_ Git - youtube-dl/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 ..utils import (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10     xpath_with_ns,
  11 )
  12
  13 _x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
  14 _find = lambda el, p: el.find(_x(p)).text.strip()
  15
  16
  17 class NosVideoIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
  19                  '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
  20     _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
  21     _TEST = {
  22         'url': 'http://nosvideo.com/?v=drlp6s40kg54',
  23         'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c',
  24         'info_dict': {
  25             'id': 'drlp6s40kg54',
  26             'ext': 'mp4',
  27             'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
  28             'thumbnail': 're:^https?://.*\.jpg$',
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35
  36         fields = {
  37             'id': video_id,
  38             'op': 'download1',
  39             'method_free': 'Continue to Video',
  40         }
  41         post = compat_urllib_parse.urlencode(fields)
  42         req = compat_urllib_request.Request(url, post)
  43         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  44         webpage = self._download_webpage(req, video_id,
  45                                          'Downloading download page')
  46         xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
  47         playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
  48         playlist = self._download_xml(playlist_url, video_id)
  49
  50         track = playlist.find(_x('.//xspf:track'))
  51         title = _find(track, './xspf:title')
  52         url = _find(track, './xspf:file')
  53         thumbnail = _find(track, './xspf:image')
  54
  55         formats = [{
  56             'format_id': 'sd',
  57             'url': url,
  58         }]
  59
  60         return {
  61             'id': video_id,
  62             'title': title,
  63             'thumbnail': thumbnail,
  64             'formats': formats,
  65         }