[Rte] Improve extractor
[youtube-dl] / youtube_dl / extractor / trutube.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class TruTubeIE(InfoExtractor):
9     _VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P<id>[0-9]+)/.*'
10     _TEST = {
11         'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-',
12         'md5': 'c5b6e301b0a2040b074746cbeaa26ca1',
13         'info_dict': {
14             'id': '14880',
15             'ext': 'flv',
16             'title': 'Ramses II - Proven To Be A Red Headed Caucasoid',
17             'thumbnail': 're:^http:.*\.jpg$',
18         }
19     }
20
21     def _real_extract(self, url):
22         mobj = re.match(self._VALID_URL, url)
23         video_id = mobj.group('id')
24
25         webpage = self._download_webpage(url, video_id)
26         video_title = self._og_search_title(webpage).strip()
27         thumbnail = self._search_regex(
28             r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False)
29
30         all_formats = re.finditer(
31             r"var (?P<key>[a-z]+)_video_file\s*=\s*'(?P<url>[^']+)';", webpage)
32         formats = [{
33             'format_id': m.group('key'),
34             'quality': -i,
35             'url': m.group('url'),
36         } for i, m in enumerate(all_formats)]
37         self._sort_formats(formats)
38
39         return {
40             'id': video_id,
41             'title': video_title,
42             'formats': formats,
43             'thumbnail': thumbnail,
44         }