aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/aljazeera.py
blob: b081695d8400c0e24d36e84bd8445efa084ed8b3 (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
from __future__ import unicode_literals

from .common import InfoExtractor


class AlJazeeraIE(InfoExtractor):
    _VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'

    _TEST = {
        'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
        'info_dict': {
            'id': '3792260579001',
            'ext': 'mp4',
            'title': 'The Slum - Episode 1: Deliverance',
            'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
            'uploader_id': '665003303001',
            'timestamp': 1411116829,
            'upload_date': '20140919',
        },
        'add_ie': ['BrightcoveNew'],
        'skip': 'Not accessible from Travis CI server',
    }
    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'

    def _real_extract(self, url):
        program_name = self._match_id(url)
        webpage = self._download_webpage(url, program_name)
        brightcove_id = self._search_regex(
            r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)