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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6 import hashlib
   7 import uuid
   8
   9 from .common import InfoExtractor
  10 from ..compat import (
  11     compat_urllib_parse,
  12     compat_urllib_request,
  13 )
  14 from ..utils import (
  15     ExtractorError,
  16     int_or_none,
  17     unified_strdate,
  18 )
  19
  20
  21 class SmotriIE(InfoExtractor):
  22     IE_DESC = 'Smotri.com'
  23     IE_NAME = 'smotri'
  24     _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})'
  25     _NETRC_MACHINE = 'smotri'
  26
  27     _TESTS = [
  28         # real video id 2610366
  29         {
  30             'url': 'http://smotri.com/video/view/?id=v261036632ab',
  31             'md5': '2a7b08249e6f5636557579c368040eb9',
  32             'info_dict': {
  33                 'id': 'v261036632ab',
  34                 'ext': 'mp4',
  35                 'title': 'катастрофа с камер видеонаблюдения',
  36                 'uploader': 'rbc2008',
  37                 'uploader_id': 'rbc08',
  38                 'upload_date': '20131118',
  39                 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
  40             },
  41         },
  42         # real video id 57591
  43         {
  44             'url': 'http://smotri.com/video/view/?id=v57591cb20',
  45             'md5': '830266dfc21f077eac5afd1883091bcd',
  46             'info_dict': {
  47                 'id': 'v57591cb20',
  48                 'ext': 'flv',
  49                 'title': 'test',
  50                 'uploader': 'Support Photofile@photofile',
  51                 'uploader_id': 'support-photofile',
  52                 'upload_date': '20070704',
  53                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
  54             },
  55         },
  56         # video-password, not approved by moderator
  57         {
  58             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
  59             'md5': 'f6331cef33cad65a0815ee482a54440b',
  60             'info_dict': {
  61                 'id': 'v1390466a13c',
  62                 'ext': 'mp4',
  63                 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
  64                 'uploader': 'timoxa40',
  65                 'uploader_id': 'timoxa40',
  66                 'upload_date': '20100404',
  67                 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
  68             },
  69             'params': {
  70                 'videopassword': 'qwerty',
  71             },
  72             'skip': 'Video is not approved by moderator',
  73         },
  74         # video-password
  75         {
  76             'url': 'http://smotri.com/video/view/?id=v6984858774#',
  77             'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
  78             'info_dict': {
  79                 'id': 'v6984858774',
  80                 'ext': 'mp4',
  81                 'title': 'Дача Солженицина ПАРОЛЬ 223322',
  82                 'uploader': 'psavari1',
  83                 'uploader_id': 'psavari1',
  84                 'upload_date': '20081103',
  85                 'thumbnail': 're:^https?://.*\.jpg$',
  86             },
  87             'params': {
  88                 'videopassword': '223322',
  89             },
  90         },
  91         # age limit + video-password, not approved by moderator
  92         {
  93             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
  94             'md5': '91e909c9f0521adf5ee86fbe073aad70',
  95             'info_dict': {
  96                 'id': 'v15408898bcf',
  97                 'ext': 'flv',
  98                 'title': 'этот ролик не покажут по ТВ',
  99                 'uploader': 'zzxxx',
 100                 'uploader_id': 'ueggb',
 101                 'upload_date': '20101001',
 102                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
 103                 'age_limit': 18,
 104             },
 105             'params': {
 106                 'videopassword': '333'
 107             },
 108             'skip': 'Video is not approved by moderator',
 109         },
 110         # age limit + video-password
 111         {
 112             'url': 'http://smotri.com/video/view/?id=v7780025814',
 113             'md5': 'b4599b068422559374a59300c5337d72',
 114             'info_dict': {
 115                 'id': 'v7780025814',
 116                 'ext': 'mp4',
 117                 'title': 'Sexy Beach (пароль 123)',
 118                 'uploader': 'вАся',
 119                 'uploader_id': 'asya_prosto',
 120                 'upload_date': '20081218',
 121                 'thumbnail': 're:^https?://.*\.jpg$',
 122                 'age_limit': 18,
 123             },
 124             'params': {
 125                 'videopassword': '123'
 126             },
 127         },
 128         # swf player
 129         {
 130             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
 131             'md5': '31099eeb4bc906712c5f40092045108d',
 132             'info_dict': {
 133                 'id': 'v9188090500',
 134                 'ext': 'mp4',
 135                 'title': 'Shakira - Don\'t Bother',
 136                 'uploader': 'HannahL',
 137                 'uploader_id': 'lisaha95',
 138                 'upload_date': '20090331',
 139                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
 140             },
 141         },
 142     ]
 143
 144     @classmethod
 145     def _extract_url(cls, webpage):
 146         mobj = re.search(
 147             r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
 148             webpage)
 149         if mobj is not None:
 150             return mobj.group('url')
 151
 152         mobj = re.search(
 153             r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
 154                     <div\s+class="video_image">[^<]+</div>\s*
 155                     <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
 156         if mobj is not None:
 157             return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
 158
 159     def _search_meta(self, name, html, display_name=None):
 160         if display_name is None:
 161             display_name = name
 162         return self._html_search_meta(name, html, display_name)
 163
 164     def _real_extract(self, url):
 165         video_id = self._match_id(url)
 166
 167         video_form = {
 168             'ticket': video_id,
 169             'video_url': '1',
 170             'frame_url': '1',
 171             'devid': 'LoadupFlashPlayer',
 172             'getvideoinfo': '1',
 173         }
 174
 175         video_password = self._downloader.params.get('videopassword', None)
 176         if video_password:
 177             video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
 178
 179         request = compat_urllib_request.Request(
 180             'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
 181         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 182
 183         video = self._download_json(request, video_id, 'Downloading video JSON')
 184
 185         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 186
 187         if not video_url:
 188             if video.get('_moderate_no'):
 189                 raise ExtractorError(
 190                     'Video %s has not been approved by moderator' % video_id, expected=True)
 191
 192             if video.get('error'):
 193                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 194
 195             if video.get('_pass_protected') == 1:
 196                 msg = ('Invalid video password' if video_password
 197                        else 'This video is protected by a password, use the --video-password option')
 198                 raise ExtractorError(msg, expected=True)
 199
 200         title = video['title']
 201         thumbnail = video['_imgURL']
 202         upload_date = unified_strdate(video['added'])
 203         uploader = video['userNick']
 204         uploader_id = video['userLogin']
 205         duration = int_or_none(video['duration'])
 206
 207         # Video JSON does not provide enough meta data
 208         # We will extract some from the video web page instead
 209         webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
 210         webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
 211
 212         # Warning if video is unavailable
 213         warning = self._html_search_regex(
 214             r'<div class="videoUnModer">(.*?)</div>', webpage,
 215             'warning message', default=None)
 216         if warning is not None:
 217             self._downloader.report_warning(
 218                 'Video %s may not be available; smotri said: %s ' %
 219                 (video_id, warning))
 220
 221         # Adult content
 222         if re.search('EroConfirmText">', webpage) is not None:
 223             self.report_age_confirmation()
 224             confirm_string = self._html_search_regex(
 225                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
 226                 webpage, 'confirm string')
 227             confirm_url = webpage_url + '&confirm=%s' % confirm_string
 228             webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
 229             adult_content = True
 230         else:
 231             adult_content = False
 232
 233         view_count = self._html_search_regex(
 234             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
 235             webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
 236
 237         return {
 238             'id': video_id,
 239             'url': video_url,
 240             'title': title,
 241             'thumbnail': thumbnail,
 242             'uploader': uploader,
 243             'upload_date': upload_date,
 244             'uploader_id': uploader_id,
 245             'duration': duration,
 246             'view_count': int_or_none(view_count),
 247             'age_limit': 18 if adult_content else 0,
 248         }
 249
 250
 251 class SmotriCommunityIE(InfoExtractor):
 252     IE_DESC = 'Smotri.com community videos'
 253     IE_NAME = 'smotri:community'
 254     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
 255     _TEST = {
 256         'url': 'http://smotri.com/community/video/kommuna',
 257         'info_dict': {
 258             'id': 'kommuna',
 259             'title': 'КПРФ',
 260         },
 261         'playlist_mincount': 4,
 262     }
 263
 264     def _real_extract(self, url):
 265         mobj = re.match(self._VALID_URL, url)
 266         community_id = mobj.group('communityid')
 267
 268         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
 269         rss = self._download_xml(url, community_id, 'Downloading community RSS')
 270
 271         entries = [self.url_result(video_url.text, 'Smotri')
 272                    for video_url in rss.findall('./channel/item/link')]
 273
 274         description_text = rss.find('./channel/description').text
 275         community_title = self._html_search_regex(
 276             '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 277
 278         return self.playlist_result(entries, community_id, community_title)
 279
 280
 281 class SmotriUserIE(InfoExtractor):
 282     IE_DESC = 'Smotri.com user videos'
 283     IE_NAME = 'smotri:user'
 284     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 285     _TESTS = [{
 286         'url': 'http://smotri.com/user/inspector',
 287         'info_dict': {
 288             'id': 'inspector',
 289             'title': 'Inspector',
 290         },
 291         'playlist_mincount': 9,
 292     }]
 293
 294     def _real_extract(self, url):
 295         mobj = re.match(self._VALID_URL, url)
 296         user_id = mobj.group('userid')
 297
 298         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
 299         rss = self._download_xml(url, user_id, 'Downloading user RSS')
 300
 301         entries = [self.url_result(video_url.text, 'Smotri')
 302                    for video_url in rss.findall('./channel/item/link')]
 303
 304         description_text = rss.find('./channel/description').text
 305         user_nickname = self._html_search_regex(
 306             '^Видео режиссера (.*)$', description_text,
 307             'user nickname')
 308
 309         return self.playlist_result(entries, user_id, user_nickname)
 310
 311
 312 class SmotriBroadcastIE(InfoExtractor):
 313     IE_DESC = 'Smotri.com broadcasts'
 314     IE_NAME = 'smotri:broadcast'
 315     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 316
 317     def _real_extract(self, url):
 318         mobj = re.match(self._VALID_URL, url)
 319         broadcast_id = mobj.group('broadcastid')
 320
 321         broadcast_url = 'http://' + mobj.group('url')
 322         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 323
 324         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 325             raise ExtractorError(
 326                 'Broadcast %s does not exist' % broadcast_id, expected=True)
 327
 328         # Adult content
 329         if re.search('EroConfirmText">', broadcast_page) is not None:
 330
 331             (username, password) = self._get_login_info()
 332             if username is None:
 333                 raise ExtractorError(
 334                     'Erotic broadcasts allowed only for registered users, '
 335                     'use --username and --password options to provide account credentials.',
 336                     expected=True)
 337
 338             login_form = {
 339                 'login-hint53': '1',
 340                 'confirm_erotic': '1',
 341                 'login': username,
 342                 'password': password,
 343             }
 344
 345             request = compat_urllib_request.Request(
 346                 broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
 347             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 348             broadcast_page = self._download_webpage(
 349                 request, broadcast_id, 'Logging in and confirming age')
 350
 351             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
 352                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 353
 354             adult_content = True
 355         else:
 356             adult_content = False
 357
 358         ticket = self._html_search_regex(
 359             r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'([^']+)'\)",
 360             broadcast_page, 'broadcast ticket')
 361
 362         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 363
 364         broadcast_password = self._downloader.params.get('videopassword', None)
 365         if broadcast_password:
 366             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 367
 368         broadcast_json_page = self._download_webpage(
 369             url, broadcast_id, 'Downloading broadcast JSON')
 370
 371         try:
 372             broadcast_json = json.loads(broadcast_json_page)
 373
 374             protected_broadcast = broadcast_json['_pass_protected'] == 1
 375             if protected_broadcast and not broadcast_password:
 376                 raise ExtractorError(
 377                     'This broadcast is protected by a password, use the --video-password option',
 378                     expected=True)
 379
 380             broadcast_offline = broadcast_json['is_play'] == 0
 381             if broadcast_offline:
 382                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 383
 384             rtmp_url = broadcast_json['_server']
 385             mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
 386             if not mobj:
 387                 raise ExtractorError('Unexpected broadcast rtmp URL')
 388
 389             broadcast_playpath = broadcast_json['_streamName']
 390             broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
 391             broadcast_thumbnail = broadcast_json['_imgURL']
 392             broadcast_title = self._live_title(broadcast_json['title'])
 393             broadcast_description = broadcast_json['description']
 394             broadcaster_nick = broadcast_json['nick']
 395             broadcaster_login = broadcast_json['login']
 396             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 397         except KeyError:
 398             if protected_broadcast:
 399                 raise ExtractorError('Bad broadcast password', expected=True)
 400             raise ExtractorError('Unexpected broadcast JSON')
 401
 402         return {
 403             'id': broadcast_id,
 404             'url': rtmp_url,
 405             'title': broadcast_title,
 406             'thumbnail': broadcast_thumbnail,
 407             'description': broadcast_description,
 408             'uploader': broadcaster_nick,
 409             'uploader_id': broadcaster_login,
 410             'age_limit': 18 if adult_content else 0,
 411             'ext': 'flv',
 412             'play_path': broadcast_playpath,
 413             'player_url': 'http://pics.smotri.com/broadcast_play.swf',
 414             'app': broadcast_app,
 415             'rtmp_live': True,
 416             'rtmp_conn': rtmp_conn,
 417             'is_live': True,
 418         }