[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / motorsport.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import (
6     compat_urlparse,
7 )
8
9
10 class MotorsportIE(InfoExtractor):
11     IE_DESC = 'motorsport.com'
12     _VALID_URL = r'https?://(?:www\.)?motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
13     _TEST = {
14         'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
15         'info_dict': {
16             'id': '2-T3WuR-KMM',
17             'ext': 'mp4',
18             'title': 'Red Bull Racing: 2014 Rules Explained',
19             'duration': 208,
20             'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
21             'uploader': 'mcomstaff',
22             'uploader_id': 'UC334JIYKkVnyFoNCclfZtHQ',
23             'upload_date': '20140903',
24             'thumbnail': r're:^https?://.+\.jpg$'
25         },
26         'add_ie': ['Youtube'],
27         'params': {
28             'skip_download': True,
29         },
30     }
31
32     def _real_extract(self, url):
33         display_id = self._match_id(url)
34         webpage = self._download_webpage(url, display_id)
35
36         iframe_path = self._html_search_regex(
37             r'<iframe id="player_iframe"[^>]+src="([^"]+)"', webpage,
38             'iframe path')
39         iframe = self._download_webpage(
40             compat_urlparse.urljoin(url, iframe_path), display_id,
41             'Downloading iframe')
42         youtube_id = self._search_regex(
43             r'www.youtube.com/embed/(.{11})', iframe, 'youtube id')
44
45         return {
46             '_type': 'url_transparent',
47             'display_id': display_id,
48             'url': 'https://youtube.com/watch?v=%s' % youtube_id,
49         }