aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/arte.py
blob: 2bd3bfe8a852159cf7aefa93e731bab995ca7d23 (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
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    ExtractorError,
    int_or_none,
    qualities,
    try_get,
    unified_strdate,
)

# There are different sources of video in arte.tv, the extraction process
# is different for each one. The videos usually expire in 7 days, so we can't
# add tests.


class ArteTVBaseIE(InfoExtractor):
    def _extract_from_json_url(self, json_url, video_id, lang, title=None):
        info = self._download_json(json_url, video_id)
        player_info = info['videoJsonPlayer']

        vsr = try_get(player_info, lambda x: x['VSR'], dict)
        if not vsr:
            error = None
            if try_get(player_info, lambda x: x['custom_msg']['type']) == 'error':
                error = try_get(
                    player_info, lambda x: x['custom_msg']['msg'], compat_str)
            if not error:
                error = 'Video %s is not available' % player_info.get('VID') or video_id
            raise ExtractorError(error, expected=True)

        upload_date_str = player_info.get('shootingDate')
        if not upload_date_str:
            upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]

        title = (player_info.get('VTI') or title or player_info['VID']).strip()
        subtitle = player_info.get('VSU', '').strip()
        if subtitle:
            title += ' - %s' % subtitle

        info_dict = {
            'id': player_info['VID'],
            'title': title,
            'description': player_info.get('VDE'),
            'upload_date': unified_strdate(upload_date_str),
            'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
        }
        qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ'])

        LANGS = {
            'fr': 'F',
            'de': 'A',
            'en': 'E[ANG]',
            'es': 'E[ESP]',
            'it': 'E[ITA]',
            'pl': 'E[POL]',
        }

        langcode = LANGS.get(lang, lang)

        formats = []
        for format_id, format_dict in vsr.items():
            f = dict(format_dict)
            versionCode = f.get('versionCode')
            l = re.escape(langcode)

            # Language preference from most to least priority
            # Reference: section 6.8 of
            # https://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-07-1.pdf
            PREFERENCES = (
                # original version in requested language, without subtitles
                r'VO{0}$'.format(l),
                # original version in requested language, with partial subtitles in requested language
                r'VO{0}-ST{0}$'.format(l),
                # original version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
                r'VO{0}-STM{0}$'.format(l),
                # non-original (dubbed) version in requested language, without subtitles
                r'V{0}$'.format(l),
                # non-original (dubbed) version in requested language, with subtitles partial subtitles in requested language
                r'V{0}-ST{0}$'.format(l),
                # non-original (dubbed) version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
                r'V{0}-STM{0}$'.format(l),
                # original version in requested language, with partial subtitles in different language
                r'VO{0}-ST(?!{0}).+?$'.format(l),
                # original version in requested language, with subtitles for the deaf and hard-of-hearing in different language
                r'VO{0}-STM(?!{0}).+?$'.format(l),
                # original version in different language, with partial subtitles in requested language
                r'VO(?:(?!{0}).+?)?-ST{0}$'.format(l),
                # original version in different language, with subtitles for the deaf and hard-of-hearing in requested language
                r'VO(?:(?!{0}).+?)?-STM{0}$'.format(l),
                # original version in different language, without subtitles
                r'VO(?:(?!{0}))?$'.format(l),
                # original version in different language, with partial subtitles in different language
                r'VO(?:(?!{0}).+?)?-ST(?!{0}).+?$'.format(l),
                # original version in different language, with subtitles for the deaf and hard-of-hearing in different language
                r'VO(?:(?!{0}).+?)?-STM(?!{0}).+?$'.format(l),
            )

            for pref, p in enumerate(PREFERENCES):
                if re.match(p, versionCode):
                    lang_pref = len(PREFERENCES) - pref
                    break
            else:
                lang_pref = -1

            format = {
                'format_id': format_id,
                'preference': -10 if f.get('videoFormat') == 'M3U8' else None,
                'language_preference': lang_pref,
                'format_note': '%s, %s' % (f.get('versionCode'), f.get('versionLibelle')),
                'width': int_or_none(f.get('width')),
                'height': int_or_none(f.get('height')),
                'tbr': int_or_none(f.get('bitrate')),
                'quality': qfunc(f.get('quality')),
            }

            if f.get('mediaType') == 'rtmp':
                format['url'] = f['streamer']
                format['play_path'] = 'mp4:' + f['url']
                format['ext'] = 'flv'
            else:
                format['url'] = f['url']

            formats.append(format)

        self._check_formats(formats, video_id)
        self._sort_formats(formats)

        info_dict['formats'] = formats
        return info_dict


class ArteTVPlus7IE(ArteTVBaseIE):
    IE_NAME = 'arte.tv:+7'
    _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>\d{6}-\d{3}-[AF])'

    _TESTS = [{
        'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
        'info_dict': {
            'id': '088501-000-A',
            'ext': 'mp4',
            'title': 'Mexico: Stealing Petrol to Survive',
            'upload_date': '20190628',
        },
    }]

    def _real_extract(self, url):
        lang, video_id = re.match(self._VALID_URL, url).groups()
        return self._extract_from_json_url(
            'https://api.arte.tv/api/player/v1/config/%s/%s' % (lang, video_id),
            video_id, lang)


class ArteTVEmbedIE(ArteTVPlus7IE):
    IE_NAME = 'arte.tv:embed'
    _VALID_URL = r'''(?x)
        https://www\.arte\.tv
        /player/v3/index\.php\?json_url=
        (?P<json_url>
            https?://api\.arte\.tv/api/player/v1/config/
            (?P<lang>[^/]+)/(?P<id>\d{6}-\d{3}-[AF])
        )
    '''

    _TESTS = []

    def _real_extract(self, url):
        json_url, lang, video_id = re.match(self._VALID_URL, url).groups()
        return self._extract_from_json_url(json_url, video_id, lang)


class ArteTVPlaylistIE(ArteTVBaseIE):
    IE_NAME = 'arte.tv:playlist'
    _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>RC-\d{6})'

    _TESTS = [{
        'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
        'info_dict': {
            'id': 'RC-016954',
            'title': 'Earn a Living',
            'description': 'md5:d322c55011514b3a7241f7fb80d494c2',
        },
        'playlist_mincount': 6,
    }]

    def _real_extract(self, url):
        lang, playlist_id = re.match(self._VALID_URL, url).groups()
        collection = self._download_json(
            'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos'
            % (lang, playlist_id), playlist_id)
        title = collection.get('title')
        description = collection.get('shortDescription') or collection.get('teaserText')
        entries = [
            self._extract_from_json_url(
                video['jsonUrl'], video.get('programId') or playlist_id, lang)
            for video in collection['videos'] if video.get('jsonUrl')]
        return self.playlist_result(entries, playlist_id, title, description)