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