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)/|(?:(?: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
  30     _TEST = {
  31         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
  32         'md5': '7205f346a52bbeba427603ba10d4b935',
  33         'info_dict': {
  34             'id': '4rurhn9x446jj',
  35             'ext': 'flv',
  36             'title': 'search engine optimization',
  37             'description': 'search engine optimization is used to rank the web page in the google search engine'
  38         },
  39         'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
  40     }
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44
  45         url = 'http://%s/video/%s' % (self._HOST, video_id)
  46
  47         webpage = self._download_webpage(
  48             url, video_id, 'Downloading video page')
  49
  50         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  51             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  52
  53         def extract_filekey(default=NO_DEFAULT):
  54             return self._search_regex(
  55                 self._FILEKEY_REGEX, webpage, 'filekey', default=default)
  56
  57         filekey = extract_filekey(default=None)
  58
  59         if not filekey:
  60             fields = self._hidden_inputs(webpage)
  61             post_url = self._search_regex(
  62                 r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
  63                 'post url', default=url, group='url')
  64             if not post_url.startswith('http'):
  65                 post_url = compat_urlparse.urljoin(url, post_url)
  66             request = sanitized_Request(
  67                 post_url, urlencode_postdata(encode_dict(fields)))
  68             request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  69             request.add_header('Referer', post_url)
  70             webpage = self._download_webpage(
  71                 request, video_id, 'Downloading continue to the video page')
  72
  73         filekey = extract_filekey()
  74
  75         title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
  76         description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
  77
  78         api_response = self._download_webpage(
  79             'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
  80             'Downloading video api response')
  81
  82         response = compat_urlparse.parse_qs(api_response)
  83
  84         if 'error_msg' in response:
  85             raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
  86
  87         video_url = response['url'][0]
  88
  89         return {
  90             'id': video_id,
  91             'url': video_url,
  92             'title': title,
  93             'description': description
  94         }
  95
  96
  97 class WholeCloudIE(NovaMovIE):
  98     IE_NAME = 'wholecloud'
  99     IE_DESC = 'WholeCloud'
 100
 101     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'}
 102
 103     _HOST = 'www.wholecloud.net'
 104
 105     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 106     _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
 107     _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
 108
 109     _TEST = {
 110         'url': 'http://www.wholecloud.net/video/559e28be54d96',
 111         'md5': 'abd31a2132947262c50429e1d16c1bfd',
 112         'info_dict': {
 113             'id': '559e28be54d96',
 114             'ext': 'flv',
 115             'title': 'dissapeared image',
 116             'description': 'optical illusion  dissapeared image  magic illusion',
 117         }
 118     }
 119
 120
 121 class NowVideoIE(NovaMovIE):
 122     IE_NAME = 'nowvideo'
 123     IE_DESC = 'NowVideo'
 124
 125     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
 126
 127     _HOST = 'www.nowvideo.to'
 128
 129     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 130     _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
 131     _TITLE_REGEX = r'<h4>([^<]+)</h4>'
 132     _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
 133
 134     _TEST = {
 135         'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
 136         'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
 137         'info_dict': {
 138             'id': '0mw0yow7b6dxa',
 139             'ext': 'flv',
 140             'title': 'youtubedl test video _BaW_jenozKc.mp4',
 141             'description': 'Description',
 142         }
 143     }
 144
 145
 146 class VideoWeedIE(NovaMovIE):
 147     IE_NAME = 'videoweed'
 148     IE_DESC = 'VideoWeed'
 149
 150     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'}
 151
 152     _HOST = 'www.videoweed.es'
 153
 154     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 155     _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
 156
 157     _TEST = {
 158         'url': 'http://www.videoweed.es/file/b42178afbea14',
 159         'md5': 'abd31a2132947262c50429e1d16c1bfd',
 160         'info_dict': {
 161             'id': 'b42178afbea14',
 162             'ext': 'flv',
 163             'title': 'optical illusion  dissapeared image magic illusion',
 164             'description': ''
 165         },
 166     }
 167
 168
 169 class CloudTimeIE(NovaMovIE):
 170     IE_NAME = 'cloudtime'
 171     IE_DESC = 'CloudTime'
 172
 173     _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'}
 174
 175     _HOST = 'www.cloudtime.to'
 176
 177     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
 178     _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
 179
 180     _TEST = None