_ Git - youtube-dl/blob - youtube_dl/extractor/movieclips.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_urllib_request,
   6 )
   7
   8
   9 class MovieClipsIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/(?P<id>[^/?#]+)'
  11     _TEST = {
  12         'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597?autoPlay=true&playlistId=5',
  13         'info_dict': {
  14             'id': 'pKIGmG83AqD9',
  15             'display_id': 'warcraft-trailer-1-561180739597',
  16             'ext': 'mp4',
  17             'title': 'Warcraft Trailer 1',
  18             'description': 'Watch Trailer 1 from Warcraft (2016). Legendary’s WARCRAFT is a 3D epic adventure of world-colliding conflict based.',
  19             'thumbnail': 're:^https?://.*\.jpg$',
  20         },
  21         'add_ie': ['ThePlatform'],
  22     }
  23
  24     def _real_extract(self, url):
  25         display_id = self._match_id(url)
  26
  27         req = compat_urllib_request.Request(url)
  28         # it doesn't work if it thinks the browser it's too old
  29         req.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/43.0 (Chrome)')
  30         webpage = self._download_webpage(req, display_id)
  31         theplatform_link = self._html_search_regex(r'src="(http://player.theplatform.com/p/.*?)"', webpage, 'theplatform link')
  32         title = self._html_search_regex(r'<title[^>]*>([^>]+)-\s*\d+\s*|\s*Movieclips.com</title>', webpage, 'title')
  33         description = self._html_search_meta('description', webpage)
  34
  35         return {
  36             '_type': 'url_transparent',
  37             'url': theplatform_link,
  38             'title': title,
  39             'display_id': display_id,
  40             'description': description,
  41         }