aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/podomatic.py
blob: f20946a2bd0616d8d90cebf360570a3f0bc40e94 (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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import int_or_none


class PodomaticIE(InfoExtractor):
    IE_NAME = 'podomatic'
    _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'

    _TESTS = [
        {
            'url': 'http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00',
            'md5': '84bb855fcf3429e6bf72460e1eed782d',
            'info_dict': {
                'id': '2009-01-02T16_03_35-08_00',
                'ext': 'mp3',
                'uploader': 'Science Teaching Tips',
                'uploader_id': 'scienceteachingtips',
                'title': '64.  When the Moon Hits Your Eye',
                'duration': 446,
            }
        },
        {
            'url': 'http://ostbahnhof.podomatic.com/entry/2013-11-15T16_31_21-08_00',
            'md5': 'd2cf443931b6148e27638650e2638297',
            'info_dict': {
                'id': '2013-11-15T16_31_21-08_00',
                'ext': 'mp3',
                'uploader': 'Ostbahnhof / Techno Mix',
                'uploader_id': 'ostbahnhof',
                'title': 'Einunddreizig',
                'duration': 3799,
            }
        },
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        channel = mobj.group('channel')

        json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
                     '?permalink=true&rtmp=0') %
                    (mobj.group('proto'), channel, video_id))
        data_json = self._download_webpage(
            json_url, video_id, 'Downloading video info')
        data = json.loads(data_json)

        video_url = data['downloadLink']
        if not video_url:
            video_url = '%s/%s' % (data['streamer'].replace('rtmp', 'http'), data['mediaLocation'])
        uploader = data['podcast']
        title = data['title']
        thumbnail = data['imageLocation']
        duration = int_or_none(data.get('length'), 1000)

        return {
            'id': video_id,
            'url': video_url,
            'title': title,
            'uploader': uploader,
            'uploader_id': channel,
            'thumbnail': thumbnail,
            'duration': duration,
        }