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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_request,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     urlencode_postdata,
  13     xpath_text,
  14     xpath_with_ns,
  15 )
  16
  17 _x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
  18
  19
  20 class NosVideoIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
  22                  '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
  23     _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
  24     _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
  25     _TEST = {
  26         'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
  27         'md5': '6124ed47130d8be3eacae635b071e6b6',
  28         'info_dict': {
  29             'id': 'mu8fle7g7rpq',
  30             'ext': 'mp4',
  31             'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
  32             'thumbnail': 're:^https?://.*\.jpg$',
  33         }
  34     }
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         fields = {
  40             'id': video_id,
  41             'op': 'download1',
  42             'method_free': 'Continue to Video',
  43         }
  44         req = compat_urllib_request.Request(url, urlencode_postdata(fields))
  45         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  46         webpage = self._download_webpage(req, video_id,
  47                                          'Downloading download page')
  48         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  49             raise ExtractorError('Video %s does not exist' % video_id,
  50                                  expected=True)
  51
  52         xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
  53         playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
  54         playlist = self._download_xml(playlist_url, video_id)
  55
  56         track = playlist.find(_x('.//xspf:track'))
  57         if track is None:
  58             raise ExtractorError(
  59                 'XML playlist is missing the \'track\' element',
  60                 expected=True)
  61         title = xpath_text(track, _x('./xspf:title'), 'title')
  62         url = xpath_text(track, _x('./xspf:file'), 'URL', fatal=True)
  63         thumbnail = xpath_text(track, _x('./xspf:image'), 'thumbnail')
  64         if title is not None:
  65             title = title.strip()
  66
  67         formats = [{
  68             'format_id': 'sd',
  69             'url': url,
  70         }]
  71
  72         return {
  73             'id': video_id,
  74             'title': title,
  75             'thumbnail': thumbnail,
  76             'formats': formats,
  77         }