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 )
  17
  18
  19 class SmotriIE(InfoExtractor):
  20     IE_DESC = 'Smotri.com'
  21     IE_NAME = 'smotri'
  22     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))'
  23     _NETRC_MACHINE = 'smotri'
  24
  25     _TESTS = [
  26         # real video id 2610366
  27         {
  28             'url': 'http://smotri.com/video/view/?id=v261036632ab',
  29             'file': 'v261036632ab.mp4',
  30             'md5': '2a7b08249e6f5636557579c368040eb9',
  31             'info_dict': {
  32                 'title': 'катастрофа с камер видеонаблюдения',
  33                 'uploader': 'rbc2008',
  34                 'uploader_id': 'rbc08',
  35                 'upload_date': '20131118',
  36                 'description': 'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
  37                 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
  38             },
  39         },
  40         # real video id 57591
  41         {
  42             'url': 'http://smotri.com/video/view/?id=v57591cb20',
  43             'file': 'v57591cb20.flv',
  44             'md5': '830266dfc21f077eac5afd1883091bcd',
  45             'info_dict': {
  46                 'title': 'test',
  47                 'uploader': 'Support Photofile@photofile',
  48                 'uploader_id': 'support-photofile',
  49                 'upload_date': '20070704',
  50                 'description': 'test, видео test',
  51                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
  52             },
  53         },
  54         # video-password
  55         {
  56             'url': 'http://smotri.com/video/view/?id=v1390466a13c',
  57             'file': 'v1390466a13c.mp4',
  58             'md5': 'f6331cef33cad65a0815ee482a54440b',
  59             'info_dict': {
  60                 'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
  61                 'uploader': 'timoxa40',
  62                 'uploader_id': 'timoxa40',
  63                 'upload_date': '20100404',
  64                 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
  65                 'description': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
  66             },
  67             'params': {
  68                 'videopassword': 'qwerty',
  69             },
  70         },
  71         # age limit + video-password
  72         {
  73             'url': 'http://smotri.com/video/view/?id=v15408898bcf',
  74             'file': 'v15408898bcf.flv',
  75             'md5': '91e909c9f0521adf5ee86fbe073aad70',
  76             'info_dict': {
  77                 'title': 'этот ролик не покажут по ТВ',
  78                 'uploader': 'zzxxx',
  79                 'uploader_id': 'ueggb',
  80                 'upload_date': '20101001',
  81                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
  82                 'age_limit': 18,
  83                 'description': 'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
  84             },
  85             'params': {
  86                 'videopassword': '333'
  87             }
  88         }
  89     ]
  90
  91     _SUCCESS = 0
  92     _PASSWORD_NOT_VERIFIED = 1
  93     _PASSWORD_DETECTED = 2
  94     _VIDEO_NOT_FOUND = 3
  95
  96     def _search_meta(self, name, html, display_name=None):
  97         if display_name is None:
  98             display_name = name
  99         return self._html_search_regex(
 100             r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
 101             html, display_name, fatal=False)
 102         return self._html_search_meta(name, html, display_name)
 103
 104     def _real_extract(self, url):
 105         mobj = re.match(self._VALID_URL, url)
 106         video_id = mobj.group('videoid')
 107         real_video_id = mobj.group('realvideoid')
 108
 109         # Download video JSON data
 110         video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id
 111         video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON')
 112         video_json = json.loads(video_json_page)
 113
 114         status = video_json['status']
 115         if status == self._VIDEO_NOT_FOUND:
 116             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 117         elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with
 118                                                 # video-password set
 119             video_password = self._downloader.params.get('videopassword', None)
 120             if not video_password:
 121                 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 122             video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest()
 123             video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON (video-password set)')
 124             video_json = json.loads(video_json_page)
 125             status = video_json['status']
 126             if status == self._PASSWORD_NOT_VERIFIED:
 127                 raise ExtractorError('Video password is invalid', expected=True)
 128
 129         if status != self._SUCCESS:
 130             raise ExtractorError('Unexpected status value %s' % status)
 131
 132         # Extract the URL of the video
 133         video_url = video_json['file_data']
 134
 135         # Video JSON does not provide enough meta data
 136         # We will extract some from the video web page instead
 137         video_page_url = 'http://' + mobj.group('url')
 138         video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page')
 139
 140         # Warning if video is unavailable
 141         warning = self._html_search_regex(
 142             r'<div class="videoUnModer">(.*?)</div>', video_page,
 143             'warning message', default=None)
 144         if warning is not None:
 145             self._downloader.report_warning(
 146                 'Video %s may not be available; smotri said: %s ' %
 147                 (video_id, warning))
 148
 149         # Adult content
 150         if re.search('EroConfirmText">', video_page) is not None:
 151             self.report_age_confirmation()
 152             confirm_string = self._html_search_regex(
 153                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
 154                 video_page, 'confirm string')
 155             confirm_url = video_page_url + '&confirm=%s' % confirm_string
 156             video_page = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
 157             adult_content = True
 158         else:
 159             adult_content = False
 160
 161         # Extract the rest of meta data
 162         video_title = self._search_meta('name', video_page, 'title')
 163         if not video_title:
 164             video_title = os.path.splitext(url_basename(video_url))[0]
 165
 166         video_description = self._search_meta('description', video_page)
 167         END_TEXT = ' на сайте Smotri.com'
 168         if video_description and video_description.endswith(END_TEXT):
 169             video_description = video_description[:-len(END_TEXT)]
 170         START_TEXT = 'Смотреть онлайн ролик '
 171         if video_description and video_description.startswith(START_TEXT):
 172             video_description = video_description[len(START_TEXT):]
 173         video_thumbnail = self._search_meta('thumbnail', video_page)
 174
 175         upload_date_str = self._search_meta('uploadDate', video_page, 'upload date')
 176         if upload_date_str:
 177             upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str)
 178             video_upload_date = (
 179                 (
 180                     upload_date_m.group('year') +
 181                     upload_date_m.group('month') +
 182                     upload_date_m.group('day')
 183                 )
 184                 if upload_date_m else None
 185             )
 186         else:
 187             video_upload_date = None
 188
 189         duration_str = self._search_meta('duration', video_page)
 190         if duration_str:
 191             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)
 192             video_duration = (
 193                 (
 194                     (int(duration_m.group('hours')) * 60 * 60) +
 195                     (int(duration_m.group('minutes')) * 60) +
 196                     int(duration_m.group('seconds'))
 197                 )
 198                 if duration_m else None
 199             )
 200         else:
 201             video_duration = None
 202
 203         video_uploader = self._html_search_regex(
 204             '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
 205             video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
 206
 207         video_uploader_id = self._html_search_regex(
 208             '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
 209             video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
 210
 211         video_view_count = self._html_search_regex(
 212             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
 213             video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
 214
 215         return {
 216             'id': video_id,
 217             'url': video_url,
 218             'title': video_title,
 219             'thumbnail': video_thumbnail,
 220             'description': video_description,
 221             'uploader': video_uploader,
 222             'upload_date': video_upload_date,
 223             'uploader_id': video_uploader_id,
 224             'duration': video_duration,
 225             'view_count': video_view_count,
 226             'age_limit': 18 if adult_content else 0,
 227             'video_page_url': video_page_url
 228         }
 229
 230
 231 class SmotriCommunityIE(InfoExtractor):
 232     IE_DESC = 'Smotri.com community videos'
 233     IE_NAME = 'smotri:community'
 234     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
 235
 236     def _real_extract(self, url):
 237         mobj = re.match(self._VALID_URL, url)
 238         community_id = mobj.group('communityid')
 239
 240         url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
 241         rss = self._download_xml(url, community_id, 'Downloading community RSS')
 242
 243         entries = [self.url_result(video_url.text, 'Smotri')
 244                    for video_url in rss.findall('./channel/item/link')]
 245
 246         description_text = rss.find('./channel/description').text
 247         community_title = self._html_search_regex(
 248             '^Видео сообщества "([^"]+)"$', description_text, 'community title')
 249
 250         return self.playlist_result(entries, community_id, community_title)
 251
 252
 253 class SmotriUserIE(InfoExtractor):
 254     IE_DESC = 'Smotri.com user videos'
 255     IE_NAME = 'smotri:user'
 256     _VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
 257
 258     def _real_extract(self, url):
 259         mobj = re.match(self._VALID_URL, url)
 260         user_id = mobj.group('userid')
 261
 262         url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
 263         rss = self._download_xml(url, user_id, 'Downloading user RSS')
 264
 265         entries = [self.url_result(video_url.text, 'Smotri')
 266                    for video_url in rss.findall('./channel/item/link')]
 267
 268         description_text = rss.find('./channel/description').text
 269         user_nickname = self._html_search_regex(
 270             '^Видео режиссера (.*)$', description_text,
 271             'user nickname')
 272
 273         return self.playlist_result(entries, user_id, user_nickname)
 274
 275
 276 class SmotriBroadcastIE(InfoExtractor):
 277     IE_DESC = 'Smotri.com broadcasts'
 278     IE_NAME = 'smotri:broadcast'
 279     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
 280
 281     def _real_extract(self, url):
 282         mobj = re.match(self._VALID_URL, url)
 283         broadcast_id = mobj.group('broadcastid')
 284
 285         broadcast_url = 'http://' + mobj.group('url')
 286         broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
 287
 288         if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
 289             raise ExtractorError('Broadcast %s does not exist' % broadcast_id, expected=True)
 290
 291         # Adult content
 292         if re.search('EroConfirmText">', broadcast_page) is not None:
 293
 294             (username, password) = self._get_login_info()
 295             if username is None:
 296                 raise ExtractorError('Erotic broadcasts allowed only for registered users, '
 297                     'use --username and --password options to provide account credentials.', expected=True)
 298
 299             login_form = {
 300                 'login-hint53': '1',
 301                 'confirm_erotic': '1',
 302                 'login': username,
 303                 'password': password,
 304             }
 305
 306             request = compat_urllib_request.Request(broadcast_url + '/?no_redirect=1', compat_urllib_parse.urlencode(login_form))
 307             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 308             broadcast_page = self._download_webpage(request, broadcast_id, 'Logging in and confirming age')
 309
 310             if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
 311                 raise ExtractorError('Unable to log in: bad username or password', expected=True)
 312
 313             adult_content = True
 314         else:
 315             adult_content = False
 316
 317         ticket = self._html_search_regex(
 318             'window\.broadcast_control\.addFlashVar\\(\'file\', \'([^\']+)\'\\);',
 319             broadcast_page, 'broadcast ticket')
 320
 321         url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
 322
 323         broadcast_password = self._downloader.params.get('videopassword', None)
 324         if broadcast_password:
 325             url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
 326
 327         broadcast_json_page = self._download_webpage(url, broadcast_id, 'Downloading broadcast JSON')
 328
 329         try:
 330             broadcast_json = json.loads(broadcast_json_page)
 331
 332             protected_broadcast = broadcast_json['_pass_protected'] == 1
 333             if protected_broadcast and not broadcast_password:
 334                 raise ExtractorError('This broadcast is protected by a password, use the --video-password option', expected=True)
 335
 336             broadcast_offline = broadcast_json['is_play'] == 0
 337             if broadcast_offline:
 338                 raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
 339
 340             rtmp_url = broadcast_json['_server']
 341             if not rtmp_url.startswith('rtmp://'):
 342                 raise ExtractorError('Unexpected broadcast rtmp URL')
 343
 344             broadcast_playpath = broadcast_json['_streamName']
 345             broadcast_thumbnail = broadcast_json['_imgURL']
 346             broadcast_title = broadcast_json['title']
 347             broadcast_description = broadcast_json['description']
 348             broadcaster_nick = broadcast_json['nick']
 349             broadcaster_login = broadcast_json['login']
 350             rtmp_conn = 'S:%s' % uuid.uuid4().hex
 351         except KeyError:
 352             if protected_broadcast:
 353                 raise ExtractorError('Bad broadcast password', expected=True)
 354             raise ExtractorError('Unexpected broadcast JSON')
 355
 356         return {
 357             'id': broadcast_id,
 358             'url': rtmp_url,
 359             'title': broadcast_title,
 360             'thumbnail': broadcast_thumbnail,
 361             'description': broadcast_description,
 362             'uploader': broadcaster_nick,
 363             'uploader_id': broadcaster_login,
 364             'age_limit': 18 if adult_content else 0,
 365             'ext': 'flv',
 366             'play_path': broadcast_playpath,
 367             'rtmp_live': True,
 368             'rtmp_conn': rtmp_conn
 369         }