aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/videolecturesnet.py
blob: eadff8d180034f407cea190a9e5f51aea72f3c8a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import parse_duration


class VideoLecturesNetIE(InfoExtractor):
    _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
    IE_NAME = 'videolectures.net'

    _TEST = {
        'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
        'info_dict': {
            'id': 'promogram_igor_mekjavic_eng',
            'ext': 'mp4',
            'title': 'Automatics, robotics and biocybernetics',
            'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
            'upload_date': '20130627',
            'duration': 565,
            'thumbnail': 're:http://.*\.jpg',
        },
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)

        smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
        smil = self._download_smil(smil_url, video_id, fatal=False)

        # Probably a playlist
        if smil is False:
            webpage = self._download_webpage(url, video_id)
            entries = [
                self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
                for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
            playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True)
            playlist_description = self._html_search_meta('description', webpage, 'description')
            return self.playlist_result(entries, video_id, playlist_title, playlist_description)

        info = self._parse_smil(smil, smil_url, video_id)

        info['id'] = video_id

        switch = smil.find('.//switch')
        if switch is not None:
            info['duration'] = parse_duration(switch.attrib.get('dur'))

        return info