aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/drtv.py
blob: e966d7483cdc2193cfc96d2bdd808c90e515f821 (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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    int_or_none,
    float_or_none,
    mimetype2ext,
    parse_iso8601,
    remove_end,
    update_url_query,
)


class DRTVIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
    IE_NAME = 'drtv'
    _TESTS = [{
        'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
        'md5': '25e659cccc9a2ed956110a299fdf5983',
        'info_dict': {
            'id': 'klassen-darlig-taber-10',
            'ext': 'mp4',
            'title': 'Klassen - Dårlig taber (10)',
            'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
            'timestamp': 1471991907,
            'upload_date': '20160823',
            'duration': 606.84,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
        'md5': '2c37175c718155930f939ef59952474a',
        'info_dict': {
            'id': 'christiania-pusher-street-ryddes-drdkrjpo',
            'ext': 'mp4',
            'title': 'LIVE Christianias rydning af Pusher Street er i gang',
            'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
            'timestamp': 1472800279,
            'upload_date': '20160902',
            'duration': 131.4,
        },
    }]

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

        webpage = self._download_webpage(url, video_id)

        if '>Programmet er ikke længere tilgængeligt' in webpage:
            raise ExtractorError(
                'Video %s is not available' % video_id, expected=True)

        video_id = self._search_regex(
            (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
                r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
            webpage, 'video id')

        programcard = self._download_json(
            'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
            video_id, 'Downloading video JSON')
        data = programcard['Data'][0]

        title = remove_end(self._og_search_title(
            webpage, default=None), ' | TV | DR') or data['Title']
        description = self._og_search_description(
            webpage, default=None) or data.get('Description')

        timestamp = parse_iso8601(data.get('CreatedTime'))

        thumbnail = None
        duration = None

        restricted_to_denmark = False

        formats = []
        subtitles = {}

        for asset in data['Assets']:
            kind = asset.get('Kind')
            if kind == 'Image':
                thumbnail = asset.get('Uri')
            elif kind in ('VideoResource', 'AudioResource'):
                duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
                restricted_to_denmark = asset.get('RestrictedToDenmark')
                spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
                for link in asset.get('Links', []):
                    uri = link.get('Uri')
                    if not uri:
                        continue
                    target = link.get('Target')
                    format_id = target or ''
                    preference = None
                    if spoken_subtitles:
                        preference = -1
                        format_id += '-spoken-subtitles'
                    if target == 'HDS':
                        f4m_formats = self._extract_f4m_formats(
                            uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
                            video_id, preference, f4m_id=format_id)
                        if kind == 'AudioResource':
                            for f in f4m_formats:
                                f['vcodec'] = 'none'
                        formats.extend(f4m_formats)
                    elif target == 'HLS':
                        formats.extend(self._extract_m3u8_formats(
                            uri, video_id, 'mp4', entry_protocol='m3u8_native',
                            preference=preference, m3u8_id=format_id))
                    else:
                        bitrate = link.get('Bitrate')
                        if bitrate:
                            format_id += '-%s' % bitrate
                        formats.append({
                            'url': uri,
                            'format_id': format_id,
                            'tbr': int_or_none(bitrate),
                            'ext': link.get('FileFormat'),
                            'vcodec': 'none' if kind == 'AudioResource' else None,
                        })
                subtitles_list = asset.get('SubtitlesList')
                if isinstance(subtitles_list, list):
                    LANGS = {
                        'Danish': 'da',
                    }
                    for subs in subtitles_list:
                        if not subs.get('Uri'):
                            continue
                        lang = subs.get('Language') or 'da'
                        subtitles.setdefault(LANGS.get(lang, lang), []).append({
                            'url': subs['Uri'],
                            'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
                        })

        if not formats and restricted_to_denmark:
            self.raise_geo_restricted(
                'Unfortunately, DR is not allowed to show this program outside Denmark.',
                expected=True)

        self._sort_formats(formats)

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


class DRTVLiveIE(InfoExtractor):
    IE_NAME = 'drtv:live'
    _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
    _TEST = {
        'url': 'https://www.dr.dk/tv/live/dr1',
        'info_dict': {
            'id': 'dr1',
            'ext': 'mp4',
            'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }

    def _real_extract(self, url):
        channel_id = self._match_id(url)
        channel_data = self._download_json(
            'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
            channel_id)
        title = self._live_title(channel_data['Title'])

        formats = []
        for streaming_server in channel_data.get('StreamingServers', []):
            server = streaming_server.get('Server')
            if not server:
                continue
            link_type = streaming_server.get('LinkType')
            for quality in streaming_server.get('Qualities', []):
                for stream in quality.get('Streams', []):
                    stream_path = stream.get('Stream')
                    if not stream_path:
                        continue
                    stream_url = update_url_query(
                        '%s/%s' % (server, stream_path), {'b': ''})
                    if link_type == 'HLS':
                        formats.extend(self._extract_m3u8_formats(
                            stream_url, channel_id, 'mp4',
                            m3u8_id=link_type, fatal=False, live=True))
                    elif link_type == 'HDS':
                        formats.extend(self._extract_f4m_formats(update_url_query(
                            '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}),
                            channel_id, f4m_id=link_type, fatal=False))
        self._sort_formats(formats)

        return {
            'id': channel_id,
            'title': title,
            'thumbnail': channel_data.get('PrimaryImageUri'),
            'formats': formats,
            'is_live': True,
        }