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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urlparse
   7 from ..utils import (
   8     ExtractorError,
   9     NO_DEFAULT,
  10     encode_dict,
  11     sanitized_Request,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class NovaMovIE(InfoExtractor):
  17     IE_NAME = 'novamov'
  18     IE_DESC = 'NovaMov'
  19
  20     _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video|mobile/#/videos)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
  21     _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
  22
  23     _HOST = 'www.novamov.com'
  24
  25     _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
  26     _FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);'
  27     _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
  28     _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
  29     _URL_TEMPLATE = 'http://%s/video/%s'
  30
  31     _TEST = {
  32         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
  33         'md5': '7205f346a52bbeba427603ba10d4b935',
  34         'info_dict': {
  35             'id': '4rurhn9x446jj',
  36             'ext': 'flv',
  37             'title': 'search engine optimization',
  38             'description': 'search engine optimization is used to rank the web page in the google search engine'
  39         },
  40         'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
  41     }
  42
  43     def _check_existence(self, webpage, video_id):
  44         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  45             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49
  50         url = self._URL_TEMPLATE % (self._HOST, video_id)
  51
  52         webpage = self._download_webpage(
  53             url, video_id, 'Downloading video page')
  54
  55         self._check_existence(webpage, video_id)
  56
  57         def extract_filekey(default=NO_DEFAULT):
  58             filekey = self._search_regex(
  59                 self._FILEKEY_REGEX, webpage, 'filekey', default=default)
  60             if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
  61                 return self._search_regex(
  62                     r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default)
  63             else:
  64                 return filekey
  65
  66         filekey = extract_filekey(default=None)
  67
  68         if not filekey:
  69             fields = self._hidden_inputs(webpage)
  70             post_url = self._search_regex(
  71                 r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
  72                 'post url', default=url, group='url')
  73             if not post_url.startswith('http'):
  74                 post_url = compat_urlparse.urljoin(url, post_url)
  75             request = sanitized_Request(
  76                 post_url, urlencode_postdata(encode_dict(fields)))
  77             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  78             request.add_header('Referer', post_url)
  79             webpage = self._download_webpage(
  80                 request, video_id, 'Downloading continue to the video page')
  81             self._check_existence(webpage, video_id)
  82
  83         filekey = extract_filekey()
  84
  85         title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
  86         description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
  87
  88         api_response = self._download_webpage(
  89             'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
  90             'Downloading video api response')
  91
  92         response = compat_urlparse.parse_qs(api_response)
  93
  94         if 'error_msg' in response:
  95             raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
  96
  97         video_url = response['url'][0]
  98
  99         return {
 100             'id': video_id,
 101             'url': video_url,
 102             'title': title,
 103             'description': description
 104         }
 105
 106
 107 class WholeCloudIE(NovaMovIE):
 108     IE_NAME = 'wholecloud'
 109     IE_DESC = 'WholeCloud'
 110
 111     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
 112
 113     _HOST = 'www.wholecloud.net'
 114
 115     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 116     _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
 117     _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
 118
 119     _TEST = {
 120         'url': 'http://www.wholecloud.net/video/559e28be54d96',
 121         'md5': 'abd31a2132947262c50429e1d16c1bfd',
 122         'info_dict': {
 123             'id': '559e28be54d96',
 124             'ext': 'flv',
 125             'title': 'dissapeared image',
 126             'description': 'optical illusion  dissapeared image  magic illusion',
 127         }
 128     }
 129
 130
 131 class NowVideoIE(NovaMovIE):
 132     IE_NAME = 'nowvideo'
 133     IE_DESC = 'NowVideo'
 134
 135     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
 136
 137     _HOST = 'www.nowvideo.to'
 138
 139     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 140     _TITLE_REGEX = r'<h4>([^<]+)</h4>'
 141     _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
 142
 143     _TEST = {
 144         'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b',
 145         'md5': '12c82cad4f2084881d8bc60ee29df092',
 146         'info_dict': {
 147             'id': 'f1d6fce9a968b',
 148             'ext': 'flv',
 149             'title': 'youtubedl test video BaWjenozKc',
 150             'description': 'Description',
 151         },
 152     }
 153
 154
 155 class VideoWeedIE(NovaMovIE):
 156     IE_NAME = 'videoweed'
 157     IE_DESC = 'VideoWeed'
 158
 159     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
 160
 161     _HOST = 'www.videoweed.es'
 162
 163     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 164     _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
 165     _URL_TEMPLATE = 'http://%s/file/%s'
 166
 167     _TEST = {
 168         'url': 'http://www.videoweed.es/file/b42178afbea14',
 169         'md5': 'abd31a2132947262c50429e1d16c1bfd',
 170         'info_dict': {
 171             'id': 'b42178afbea14',
 172             'ext': 'flv',
 173             'title': 'optical illusion  dissapeared image magic illusion',
 174             'description': ''
 175         },
 176     }
 177
 178
 179 class CloudTimeIE(NovaMovIE):
 180     IE_NAME = 'cloudtime'
 181     IE_DESC = 'CloudTime'
 182
 183     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
 184
 185     _HOST = 'www.cloudtime.to'
 186
 187     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 188     _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
 189
 190     _TEST = None