youtube_dl/extractor/smotri.py

   1 # coding: 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 ..utils import (
  11     ExtractorError,
  12     int_or_none,
  13     sanitized_Request,
  14     unified_strdate,
  15     urlencode_postdata,
  16     xpath_text,
  17 )
  18
  19
  20 class SmotriIE(InfoExtractor):
  21     IE_DESC = 'Smotri.com'
  22     IE_NAME = 'smotri'
  23     _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})'
  24     _NETRC_MACHINE = 'smotri'
  25
  26     _TESTS = [
  27         # real video id 2610366
  28         {
  29             'url': 'http://smotri.com/video/view/?id=v261036632ab',
  30             'md5': '02c0dfab2102984e9c5bb585cc7cc321',
  31             'info_dict': {
  32                 'id': 'v261036632ab',
  33                 'ext': 'mp4',
  34                 'title': 'катастрофа с камер видеонаблюдения',
  35                 'uploader': 'rbc2008',
  36                 'uploader_id': 'rbc08',
  37                 'upload_date': '20131118',
  38                 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
  39             },
  40         },
  41         # real video id 57591
  42         {
  43             'url': 'http://smotri.com/video/view/?id=v57591cb20',
  44             'md5': '830266dfc21f077eac5afd1883091bcd',
  45             'info_dict': {
  46                 'id': 'v57591cb20',
  47                 'ext': 'flv',
  48                 'title': 'test',
  49                 'uploader': 'Support Photofile@photofile',
  50                 'uploader_id': 'support-photofile',
  51                 'upload_date': '20070704',
  52                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
  53             },
  54         },
  55         # video-password, not approved by moderator
  56         {
  57             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
  58             'md5': 'f6331cef33cad65a0815ee482a54440b',
  59             'info_dict': {
  60                 'id': 'v1390466a13c',
  61                 'ext': 'mp4',
  62                 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
  63                 'uploader': 'timoxa40',
  64                 'uploader_id': 'timoxa40',
  65                 'upload_date': '20100404',
  66                 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
  67             },
  68             'params': {
  69                 'videopassword': 'qwerty',
  70             },
  71             'skip': 'Video is not approved by moderator',
  72         },
  73         # video-password
  74         {
  75             'url': 'http://smotri.com/video/view/?id=v6984858774#',
  76             'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
  77             'info_dict': {
  78                 'id': 'v6984858774',
  79                 'ext': 'mp4',
  80                 'title': 'Дача Солженицина ПАРОЛЬ 223322',
  81                 'uploader': 'psavari1',
  82                 'uploader_id': 'psavari1',
  83                 'upload_date': '20081103',
  84                 'thumbnail': r're:^https?://.*\.jpg$',
  85             },
  86             'params': {
  87                 'videopassword': '223322',
  88             },
  89         },
  90         # age limit + video-password, not approved by moderator
  91         {
  92             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
  93             'md5': '91e909c9f0521adf5ee86fbe073aad70',
  94             'info_dict': {
  95                 'id': 'v15408898bcf',
  96                 'ext': 'flv',
  97                 'title': 'этот ролик не покажут по ТВ',
  98                 'uploader': 'zzxxx',
  99                 'uploader_id': 'ueggb',
 100                 'upload_date': '20101001',
 101                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
 102                 'age_limit': 18,
 103             },
 104             'params': {
 105                 'videopassword': '333'
 106             },
 107             'skip': 'Video is not approved by moderator',
 108         },
 109         # age limit + video-password
 110         {
 111             'url': 'http://smotri.com/video/view/?id=v7780025814',
 112             'md5': 'b4599b068422559374a59300c5337d72',
 113             'info_dict': {
 114                 'id': 'v7780025814',
 115                 'ext': 'mp4',
 116                 'title': 'Sexy Beach (пароль 123)',
 117                 'uploader': 'вАся',
 118                 'uploader_id': 'asya_prosto',
 119                 'upload_date': '20081218',
 120                 'thumbnail': r're:^https?://.*\.jpg$',
 121                 'age_limit': 18,
 122             },
 123             'params': {
 124                 'videopassword': '123'
 125             },
 126         },
 127         # swf player
 128         {
 129             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
 130             'md5': '31099eeb4bc906712c5f40092045108d',
 131             'info_dict': {
 132                 'id': 'v9188090500',
 133                 'ext': 'mp4',
 134                 'title': 'Shakira - Don\'t Bother',
 135                 'uploader': 'HannahL',
 136                 'uploader_id': 'lisaha95',
 137                 'upload_date': '20090331',
 138                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
 139             },
 140         },
 141     ]
 142
 143     @classmethod
 144     def _extract_url(cls, webpage):
 145         mobj = re.search(
 146             r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
 147             webpage)
 148         if mobj is not None:
 149             return mobj.group('url')
 150
 151         mobj = re.search(
 152             r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
 153                     <div\s+class="video_image">[^<]+</div>\s*
 154                     <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
 155         if mobj is not None:
 156             return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
 157
 158     def _search_meta(self, name, html, display_name=None):
 159         if display_name is None:
 160             display_name = name
 161         return self._html_search_meta(name, html, display_name)
 162
 163     def _real_extract(self, url):
 164         video_id = self._match_id(url)
 165
 166         video_form = {
 167             'ticket': video_id,
 168             'video_url': '1',
 169             'frame_url': '1',
 170             'devid': 'LoadupFlashPlayer',
 171             'getvideoinfo': '1',
 172         }
 173
 174         video_password = self._downloader.params.get('videopassword')
 175         if video_password:
 176             video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
 177
 178         video = self._download_json(
 179             'http://smotri.com/video/view/url/bot/',
 180             video_id, 'Downloading video JSON',
 181             data=urlencode_postdata(video_form),
 182             headers={'Content-Type': 'application/x-www-form-urlencoded'})
 183
 184         video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
 185
 186         if not video_url:
 187             if video.get('_moderate_no'):
 188                 raise ExtractorError(
 189                     'Video %s has not been approved by moderator' % video_id, expected=True)
 190
 191             if video.get('error'):
 192                 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 193
 194             if video.get('_pass_protected') == 1:
 195                 msg = ('Invalid video password' if video_password
 196                        else 'This video is protected by a password, use the --video-password option')
 197                 raise ExtractorError(msg, expected=True)
 198
 199         title = video['title']
 200         thumbnail = video.get('_imgURL')
 201         upload_date = unified_strdate(video.get('added'))
 202         uploader = video.get('userNick')
 203         uploader_id = video.get('userLogin')
 204         duration = int_or_none(video.get('duration'))
 205
 206         # Video JSON does not provide enough meta data
 207         # We will extract some from the video web page instead
 208         webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
 209         webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
 210
 211         # Warning if video is unavailable
 212         warning = self._html_search_regex(
 213             r'<div[^>]+class="videoUnModer"[^>]*>(.+?)</div>', webpage,
 214             'warning message', default=None)
 215         if warning is not None:
 216             self._downloader.report_warning(
 217                 'Video %s may not be available; smotri said: %s ' %
 218                 (video_id, warning))
 219
 220         # Adult content
 221         if 'EroConfirmText">' in webpage:
 222             self.report_age_confirmation()
 223             confirm_string = self._html_search_regex(
 224                 r'<a[^>]+href="/video/view/\?id=%s&confirm=([^"]+)"' % video_id,
 225                 webpage, 'confirm string')
 226             confirm_url = webpage_url + '&confirm=%s' % confirm_string
 227             webpage = self._download_webpage(
 228                 confirm_url, video_id,
 229                 'Downloading video page (age confirmed)')
 230             adult_content = True
 231         else:
 232             adult_content = False
 233
 234         view_count = self._html_search_regex(
 235             r'(?s)Общее количество просмотров.*?<span class="Number">(\d+)</span>',
 236             webpage, 'view count', fatal=False)
 237
 238         return {
 239             'id': video_id,
 240             'url': video_url,
 241             'title': title,
 242             'thumbnail': thumbnail,
 243             'uploader': uploader,
 244             'upload_date': upload_date,
 245             'uploader_id': uploader_id,
 246             'duration': duration,
 247             'view_count': int_or_none(view_count),
 248             'age_limit': 18 if adult_content else 0,
 249         }
 250
 251
 252 class SmotriCommunityIE(InfoExtractor):
 253     IE_DESC = 'Smotri.com community videos'
 254     IE_NAME = 'smotri:community'
 255     _VALID_URL = r'https?://(?:www\.)?smotri\.com/community/video/(?P<id>[0-9A-Za-z_\'-]+)'
 256     _TEST = {
 257         'url': 'http://smotri.com/community/video/kommuna',
 258         'info_dict': {
 259             'id': 'kommuna',
 260         },
 261         'playlist_mincount': 4,
 262     }
 263
 264     def _real_extract(self, url):
 265         community_id = self._match_id(url)
 266
 267         rss = self._download_xml(
 268             'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id,
 269             community_id, 'Downloading community RSS')
 270
 271         entries = [
 272             self.url_result(video_url.text, SmotriIE.ie_key())
 273             for video_url in rss.findall('./channel/item/link')]
 274
 275         return self.playlist_result(entries, community_id)
 276
 277
 278 class SmotriUserIE(InfoExtractor):
 279     IE_DESC = 'Smotri.com user videos'
 280     IE_NAME = 'smotri:user'
 281     _VALID_URL = r'https?://(?:www\.)?smotri\.com/user/(?P<id>[0-9A-Za-z_\'-]+)'
 282     _TESTS = [{
 283         'url': 'http://smotri.com/user/inspector',
 284         'info_dict': {
 285             'id': 'inspector',
 286             'title': 'Inspector',
 287         },
 288         'playlist_mincount': 9,
 289     }]
 290
 291     def _real_extract(self, url):
 292         user_id = self._match_id(url)
 293
 294         rss = self._download_xml(
 295             'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id,
 296             user_id, 'Downloading user RSS')
 297
 298         entries = [self.url_result(video_url.text, 'Smotri')
 299                    for video_url in rss.findall('./channel/item/link')]
 300
 301         description_text = xpath_text(rss, './channel/description') or ''
 302         user_nickname = self._search_regex(
 303             '^Видео режиссера (.+)$', description_text,
 304             'user nickname', fatal=False)
 305
 306         return self.playlist_result(entries, user_id, user_nickname)
 307
 308
 309 class SmotriBroadcastIE(InfoExtractor):
 310     IE_DESC = 'Smotri.com broadcasts'
 311     IE_NAME = 'smotri:broadcast'
 312     _VALID_URL = r'https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<id>[^/]+))/?.*'
 313     _NETRC_MACHINE = 'smotri'
 314
 315     def _real_extract(self, url):
 316         mobj = re.match(self._VALID_URL, url)
 317         broadcast_id = mobj.group('id')
 318
 319         broadcast_url = 'http://' + mobj.group('url')
 320         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 321
 322         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 323             raise ExtractorError(
 324                 'Broadcast %s does not exist' % broadcast_id, expected=True)
 325
 326         # Adult content
 327         if re.search('EroConfirmText">', broadcast_page) is not None:
 328
 329             (username, password) = self._get_login_info()
 330             if username is None:
 331                 self.raise_login_required(
 332                     'Erotic broadcasts allowed only for registered users')
 333
 334             login_form = {
 335                 'login-hint53': '1',
 336                 'confirm_erotic': '1',
 337                 'login': username,
 338                 'password': password,
 339             }
 340
 341             request = sanitized_Request(
 342                 broadcast_url + '/?no_redirect=1', urlencode_postdata(login_form))
 343             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 344             broadcast_page = self._download_webpage(
 345                 request, broadcast_id, 'Logging in and confirming age')
 346
 347             if '>Неверный логин или пароль<' in broadcast_page:
 348                 raise ExtractorError(
 349                     'Unable to log in: bad username or password', expected=True)
 350
 351             adult_content = True
 352         else:
 353             adult_content = False
 354
 355         ticket = self._html_search_regex(
 356             (r'data-user-file=(["\'])(?P<ticket>(?!\1).+)\1',
 357              r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'(?P<ticket>[^']+)'\)"),
 358             broadcast_page, 'broadcast ticket', group='ticket')
 359
 360         broadcast_url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 361
 362         broadcast_password = self._downloader.params.get('videopassword')
 363         if broadcast_password:
 364             broadcast_url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 365
 366         broadcast_json_page = self._download_webpage(
 367             broadcast_url, broadcast_id, 'Downloading broadcast JSON')
 368
 369         try:
 370             broadcast_json = json.loads(broadcast_json_page)
 371
 372             protected_broadcast = broadcast_json['_pass_protected'] == 1
 373             if protected_broadcast and not broadcast_password:
 374                 raise ExtractorError(
 375                     'This broadcast is protected by a password, use the --video-password option',
 376                     expected=True)
 377
 378             broadcast_offline = broadcast_json['is_play'] == 0
 379             if broadcast_offline:
 380                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 381
 382             rtmp_url = broadcast_json['_server']
 383             mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
 384             if not mobj:
 385                 raise ExtractorError('Unexpected broadcast rtmp URL')
 386
 387             broadcast_playpath = broadcast_json['_streamName']
 388             broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
 389             broadcast_thumbnail = broadcast_json.get('_imgURL')
 390             broadcast_title = self._live_title(broadcast_json['title'])
 391             broadcast_description = broadcast_json.get('description')
 392             broadcaster_nick = broadcast_json.get('nick')
 393             broadcaster_login = broadcast_json.get('login')
 394             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 395         except KeyError:
 396             if protected_broadcast:
 397                 raise ExtractorError('Bad broadcast password', expected=True)
 398             raise ExtractorError('Unexpected broadcast JSON')
 399
 400         return {
 401             'id': broadcast_id,
 402             'url': rtmp_url,
 403             'title': broadcast_title,
 404             'thumbnail': broadcast_thumbnail,
 405             'description': broadcast_description,
 406             'uploader': broadcaster_nick,
 407             'uploader_id': broadcaster_login,
 408             'age_limit': 18 if adult_content else 0,
 409             'ext': 'flv',
 410             'play_path': broadcast_playpath,
 411             'player_url': 'http://pics.smotri.com/broadcast_play.swf',
 412             'app': broadcast_app,
 413             'rtmp_live': True,
 414             'rtmp_conn': rtmp_conn,
 415             'is_live': True,
 416         }