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

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