]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/anitube.py
23f942ae2d039cf92c9a67934a07d3062f744b0d
[youtubedl] / youtube_dl / extractor / anitube.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class AnitubeIE(InfoExtractor):
9 IE_NAME = 'anitube.se'
10 _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
11
12 _TEST = {
13 'url': 'http://www.anitube.se/video/36621',
14 'md5': '59d0eeae28ea0bc8c05e7af429998d43',
15 'info_dict': {
16 'id': '36621',
17 'ext': 'mp4',
18 'title': 'Recorder to Randoseru 01',
19 'duration': 180.19,
20 },
21 'skip': 'Blocked in the US',
22 }
23
24 def _real_extract(self, url):
25 mobj = re.match(self._VALID_URL, url)
26 video_id = mobj.group('id')
27
28 webpage = self._download_webpage(url, video_id)
29 key = self._search_regex(
30 r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
31
32 config_xml = self._download_xml(
33 'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)
34
35 video_title = config_xml.find('title').text
36 thumbnail = config_xml.find('image').text
37 duration = float(config_xml.find('duration').text)
38
39 formats = []
40 video_url = config_xml.find('file')
41 if video_url is not None:
42 formats.append({
43 'format_id': 'sd',
44 'url': video_url.text,
45 })
46 video_url = config_xml.find('filehd')
47 if video_url is not None:
48 formats.append({
49 'format_id': 'hd',
50 'url': video_url.text,
51 })
52
53 return {
54 'id': video_id,
55 'title': video_title,
56 'thumbnail': thumbnail,
57 'duration': duration,
58 'formats': formats
59 }