aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ndr.py
blob: 87f3edbbeb9710482b4ae5563fd153a88bcf31b5 (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
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
# encoding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    int_or_none,
    qualities,
)


preference = qualities(['xs', 's', 'm','l', 'xl'])


class NDRBaseIE(InfoExtractor):

    def extract_video_info(self, playlist, video_id):
        formats = []
        streamType = playlist.get('config').get('streamType')
        if streamType == 'httpVideo':
            for key, f in playlist.items():
                if key != 'config':
                    src = f['src']
                    if '.f4m' in src:
                        formats.extend(self._extract_f4m_formats(src, video_id))
                    elif '.m3u8' in src:
                        formats.extend(self._extract_m3u8_formats(src, video_id, fatal=False))
                    else:
                        quality = f.get('quality')
                        formats.append({
                            'url': src,
                            'format_id': quality,
                            'preference': preference(quality),
                        })
        elif streamType == 'httpAudio':
            for key, f in playlist.items():
                if key != 'config':
                    formats.append({
                        'url': f['src'],
                        'format_id': 'mp3',
                        'vcodec': 'none',
                    })
        else:
            raise ExtractorError('No media links available for %s' % video_id)

        self._sort_formats(formats)

        config = playlist.get('config')

        title = config['title']
        duration = int_or_none(config.get('duration'))
        thumbnails = [{
            'id': thumbnail.get('quality'),
            'url': thumbnail.get('src'),
            'preference': preference(thumbnail.get('quality'))
        } for thumbnail in config.get('poster').values()]

        return {
            'id': video_id,
            'title': title,
            'thumbnails': thumbnails,
            'duration': duration,
            'formats': formats,
        }

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

        json_data = self._download_json('http://www.ndr.de/%s-ppjson.json' % video_id, video_id, fatal=False)

        if not json_data:
            webpage = self._download_webpage(url, video_id)
            embed_url = self._html_search_regex(r'<iframe[^>]+id="pp_\w+"[^>]+src="(/.*)"', webpage, 'embed url', None, False)
            if not embed_url:
                embed_url = self._html_search_meta('embedURL', webpage, fatal=False)
            if embed_url:
                if embed_url.startswith('/'):
                    return self.url_result('http://www.ndr.de%s' % embed_url, 'NDREmbed')
                else:
                    return self.url_result(embed_url, 'NDREmbed')
            raise ExtractorError('No media links available for %s' % video_id)

        return self.extract_video_info(json_data['playlist'], video_id)


class NDRIE(NDRBaseIE):
    IE_NAME = 'ndr'
    IE_DESC = 'NDR.de - Mediathek'
    _VALID_URL = r'https?://www\.ndr\.de/.+?,(?P<id>\w+)\.html'

    _TESTS = [
        {
            'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html',
            'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c',
            'note': 'Video file',
            'info_dict': {
                'id': 'nordmagazin25866',
                'ext': 'mp4',
                'title': 'Kartoffeltage in der Lewitz',
                'duration': 166,
            },
            'skip': '404 Not found',
        },
        {
            'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
            'md5': 'dadc003c55ae12a5d2f6bd436cd73f59',
            'info_dict': {
                'id': 'hafengeburtstag988',
                'ext': 'mp4',
                'title': 'Party, Pötte und Parade',
                'duration': 3498,
            },
        },
        {
            'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html',
            'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
            'note': 'Audio file',
            'info_dict': {
                'id': 'audio51535',
                'ext': 'mp3',
                'title': 'La Valette entgeht der Hinrichtung',
                'duration': 884,
            }
        }
    ]


class NJoyIE(NDRBaseIE):
    IE_NAME = 'N-JOY'
    _VALID_URL = r'https?://www\.n-joy\.de/.+?,(?P<id>\w+)\.html'

    _TEST = {
        'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
        'md5': 'cb63be60cd6f9dd75218803146d8dc67',
        'info_dict': {
            'id': 'comedycontest2480',
            'ext': 'mp4',
            'title': 'Benaissa beim NDR Comedy Contest',
            'duration': 654,
        }
    }


class NDREmbedBaseIE(NDRBaseIE):

    def _real_extract(self, url):
        video_id = self._match_id(url)
        json_data = self._download_json('http://www.ndr.de/%s-ppjson.json' % video_id, video_id, fatal=False)
        if not json_data:
            raise ExtractorError('No media links available for %s' % video_id)
        return self.extract_video_info(json_data['playlist'], video_id)


class NDREmbedIE(NDREmbedBaseIE):
    IE_NAME = 'ndr:embed'
    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[a-z0-9]+)-(?:player|externalPlayer)\.html'

    _TEST = {
        'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
        'md5': 'cb63be60cd6f9dd75218803146d8dc67',
        'info_dict': {
            'id': 'ndraktuell28488',
            'ext': 'mp4',
            'title': 'Norddeutschland begrüßt Flüchtlinge',
            'duration': 132,
        }
    }


class NJoyEmbedIE(NDREmbedBaseIE):
    IE_NAME = 'N-JOY:embed'
    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[a-z0-9]+)-(?:player|externalPlayer)\.html'

    _TEST = {
        'url': 'http://www.n-joy.de/entertainment/film/portraet374-player_image-832d9b79-fa8a-4026-92e2-e0fd99deb2f9_theme-n-joy.html',
        'md5': 'cb63be60cd6f9dd75218803146d8dc67',
        'info_dict': {
            'id': 'portraet374',
            'ext': 'mp4',
            'title': 'Viviane Andereggen - "Schuld um Schuld"',
            'duration': 129,
        }
    }