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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import os.path
   5 import re
   6 import json
   7 import hashlib
   8 import uuid
   9
  10 from .common import InfoExtractor
  11 from ..utils import (
  12     compat_urllib_parse,
  13     compat_urllib_request,
  14     ExtractorError,
  15     url_basename,
  16     int_or_none,
  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<videoid>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': '2a7b08249e6f5636557579c368040eb9',
  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                 'description': 'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
  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                 'description': 'test, видео test',
  54                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
  55             },
  56         },
  57         # video-password
  58         {
  59             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
  60             'md5': 'f6331cef33cad65a0815ee482a54440b',
  61             'info_dict': {
  62                 'id': 'v1390466a13c',
  63                 'ext': 'mp4',
  64                 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
  65                 'uploader': 'timoxa40',
  66                 'uploader_id': 'timoxa40',
  67                 'upload_date': '20100404',
  68                 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
  69                 'description': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
  70             },
  71             'params': {
  72                 'videopassword': 'qwerty',
  73             },
  74         },
  75         # age limit + video-password
  76         {
  77             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
  78             'md5': '91e909c9f0521adf5ee86fbe073aad70',
  79             'info_dict': {
  80                 'id': 'v15408898bcf',
  81                 'ext': 'flv',
  82                 'title': 'этот ролик не покажут по ТВ',
  83                 'uploader': 'zzxxx',
  84                 'uploader_id': 'ueggb',
  85                 'upload_date': '20101001',
  86                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
  87                 'age_limit': 18,
  88                 'description': 'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
  89             },
  90             'params': {
  91                 'videopassword': '333'
  92             }
  93         },
  94         # swf player
  95         {
  96             'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
  97             'md5': '4d47034979d9390d14acdf59c4935bc2',
  98             'info_dict': {
  99                 'id': 'v9188090500',
 100                 'ext': 'mp4',
 101                 'title': 'Shakira - Don\'t Bother',
 102                 'uploader': 'HannahL',
 103                 'uploader_id': 'lisaha95',
 104                 'upload_date': '20090331',
 105                 'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother',
 106                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
 107             },
 108         },
 109     ]
 110
 111     _SUCCESS = 0
 112     _PASSWORD_NOT_VERIFIED = 1
 113     _PASSWORD_DETECTED = 2
 114     _VIDEO_NOT_FOUND = 3
 115
 116     @classmethod
 117     def _extract_url(cls, webpage):
 118         mobj = re.search(
 119             r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
 120             webpage)
 121         if mobj is not None:
 122             return mobj.group('url')
 123
 124         mobj = re.search(
 125             r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
 126                     <div\s+class="video_image">[^<]+</div>\s*
 127                     <div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
 128         if mobj is not None:
 129             return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
 130
 131     def _search_meta(self, name, html, display_name=None):
 132         if display_name is None:
 133             display_name = name
 134         return self._html_search_regex(
 135             r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
 136             html, display_name, fatal=False)
 137         return self._html_search_meta(name, html, display_name)
 138
 139     def _real_extract(self, url):
 140         mobj = re.match(self._VALID_URL, url)
 141         video_id = mobj.group('videoid')
 142         real_video_id = mobj.group('realvideoid')
 143
 144         # Download video JSON data
 145         video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id
 146         video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON')
 147         video_json = json.loads(video_json_page)
 148
 149         status = video_json['status']
 150         if status == self._VIDEO_NOT_FOUND:
 151             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 152         elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with
 153                                                 # video-password set
 154             video_password = self._downloader.params.get('videopassword', None)
 155             if not video_password:
 156                 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 157             video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest()
 158             video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON (video-password set)')
 159             video_json = json.loads(video_json_page)
 160             status = video_json['status']
 161             if status == self._PASSWORD_NOT_VERIFIED:
 162                 raise ExtractorError('Video password is invalid', expected=True)
 163
 164         if status != self._SUCCESS:
 165             raise ExtractorError('Unexpected status value %s' % status)
 166
 167         # Extract the URL of the video
 168         video_url = video_json['file_data']
 169
 170         # Video JSON does not provide enough meta data
 171         # We will extract some from the video web page instead
 172         video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id
 173         video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page')
 174
 175         # Warning if video is unavailable
 176         warning = self._html_search_regex(
 177             r'<div class="videoUnModer">(.*?)</div>', video_page,
 178             'warning message', default=None)
 179         if warning is not None:
 180             self._downloader.report_warning(
 181                 'Video %s may not be available; smotri said: %s ' %
 182                 (video_id, warning))
 183
 184         # Adult content
 185         if re.search('EroConfirmText">', video_page) is not None:
 186             self.report_age_confirmation()
 187             confirm_string = self._html_search_regex(
 188                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
 189                 video_page, 'confirm string')
 190             confirm_url = video_page_url + '&confirm=%s' % confirm_string
 191             video_page = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
 192             adult_content = True
 193         else:
 194             adult_content = False
 195
 196         # Extract the rest of meta data
 197         video_title = self._search_meta('name', video_page, 'title')
 198         if not video_title:
 199             video_title = os.path.splitext(url_basename(video_url))[0]
 200
 201         video_description = self._search_meta('description', video_page)
 202         END_TEXT = ' на сайте Smotri.com'
 203         if video_description and video_description.endswith(END_TEXT):
 204             video_description = video_description[:-len(END_TEXT)]
 205         START_TEXT = 'Смотреть онлайн ролик '
 206         if video_description and video_description.startswith(START_TEXT):
 207             video_description = video_description[len(START_TEXT):]
 208         video_thumbnail = self._search_meta('thumbnail', video_page)
 209
 210         upload_date_str = self._search_meta('uploadDate', video_page, 'upload date')
 211         if upload_date_str:
 212             upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str)
 213             video_upload_date = (
 214                 (
 215                     upload_date_m.group('year') +
 216                     upload_date_m.group('month') +
 217                     upload_date_m.group('day')
 218                 )
 219                 if upload_date_m else None
 220             )
 221         else:
 222             video_upload_date = None
 223
 224         duration_str = self._search_meta('duration', video_page)
 225         if duration_str:
 226             duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str)
 227             video_duration = (
 228                 (
 229                     (int(duration_m.group('hours')) * 60 * 60) +
 230                     (int(duration_m.group('minutes')) * 60) +
 231                     int(duration_m.group('seconds'))
 232                 )
 233                 if duration_m else None
 234             )
 235         else:
 236             video_duration = None
 237
 238         video_uploader = self._html_search_regex(
 239             '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
 240             video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
 241
 242         video_uploader_id = self._html_search_regex(
 243             '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
 244             video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
 245
 246         video_view_count = self._html_search_regex(
 247             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
 248             video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
 249
 250         return {
 251             'id': video_id,
 252             'url': video_url,
 253             'title': video_title,
 254             'thumbnail': video_thumbnail,
 255             'description': video_description,
 256             'uploader': video_uploader,
 257             'upload_date': video_upload_date,
 258             'uploader_id': video_uploader_id,
 259             'duration': video_duration,
 260             'view_count': int_or_none(video_view_count),
 261             'age_limit': 18 if adult_content else 0,
 262             'video_page_url': video_page_url
 263         }
 264
 265
 266 class SmotriCommunityIE(InfoExtractor):
 267     IE_DESC = 'Smotri.com community videos'
 268     IE_NAME = 'smotri:community'
 269     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
 270     _TEST = {
 271         'url': 'http://smotri.com/community/video/kommuna',
 272         'info_dict': {
 273             'id': 'kommuna',
 274             'title': 'КПРФ',
 275         },
 276         'playlist_mincount': 4,
 277     }
 278
 279     def _real_extract(self, url):
 280         mobj = re.match(self._VALID_URL, url)
 281         community_id = mobj.group('communityid')
 282
 283         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
 284         rss = self._download_xml(url, community_id, 'Downloading community RSS')
 285
 286         entries = [self.url_result(video_url.text, 'Smotri')
 287                    for video_url in rss.findall('./channel/item/link')]
 288
 289         description_text = rss.find('./channel/description').text
 290         community_title = self._html_search_regex(
 291             '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 292
 293         return self.playlist_result(entries, community_id, community_title)
 294
 295
 296 class SmotriUserIE(InfoExtractor):
 297     IE_DESC = 'Smotri.com user videos'
 298     IE_NAME = 'smotri:user'
 299     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 300     _TESTS = [{
 301         'url': 'http://smotri.com/user/inspector',
 302         'info_dict': {
 303             'id': 'inspector',
 304             'title': 'Inspector',
 305         },
 306         'playlist_mincount': 9,
 307     }]
 308
 309     def _real_extract(self, url):
 310         mobj = re.match(self._VALID_URL, url)
 311         user_id = mobj.group('userid')
 312
 313         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
 314         rss = self._download_xml(url, user_id, 'Downloading user RSS')
 315
 316         entries = [self.url_result(video_url.text, 'Smotri')
 317                    for video_url in rss.findall('./channel/item/link')]
 318
 319         description_text = rss.find('./channel/description').text
 320         user_nickname = self._html_search_regex(
 321             '^Видео режиссера (.*)$', description_text,
 322             'user nickname')
 323
 324         return self.playlist_result(entries, user_id, user_nickname)
 325
 326
 327 class SmotriBroadcastIE(InfoExtractor):
 328     IE_DESC = 'Smotri.com broadcasts'
 329     IE_NAME = 'smotri:broadcast'
 330     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 331
 332     def _real_extract(self, url):
 333         mobj = re.match(self._VALID_URL, url)
 334         broadcast_id = mobj.group('broadcastid')
 335
 336         broadcast_url = 'http://' + mobj.group('url')
 337         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 338
 339         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 340             raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True)
 341
 342         # Adult content
 343         if re.search('EroConfirmText">', broadcast_page) is not None:
 344
 345             (username, password) = self._get_login_info()
 346             if username is None:
 347                 raise ExtractorError('Erotic broadcasts allowed only for registered users, '
 348                     'use --username and --password options to provide account credentials.', expected=True)
 349
 350             login_form = {
 351                 'login-hint53': '1',
 352                 'confirm_erotic': '1',
 353                 'login': username,
 354                 'password': password,
 355             }
 356
 357             request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
 358             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 359             broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age')
 360
 361             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
 362                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 363
 364             adult_content = True
 365         else:
 366             adult_content = False
 367
 368         ticket = self._html_search_regex(
 369             'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
 370             broadcast_page, 'broadcast ticket')
 371
 372         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 373
 374         broadcast_password = self._downloader.params.get('videopassword', None)
 375         if broadcast_password:
 376             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 377
 378         broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON')
 379
 380         try:
 381             broadcast_json = json.loads(broadcast_json_page)
 382
 383             protected_broadcast = broadcast_json['_pass_protected'] == 1
 384             if protected_broadcast and not broadcast_password:
 385                 raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True)
 386
 387             broadcast_offline = broadcast_json['is_play'] == 0
 388             if broadcast_offline:
 389                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 390
 391             rtmp_url = broadcast_json['_server']
 392             if not rtmp_url.startswith('rtmp://'):
 393                 raise ExtractorError('Unexpected broadcast rtmp URL')
 394
 395             broadcast_playpath = broadcast_json['_streamName']
 396             broadcast_thumbnail = broadcast_json['_imgURL']
 397             broadcast_title = broadcast_json['title']
 398             broadcast_description = broadcast_json['description']
 399             broadcaster_nick = broadcast_json['nick']
 400             broadcaster_login = broadcast_json['login']
 401             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 402         except KeyError:
 403             if protected_broadcast:
 404                 raise ExtractorError('Bad broadcast password', expected=True)
 405             raise ExtractorError('Unexpected broadcast JSON')
 406
 407         return {
 408             'id': broadcast_id,
 409             'url': rtmp_url,
 410             'title': broadcast_title,
 411             'thumbnail': broadcast_thumbnail,
 412             'description': broadcast_description,
 413             'uploader': broadcaster_nick,
 414             'uploader_id': broadcaster_login,
 415             'age_limit': 18 if adult_content else 0,
 416             'ext': 'flv',
 417             'play_path': broadcast_playpath,
 418             'rtmp_live': True,
 419             'rtmp_conn': rtmp_conn
 420         }