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 ..compat import (
   6     compat_urllib_request,
   7 )
   8
   9
  10 class MovieClipsIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/(?P<id>[^/?#]+)'
  12     _TEST = {
  13         'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597?autoPlay=true&playlistId=5',
  14         'info_dict': {
  15             'id': 'pKIGmG83AqD9',
  16             'display_id': 'warcraft-trailer-1-561180739597',
  17             'ext': 'mp4',
  18             'title': 'Warcraft Trailer 1',
  19             'description': 'Watch Trailer 1 from Warcraft (2016). Legendary’s WARCRAFT is a 3D epic adventure of world-colliding conflict based.',
  20             'thumbnail': 're:^https?://.*\.jpg$',
  21         },
  22         'add_ie': ['ThePlatform'],
  23     }
  24
  25     def _real_extract(self, url):
  26         display_id = self._match_id(url)
  27
  28         req = compat_urllib_request.Request(url)
  29         # it doesn't work if it thinks the browser it's too old
  30         req.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/43.0 (Chrome)')
  31         webpage = self._download_webpage(req, display_id)
  32         theplatform_link = self._html_search_regex(r'src="(http://player.theplatform.com/p/.*?)"', webpage, 'theplatform link')
  33         title = self._html_search_regex(r'<title[^>]*>([^>]+)-\s*\d+\s*|\s*Movieclips.com</title>', webpage, 'title')
  34         description = self._html_search_meta('description', webpage)
  35
  36         return {
  37             '_type': 'url_transparent',
  38             'url': theplatform_link,
  39             'title': title,
  40             'display_id': display_id,
  41             'description': description,
  42         }