[polskieradio] Add support for downloading whole programmes.
[youtube-dl] / youtube_dl / extractor / parliamentliveuk.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class ParliamentLiveUKIE(InfoExtractor):
9     IE_NAME = 'parliamentlive.tv'
10     IE_DESC = 'UK parliament videos'
11     _VALID_URL = r'https?://www\.parliamentlive\.tv/Main/Player\.aspx\?(?:[^&]+&)*?meetingId=(?P<id>[0-9]+)'
12
13     _TEST = {
14         'url': 'http://www.parliamentlive.tv/Main/Player.aspx?meetingId=15121&player=windowsmedia',
15         'info_dict': {
16             'id': '15121',
17             'ext': 'asf',
18             'title': 'hoc home affairs committee, 18 mar 2014.pm',
19             'description': 'md5:033b3acdf83304cd43946b2d5e5798d1',
20         },
21         'params': {
22             'skip_download': True,  # Requires mplayer (mms)
23         }
24     }
25
26     def _real_extract(self, url):
27         mobj = re.match(self._VALID_URL, url)
28         video_id = mobj.group('id')
29         webpage = self._download_webpage(url, video_id)
30
31         asx_url = self._html_search_regex(
32             r'embed.*?src="([^"]+)" name="MediaPlayer"', webpage,
33             'metadata URL')
34         asx = self._download_xml(asx_url, video_id, 'Downloading ASX metadata')
35         video_url = asx.find('.//REF').attrib['HREF']
36
37         title = self._search_regex(
38             r'''(?x)player\.setClipDetails\(
39                 (?:(?:[0-9]+|"[^"]+"),\s*){2}
40                 "([^"]+",\s*"[^"]+)"
41                 ''',
42             webpage, 'title').replace('", "', ', ')
43         description = self._html_search_regex(
44             r'(?s)<span id="MainContentPlaceHolder_CaptionsBlock_WitnessInfo">(.*?)</span>',
45             webpage, 'description')
46
47         return {
48             'id': video_id,
49             'ext': 'asf',
50             'url': video_url,
51             'title': title,
52             'description': description,
53         }