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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     compat_urllib_request,
  11     compat_urllib_parse,
  12     compat_str,
  13     unescapeHTML,
  14 )
  15
  16
  17 class VKIE(InfoExtractor):
  18     IE_NAME = 'vk.com'
  19     _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
  20     _NETRC_MACHINE = 'vk'
  21
  22     _TESTS = [
  23         {
  24             'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
  25             'md5': '0deae91935c54e00003c2a00646315f0',
  26             'info_dict': {
  27                 'id': '162222515',
  28                 'ext': 'flv',
  29                 'title': 'ProtivoGunz - Хуёвая песня',
  30                 'uploader': 're:Noize MC.*',
  31                 'duration': 195,
  32             },
  33         },
  34         {
  35             'url': 'http://vk.com/video4643923_163339118',
  36             'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
  37             'info_dict': {
  38                 'id': '163339118',
  39                 'ext': 'mp4',
  40                 'uploader': 'Elya Iskhakova',
  41                 'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
  42                 'duration': 558,
  43             }
  44         },
  45         {
  46             'note': 'Embedded video',
  47             'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
  48             'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
  49             'info_dict': {
  50                 'id': '162925554',
  51                 'ext': 'mp4',
  52                 'uploader': 'Vladimir Gavrin',
  53                 'title': 'Lin Dan',
  54                 'duration': 101,
  55             }
  56         },
  57         {
  58             'url': 'http://vk.com/video-8871596_164049491',
  59             'md5': 'a590bcaf3d543576c9bd162812387666',
  60             'note': 'Only available for registered users',
  61             'info_dict': {
  62                 'id': '164049491',
  63                 'ext': 'mp4',
  64                 'uploader': 'Триллеры',
  65                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
  66                 'duration': 8352,
  67             },
  68             'skip': 'Requires vk account credentials',
  69         },
  70         {
  71             'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
  72             'md5': 'd82c22e449f036282d1d3f7f4d276869',
  73             'info_dict': {
  74                 'id': '166094326',
  75                 'ext': 'mp4',
  76                 'uploader': 'Киномания - лучшее из мира кино',
  77                 'title': 'Запах женщины (1992)',
  78                 'duration': 9392,
  79             },
  80             'skip': 'Requires vk account credentials',
  81         },
  82         {
  83             'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
  84             'md5': '4d7a5ef8cf114dfa09577e57b2993202',
  85             'info_dict': {
  86                 'id': '168067957',
  87                 'ext': 'mp4',
  88                 'uploader': 'Киномания - лучшее из мира кино',
  89                 'title': ' ',
  90                 'duration': 7291,
  91             },
  92             'skip': 'Requires vk account credentials',
  93         },
  94         {
  95             'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
  96             'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
  97             'note': 'ivi.ru embed',
  98             'info_dict': {
  99                 'id': '60690',
 100                 'ext': 'mp4',
 101                 'title': 'Книга Илая',
 102                 'duration': 6771,
 103             },
 104             'skip': 'Only works from Russia',
 105         },
 106     ]
 107
 108     def _login(self):
 109         (username, password) = self._get_login_info()
 110         if username is None:
 111             return
 112
 113         login_form = {
 114             'act': 'login',
 115             'role': 'al_frame',
 116             'expire': '1',
 117             'email': username,
 118             'pass': password,
 119         }
 120
 121         request = compat_urllib_request.Request('https://login.vk.com/?act=login',
 122             compat_urllib_parse.urlencode(login_form).encode('utf-8'))
 123         login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
 124
 125         if re.search(r'onLoginFailed', login_page):
 126             raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
 127
 128     def _real_initialize(self):
 129         self._login()
 130
 131     def _real_extract(self, url):
 132         mobj = re.match(self._VALID_URL, url)
 133         video_id = mobj.group('videoid')
 134
 135         if not video_id:
 136             video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
 137
 138         info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
 139         info_page = self._download_webpage(info_url, video_id)
 140
 141         if re.search(r'<!>Please log in or <', info_page):
 142             raise ExtractorError('This video is only available for registered users, '
 143                 'use --username and --password options to provide account credentials.', expected=True)
 144
 145         m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
 146         if m_yt is not None:
 147             self.to_screen('Youtube video detected')
 148             return self.url_result(m_yt.group(1), 'Youtube')
 149
 150         m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
 151         if m_opts:
 152             m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))
 153             if m_opts_url:
 154                 opts_url = m_opts_url.group(1)
 155                 if opts_url.startswith('//'):
 156                     opts_url = 'http:' + opts_url
 157                 return self.url_result(opts_url)
 158
 159         data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
 160         data = json.loads(data_json)
 161
 162         formats = [{
 163             'format_id': k,
 164             'url': v,
 165             'width': int(k[len('url'):]),
 166         } for k, v in data.items()
 167             if k.startswith('url')]
 168         self._sort_formats(formats)
 169
 170         return {
 171             'id': compat_str(data['vid']),
 172             'formats': formats,
 173             'title': unescapeHTML(data['md_title']),
 174             'thumbnail': data.get('jpg'),
 175             'uploader': data.get('md_author'),
 176             'duration': data.get('duration')
 177         }