aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/mdr.py
blob: a63257c5634962f269184aa384741bf911de6786 (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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
    determine_ext,
    int_or_none,
    parse_duration,
    parse_iso8601,
    xpath_text,
)


class MDRIE(InfoExtractor):
    IE_DESC = 'MDR.DE and KiKA'
    _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'

    _TESTS = [{
        # MDR regularily deletes its videos
        'url': 'http://www.mdr.de/fakt/video189002.html',
        'only_matching': True,
    },  {
        # audio
        'url': 'http://www.mdr.de/kultur/audio1312272_zc-15948bad_zs-86171fdd.html',
        'md5': '64c4ee50f0a791deb9479cd7bbe9d2fa',
        'info_dict': {
            'id': '1312272',
            'ext': 'mp3',
            'title': 'Feuilleton vom 30. Oktober 2015',
            'duration': 250,
            'uploader': 'MITTELDEUTSCHER RUNDFUNK',
        },
    }, {
        'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
        'md5': '4930515e36b06c111213e80d1e4aad0e',
        'info_dict': {
            'id': '19636',
            'ext': 'mp4',
            'title': 'Baumhaus vom 30. Oktober 2015',
            'duration': 134,
            'uploader': 'KIKA',
        },
    }, {
        'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
        'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
        'info_dict': {
            'id': '8182',
            'ext': 'mp4',
            'title': 'Beutolomäus und der geheime Weihnachtswunsch',
            'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
            'timestamp': 1419047100,
            'upload_date': '20141220',
            'duration': 4628,
            'uploader': 'KIKA',
        },
    }, {
        'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
        'only_matching': True,
    }, {
        'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(url, video_id)

        data_url = self._search_regex(
            r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1',
            webpage, 'data url', group='url')

        doc = self._download_xml(
            compat_urlparse.urljoin(url, data_url), video_id)

        title = xpath_text(doc, ['./title', './broadcast/broadcastName'], 'title', fatal=True)

        formats = []
        processed_urls = []
        for asset in doc.findall('./assets/asset'):
            for source in (
                    'progressiveDownload',
                    'dynamicHttpStreamingRedirector',
                    'adaptiveHttpStreamingRedirector'):
                url_el = asset.find('./%sUrl' % source)
                if url_el is None:
                    continue

                video_url = url_el.text
                if video_url in processed_urls:
                    continue

                processed_urls.append(video_url)

                vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
                abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)

                url_formats = []

                ext = determine_ext(url_el.text)
                if ext == 'm3u8':
                    url_formats = self._extract_m3u8_formats(
                        video_url, video_id, 'mp4', entry_protocol='m3u8_native',
                        preference=0, m3u8_id='HLS', fatal=False)
                elif ext == 'f4m':
                    url_formats = self._extract_f4m_formats(
                        video_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
                        preference=0, f4m_id='HDS', fatal=False)
                else:
                    media_type = xpath_text(asset, './mediaType', 'media type', default='MP4')
                    vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
                    abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
                    filesize = int_or_none(xpath_text(asset, './fileSize', 'file size'))

                    f = {
                        'url': video_url,
                        'format_id': '%s-%d' % (media_type, vbr or abr),
                        'filesize': filesize,
                        'abr': abr,
                        'preference': 1,
                    }

                    if vbr:
                        width = int_or_none(xpath_text(asset, './frameWidth', 'width'))
                        height = int_or_none(xpath_text(asset, './frameHeight', 'height'))
                        f.update({
                            'vbr': vbr,
                            'width': width,
                            'height': height,
                        })

                    url_formats.append(f)

                if not vbr:
                    for f in url_formats:
                        abr = f.get('tbr') or abr
                        if 'tbr' in f:
                            del f['tbr']
                        f.update({
                            'abr': abr,
                            'vcodec': 'none',
                        })

                if url_formats:
                    formats.extend(url_formats)
        self._sort_formats(formats)

        description = xpath_text(doc, './broadcast/broadcastDescription', 'description')
        timestamp = parse_iso8601(
            xpath_text(
                doc, [
                    './broadcast/broadcastDate',
                    './broadcast/broadcastStartDate',
                    './broadcast/broadcastEndDate'],
                'timestamp', default=None))
        duration = parse_duration(xpath_text(doc, './duration', 'duration'))
        uploader = xpath_text(doc, './rights', 'uploader')

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'timestamp': timestamp,
            'duration': duration,
            'uploader': uploader,
            'formats': formats,
        }