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)/|(?:(?: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         }