aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/svt.py
blob: 7aa1b591949b298f5b1eee1d4c57e23e7d889d5f (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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_parse_qs,
    compat_urllib_parse_urlparse,
)
from ..utils import (
    determine_ext,
    dict_get,
    int_or_none,
    orderedSet,
    strip_or_none,
    try_get,
    urljoin,
    compat_str,
)


class SVTBaseIE(InfoExtractor):
    _GEO_COUNTRIES = ['SE']

    def _extract_video(self, video_info, video_id):
        is_live = dict_get(video_info, ('live', 'simulcast'), default=False)
        m3u8_protocol = 'm3u8' if is_live else 'm3u8_native'
        formats = []
        for vr in video_info['videoReferences']:
            player_type = vr.get('playerType') or vr.get('format')
            vurl = vr['url']
            ext = determine_ext(vurl)
            if ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    vurl, video_id,
                    ext='mp4', entry_protocol=m3u8_protocol,
                    m3u8_id=player_type, fatal=False))
            elif ext == 'f4m':
                formats.extend(self._extract_f4m_formats(
                    vurl + '?hdcore=3.3.0', video_id,
                    f4m_id=player_type, fatal=False))
            elif ext == 'mpd':
                if player_type == 'dashhbbtv':
                    formats.extend(self._extract_mpd_formats(
                        vurl, video_id, mpd_id=player_type, fatal=False))
            else:
                formats.append({
                    'format_id': player_type,
                    'url': vurl,
                })
        if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
            self.raise_geo_restricted(
                'This video is only available in Sweden',
                countries=self._GEO_COUNTRIES)
        self._sort_formats(formats)

        subtitles = {}
        subtitle_references = dict_get(video_info, ('subtitles', 'subtitleReferences'))
        if isinstance(subtitle_references, list):
            for sr in subtitle_references:
                subtitle_url = sr.get('url')
                subtitle_lang = sr.get('language', 'sv')
                if subtitle_url:
                    if determine_ext(subtitle_url) == 'm3u8':
                        # TODO(yan12125): handle WebVTT in m3u8 manifests
                        continue

                    subtitles.setdefault(subtitle_lang, []).append({'url': subtitle_url})

        title = video_info.get('title')

        series = video_info.get('programTitle')
        season_number = int_or_none(video_info.get('season'))
        episode = video_info.get('episodeTitle')
        episode_number = int_or_none(video_info.get('episodeNumber'))

        duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
        age_limit = None
        adult = dict_get(
            video_info, ('inappropriateForChildren', 'blockedForChildren'),
            skip_false_values=False)
        if adult is not None:
            age_limit = 18 if adult else 0

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
            'subtitles': subtitles,
            'duration': duration,
            'age_limit': age_limit,
            'series': series,
            'season_number': season_number,
            'episode': episode,
            'episode_number': episode_number,
            'is_live': is_live,
        }


class SVTIE(SVTBaseIE):
    _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
        'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
        'info_dict': {
            'id': '2900353',
            'ext': 'mp4',
            'title': 'Stjärnorna skojar till det - under SVT-intervjun',
            'duration': 27,
            'age_limit': 0,
        },
    }

    @staticmethod
    def _extract_url(webpage):
        mobj = re.search(
            r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE._VALID_URL, webpage)
        if mobj:
            return mobj.group('url')

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

        info = self._download_json(
            'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id),
            article_id)

        info_dict = self._extract_video(info['video'], article_id)
        info_dict['title'] = info['context']['title']
        return info_dict


class SVTPlayBaseIE(SVTBaseIE):
    _SVTPLAY_RE = r'root\s*\[\s*(["\'])_*svtplay\1\s*\]\s*=\s*(?P<json>{.+?})\s*;\s*\n'


class SVTPlayIE(SVTPlayBaseIE):
    IE_DESC = 'SVT Play and Öppet arkiv'
    _VALID_URL = r'''(?x)
                    (?:
                        svt:(?P<svt_id>[^/?#&]+)|
                        https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
                    )
                    '''
    _TESTS = [{
        'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
        'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
        'info_dict': {
            'id': '5996901',
            'ext': 'mp4',
            'title': 'Flygplan till Haile Selassie',
            'duration': 3527,
            'thumbnail': r're:^https?://.*[\.-]jpg$',
            'age_limit': 0,
            'subtitles': {
                'sv': [{
                    'ext': 'wsrt',
                }]
            },
        },
    }, {
        # geo restricted to Sweden
        'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
        'only_matching': True,
    }, {
        'url': 'http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg',
        'only_matching': True,
    }, {
        'url': 'https://www.svtplay.se/kanaler/svt1',
        'only_matching': True,
    }, {
        'url': 'svt:1376446-003A',
        'only_matching': True,
    }, {
        'url': 'svt:14278044',
        'only_matching': True,
    }]

    def _adjust_title(self, info):
        if info['is_live']:
            info['title'] = self._live_title(info['title'])

    def _extract_by_video_id(self, video_id, webpage=None):
        data = self._download_json(
            'https://api.svt.se/video/%s' % video_id,
            video_id, headers=self.geo_verification_headers())
        info_dict = self._extract_video(data, video_id)
        if not info_dict.get('title'):
            title = dict_get(info_dict, ('episode', 'series'))
            if not title and webpage:
                title = re.sub(
                    r'\s*\|\s*.+?$', '', self._og_search_title(webpage))
            if not title:
                title = video_id
            info_dict['title'] = title
        self._adjust_title(info_dict)
        return info_dict

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

        if svt_id:
            return self._extract_by_video_id(svt_id)

        webpage = self._download_webpage(url, video_id)

        data = self._parse_json(
            self._search_regex(
                self._SVTPLAY_RE, webpage, 'embedded data', default='{}',
                group='json'),
            video_id, fatal=False)

        thumbnail = self._og_search_thumbnail(webpage)

        if data:
            video_info = try_get(
                data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'],
                dict)
            if video_info:
                info_dict = self._extract_video(video_info, video_id)
                info_dict.update({
                    'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
                    'thumbnail': thumbnail,
                })
                self._adjust_title(info_dict)
                return info_dict

        svt_id = self._search_regex(
            r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
            webpage, 'video id')

        return self._extract_by_video_id(svt_id, webpage)


class SVTSeriesIE(SVTPlayBaseIE):
    _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)'
    _TESTS = [{
        'url': 'https://www.svtplay.se/rederiet',
        'info_dict': {
            'id': 'rederiet',
            'title': 'Rederiet',
            'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
        },
        'playlist_mincount': 318,
    }, {
        'url': 'https://www.svtplay.se/rederiet?tab=sasong2',
        'info_dict': {
            'id': 'rederiet-sasong2',
            'title': 'Rederiet - Säsong 2',
            'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
        },
        'playlist_count': 12,
    }]

    @classmethod
    def suitable(cls, url):
        return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)

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

        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
        season_slug = qs.get('tab', [None])[0]

        if season_slug:
            series_id += '-%s' % season_slug

        webpage = self._download_webpage(
            url, series_id, 'Downloading series page')

        root = self._parse_json(
            self._search_regex(
                self._SVTPLAY_RE, webpage, 'content', group='json'),
            series_id)

        season_name = None

        entries = []
        for season in root['relatedVideoContent']['relatedVideosAccordion']:
            if not isinstance(season, dict):
                continue
            if season_slug:
                if season.get('slug') != season_slug:
                    continue
                season_name = season.get('name')
            videos = season.get('videos')
            if not isinstance(videos, list):
                continue
            for video in videos:
                content_url = video.get('contentUrl')
                if not content_url or not isinstance(content_url, compat_str):
                    continue
                entries.append(
                    self.url_result(
                        urljoin(url, content_url),
                        ie=SVTPlayIE.ie_key(),
                        video_title=video.get('title')
                    ))

        metadata = root.get('metaData')
        if not isinstance(metadata, dict):
            metadata = {}

        title = metadata.get('title')
        season_name = season_name or season_slug

        if title and season_name:
            title = '%s - %s' % (title, season_name)
        elif season_slug:
            title = season_slug

        return self.playlist_result(
            entries, series_id, title, metadata.get('description'))


class SVTPageIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)'
    _TESTS = [{
        'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
        'info_dict': {
            'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
            'title': 'GUIDE: Sommarträning du kan göra var och när du vill',
        },
        'playlist_count': 7,
    }, {
        'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
        'info_dict': {
            'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
            'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”',
        },
        'playlist_count': 1,
    }, {
        # only programTitle
        'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
        'info_dict': {
            'id': '2900353',
            'ext': 'mp4',
            'title': 'Stjärnorna skojar till det - under SVT-intervjun',
            'duration': 27,
            'age_limit': 0,
        },
    }, {
        'url': 'https://www.svt.se/nyheter/lokalt/vast/svt-testar-tar-nagon-upp-skrapet-1',
        'only_matching': True,
    }, {
        'url': 'https://www.svt.se/vader/manadskronikor/maj2018',
        'only_matching': True,
    }]

    @classmethod
    def suitable(cls, url):
        return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)

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

        webpage = self._download_webpage(url, playlist_id)

        entries = [
            self.url_result(
                'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id)
            for video_id in orderedSet(re.findall(
                r'data-video-id=["\'](\d+)', webpage))]

        title = strip_or_none(self._og_search_title(webpage, default=None))

        return self.playlist_result(entries, playlist_id, title)