
334 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
336 rtmp_url = broadcast_json['_server']
337 mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
339 raise ExtractorError('Unexpected broadcast rtmp URL')
341 broadcast_playpath = broadcast_json['_streamName']
342 broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
343 broadcast_thumbnail = broadcast_json['_imgURL']
344 broadcast_title = self._live_title(broadcast_json['title'])
345 broadcast_description = broadcast_json['description']
346 broadcaster_nick = broadcast_json['nick']
347 broadcaster_login = broadcast_json['login']
348 rtmp_conn = 'S:%s' % uuid.uuid4().hex
350 if protected_broadcast:
351 raise ExtractorError('Bad broadcast password', expected=True)
352 raise ExtractorError('Unexpected broadcast JSON')
357 'title': broadcast_title,
358 'thumbnail': broadcast_thumbnail,
359 'description': broadcast_description,
360 'uploader': broadcaster_nick,
361 'uploader_id': broadcaster_login,
362 'age_limit': 18 if adult_content else 0,
364 'play_path': broadcast_playpath,
365 'player_url': 'http://pics.smotri.com/broadcast_play.swf',
366 'app': broadcast_app,
368 'rtmp_conn': rtmp_conn,