]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/ro220.py
[brightcove:new] extract subtitles and strip video title
[youtube-dl] / youtube_dl / extractor / ro220.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..compat import compat_urllib_parse_unquote
5
6
7 class Ro220IE(InfoExtractor):
8     IE_NAME = '220.ro'
9     _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<id>[^/]+)'
10     _TEST = {
11         'url': 'http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/',
12         'md5': '03af18b73a07b4088753930db7a34add',
13         'info_dict': {
14             'id': 'LYV6doKo7f',
15             'ext': 'mp4',
16             'title': 'Luati-le Banii sez 4 ep 1',
17             'description': 're:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$',
18         }
19     }
20
21     def _real_extract(self, url):
22         video_id = self._match_id(url)
23
24         webpage = self._download_webpage(url, video_id)
25         url = compat_urllib_parse_unquote(self._search_regex(
26             r'(?s)clip\s*:\s*{.*?url\s*:\s*\'([^\']+)\'', webpage, 'url'))
27         title = self._og_search_title(webpage)
28         description = self._og_search_description(webpage)
29         thumbnail = self._og_search_thumbnail(webpage)
30
31         formats = [{
32             'format_id': 'sd',
33             'url': url,
34             'ext': 'mp4',
35         }]
36
37         return {
38             'id': video_id,
39             'formats': formats,
40             'title': title,
41             'description': description,
42             'thumbnail': thumbnail,
43         }