aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/voicerepublic.py
blob: d150b5b5e275bcc402c3d50aae0603cc28aa81b4 (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
52
53
54
55
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import ExtractorError


class VoiceRepublicIE(InfoExtractor):
    _VALID_URL = r'https?://voicerepublic\.com/talks/(?P<id>[0-9a-z-]+)'
    _TEST = {
        'url': 'https://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
        'md5': '0554a24d1657915aa8e8f84e15dc9353',
        'info_dict': {
            'id': '2296',
            'ext': 'm4a',
            'title': 'Watching the Watchers: Building a Sousveillance State',
            'thumbnail': 'https://voicerepublic.com/system/flyer/2296.png',
            'description': 'md5:715ba964958afa2398df615809cfecb1',
        }
    }

    def _real_extract(self, url):
        display_id = self._match_id(url)
        req = compat_urllib_request.Request(url)
        # Older versions of Firefox get redirected to an "upgrade browser" page
        req.add_header('User-Agent', 'youtube-dl')
        webpage = self._download_webpage(req, display_id)
        thumbnail = self._og_search_thumbnail(webpage)
        video_id = self._search_regex(r'/(\d+)\.png', thumbnail, 'id')

        if '<a>Queued for processing, please stand by...</a>' in webpage:
            raise ExtractorError('Audio is still queued for processing')

        ext_matches = re.finditer(r'data-\w+=\'/vrmedia/\d+-clean\.(\w+)\'', webpage)
        exts = [match.group(1) for match in ext_matches]

        formats = [{
            'url': 'https://voicerepublic.com/vrmedia/{}-clean.{}'.format(video_id, ext),
            'ext': ext,
            'format_id': ext,
            'vcodec': 'none',
        } for ext in exts]
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': self._og_search_title(webpage),
            'formats': formats,
            'url': self._og_search_url(webpage),
            'thumbnail': thumbnail,
            'description': self._og_search_description(webpage),
        }