]>
Commit | Line | Data |
---|---|---|
1 | # coding: utf-8 | |
2 | from __future__ import unicode_literals | |
3 | ||
4 | import re | |
5 | ||
6 | from .common import InfoExtractor | |
7 | from ..compat import compat_str | |
8 | from ..utils import ( | |
9 | determine_ext, | |
10 | dict_get, | |
11 | int_or_none, | |
12 | unified_timestamp, | |
13 | str_or_none, | |
14 | strip_or_none, | |
15 | try_get, | |
16 | ) | |
17 | ||
18 | ||
19 | class SVTBaseIE(InfoExtractor): | |
20 | _GEO_COUNTRIES = ['SE'] | |
21 | ||
22 | def _extract_video(self, video_info, video_id): | |
23 | is_live = dict_get(video_info, ('live', 'simulcast'), default=False) | |
24 | m3u8_protocol = 'm3u8' if is_live else 'm3u8_native' | |
25 | formats = [] | |
26 | for vr in video_info['videoReferences']: | |
27 | player_type = vr.get('playerType') or vr.get('format') | |
28 | vurl = vr['url'] | |
29 | ext = determine_ext(vurl) | |
30 | if ext == 'm3u8': | |
31 | formats.extend(self._extract_m3u8_formats( | |
32 | vurl, video_id, | |
33 | ext='mp4', entry_protocol=m3u8_protocol, | |
34 | m3u8_id=player_type, fatal=False)) | |
35 | elif ext == 'f4m': | |
36 | formats.extend(self._extract_f4m_formats( | |
37 | vurl + '?hdcore=3.3.0', video_id, | |
38 | f4m_id=player_type, fatal=False)) | |
39 | elif ext == 'mpd': | |
40 | if player_type == 'dashhbbtv': | |
41 | formats.extend(self._extract_mpd_formats( | |
42 | vurl, video_id, mpd_id=player_type, fatal=False)) | |
43 | else: | |
44 | formats.append({ | |
45 | 'format_id': player_type, | |
46 | 'url': vurl, | |
47 | }) | |
48 | rights = try_get(video_info, lambda x: x['rights'], dict) or {} | |
49 | if not formats and rights.get('geoBlockedSweden'): | |
50 | self.raise_geo_restricted( | |
51 | 'This video is only available in Sweden', | |
52 | countries=self._GEO_COUNTRIES, metadata_available=True) | |
53 | self._sort_formats(formats) | |
54 | ||
55 | subtitles = {} | |
56 | subtitle_references = dict_get(video_info, ('subtitles', 'subtitleReferences')) | |
57 | if isinstance(subtitle_references, list): | |
58 | for sr in subtitle_references: | |
59 | subtitle_url = sr.get('url') | |
60 | subtitle_lang = sr.get('language', 'sv') | |
61 | if subtitle_url: | |
62 | if determine_ext(subtitle_url) == 'm3u8': | |
63 | # TODO(yan12125): handle WebVTT in m3u8 manifests | |
64 | continue | |
65 | ||
66 | subtitles.setdefault(subtitle_lang, []).append({'url': subtitle_url}) | |
67 | ||
68 | title = video_info.get('title') | |
69 | ||
70 | series = video_info.get('programTitle') | |
71 | season_number = int_or_none(video_info.get('season')) | |
72 | episode = video_info.get('episodeTitle') | |
73 | episode_number = int_or_none(video_info.get('episodeNumber')) | |
74 | ||
75 | timestamp = unified_timestamp(rights.get('validFrom')) | |
76 | duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration'))) | |
77 | age_limit = None | |
78 | adult = dict_get( | |
79 | video_info, ('inappropriateForChildren', 'blockedForChildren'), | |
80 | skip_false_values=False) | |
81 | if adult is not None: | |
82 | age_limit = 18 if adult else 0 | |
83 | ||
84 | return { | |
85 | 'id': video_id, | |
86 | 'title': title, | |
87 | 'formats': formats, | |
88 | 'subtitles': subtitles, | |
89 | 'duration': duration, | |
90 | 'timestamp': timestamp, | |
91 | 'age_limit': age_limit, | |
92 | 'series': series, | |
93 | 'season_number': season_number, | |
94 | 'episode': episode, | |
95 | 'episode_number': episode_number, | |
96 | 'is_live': is_live, | |
97 | } | |
98 | ||
99 | ||
100 | class SVTIE(SVTBaseIE): | |
101 | _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)' | |
102 | _TEST = { | |
103 | 'url': 'http://www.svt.se/wd?widgetId=23991§ionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false', | |
104 | 'md5': '33e9a5d8f646523ce0868ecfb0eed77d', | |
105 | 'info_dict': { | |
106 | 'id': '2900353', | |
107 | 'ext': 'mp4', | |
108 | 'title': 'Stjärnorna skojar till det - under SVT-intervjun', | |
109 | 'duration': 27, | |
110 | 'age_limit': 0, | |
111 | }, | |
112 | } | |
113 | ||
114 | @staticmethod | |
115 | def _extract_url(webpage): | |
116 | mobj = re.search( | |
117 | r'(?:<iframe src|href)="(?P<url>%s[^"]*)"' % SVTIE._VALID_URL, webpage) | |
118 | if mobj: | |
119 | return mobj.group('url') | |
120 | ||
121 | def _real_extract(self, url): | |
122 | mobj = self._match_valid_url(url) | |
123 | widget_id = mobj.group('widget_id') | |
124 | article_id = mobj.group('id') | |
125 | ||
126 | info = self._download_json( | |
127 | 'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id), | |
128 | article_id) | |
129 | ||
130 | info_dict = self._extract_video(info['video'], article_id) | |
131 | info_dict['title'] = info['context']['title'] | |
132 | return info_dict | |
133 | ||
134 | ||
135 | class SVTPlayBaseIE(SVTBaseIE): | |
136 | _SVTPLAY_RE = r'root\s*\[\s*(["\'])_*svtplay\1\s*\]\s*=\s*(?P<json>{.+?})\s*;\s*\n' | |
137 | ||
138 | ||
139 | class SVTPlayIE(SVTPlayBaseIE): | |
140 | IE_DESC = 'SVT Play and Öppet arkiv' | |
141 | _VALID_URL = r'''(?x) | |
142 | (?: | |
143 | (?: | |
144 | svt:| | |
145 | https?://(?:www\.)?svt\.se/barnkanalen/barnplay/[^/]+/ | |
146 | ) | |
147 | (?P<svt_id>[^/?#&]+)| | |
148 | https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+) | |
149 | (?:.*?(?:modalId|id)=(?P<modal_id>[\da-zA-Z-]+))? | |
150 | ) | |
151 | ''' | |
152 | _TESTS = [{ | |
153 | 'url': 'https://www.svtplay.se/video/30479064', | |
154 | 'md5': '2382036fd6f8c994856c323fe51c426e', | |
155 | 'info_dict': { | |
156 | 'id': '8zVbDPA', | |
157 | 'ext': 'mp4', | |
158 | 'title': 'Designdrömmar i Stenungsund', | |
159 | 'timestamp': 1615770000, | |
160 | 'upload_date': '20210315', | |
161 | 'duration': 3519, | |
162 | 'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$', | |
163 | 'age_limit': 0, | |
164 | 'subtitles': { | |
165 | 'sv': [{ | |
166 | 'ext': 'vtt', | |
167 | }] | |
168 | }, | |
169 | }, | |
170 | 'params': { | |
171 | # skip for now due to download test asserts that segment is > 10000 bytes and svt uses | |
172 | # init segments that are smaller | |
173 | # AssertionError: Expected test_SVTPlay_jNwpV9P.mp4 to be at least 9.77KiB, but it's only 864.00B | |
174 | 'skip_download': True, | |
175 | }, | |
176 | }, { | |
177 | 'url': 'https://www.svtplay.se/video/30479064/husdrommar/husdrommar-sasong-8-designdrommar-i-stenungsund?modalId=8zVbDPA', | |
178 | 'only_matching': True, | |
179 | }, { | |
180 | 'url': 'https://www.svtplay.se/video/30684086/rapport/rapport-24-apr-18-00-7?id=e72gVpa', | |
181 | 'only_matching': True, | |
182 | }, { | |
183 | # geo restricted to Sweden | |
184 | 'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten', | |
185 | 'only_matching': True, | |
186 | }, { | |
187 | 'url': 'http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg', | |
188 | 'only_matching': True, | |
189 | }, { | |
190 | 'url': 'https://www.svtplay.se/kanaler/svt1', | |
191 | 'only_matching': True, | |
192 | }, { | |
193 | 'url': 'svt:1376446-003A', | |
194 | 'only_matching': True, | |
195 | }, { | |
196 | 'url': 'svt:14278044', | |
197 | 'only_matching': True, | |
198 | }, { | |
199 | 'url': 'https://www.svt.se/barnkanalen/barnplay/kar/eWv5MLX/', | |
200 | 'only_matching': True, | |
201 | }, { | |
202 | 'url': 'svt:eWv5MLX', | |
203 | 'only_matching': True, | |
204 | }] | |
205 | ||
206 | def _extract_by_video_id(self, video_id, webpage=None): | |
207 | data = self._download_json( | |
208 | 'https://api.svt.se/videoplayer-api/video/%s' % video_id, | |
209 | video_id, headers=self.geo_verification_headers()) | |
210 | info_dict = self._extract_video(data, video_id) | |
211 | if not info_dict.get('title'): | |
212 | title = dict_get(info_dict, ('episode', 'series')) | |
213 | if not title and webpage: | |
214 | title = re.sub( | |
215 | r'\s*\|\s*.+?$', '', self._og_search_title(webpage)) | |
216 | if not title: | |
217 | title = video_id | |
218 | info_dict['title'] = title | |
219 | return info_dict | |
220 | ||
221 | def _real_extract(self, url): | |
222 | mobj = self._match_valid_url(url) | |
223 | video_id = mobj.group('id') | |
224 | svt_id = mobj.group('svt_id') or mobj.group('modal_id') | |
225 | ||
226 | if svt_id: | |
227 | return self._extract_by_video_id(svt_id) | |
228 | ||
229 | webpage = self._download_webpage(url, video_id) | |
230 | ||
231 | data = self._parse_json( | |
232 | self._search_regex( | |
233 | self._SVTPLAY_RE, webpage, 'embedded data', default='{}', | |
234 | group='json'), | |
235 | video_id, fatal=False) | |
236 | ||
237 | thumbnail = self._og_search_thumbnail(webpage) | |
238 | ||
239 | if data: | |
240 | video_info = try_get( | |
241 | data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'], | |
242 | dict) | |
243 | if video_info: | |
244 | info_dict = self._extract_video(video_info, video_id) | |
245 | info_dict.update({ | |
246 | 'title': data['context']['dispatcher']['stores']['MetaStore']['title'], | |
247 | 'thumbnail': thumbnail, | |
248 | }) | |
249 | return info_dict | |
250 | ||
251 | svt_id = try_get( | |
252 | data, lambda x: x['statistics']['dataLake']['content']['id'], | |
253 | compat_str) | |
254 | ||
255 | if not svt_id: | |
256 | svt_id = self._search_regex( | |
257 | (r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)', | |
258 | r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/%s/[^"\']*\b(?:modalId|id)=([\da-zA-Z-]+)' % re.escape(video_id), | |
259 | r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)', | |
260 | r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)', | |
261 | r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"', | |
262 | r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)', | |
263 | r'["\']svtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)'), | |
264 | webpage, 'video id') | |
265 | ||
266 | info_dict = self._extract_by_video_id(svt_id, webpage) | |
267 | info_dict['thumbnail'] = thumbnail | |
268 | ||
269 | return info_dict | |
270 | ||
271 | ||
272 | class SVTSeriesIE(SVTPlayBaseIE): | |
273 | _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?' | |
274 | _TESTS = [{ | |
275 | 'url': 'https://www.svtplay.se/rederiet', | |
276 | 'info_dict': { | |
277 | 'id': '14445680', | |
278 | 'title': 'Rederiet', | |
279 | 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039', | |
280 | }, | |
281 | 'playlist_mincount': 318, | |
282 | }, { | |
283 | 'url': 'https://www.svtplay.se/rederiet?tab=season-2-14445680', | |
284 | 'info_dict': { | |
285 | 'id': 'season-2-14445680', | |
286 | 'title': 'Rederiet - Säsong 2', | |
287 | 'description': 'md5:d9fdfff17f5d8f73468176ecd2836039', | |
288 | }, | |
289 | 'playlist_mincount': 12, | |
290 | }] | |
291 | ||
292 | @classmethod | |
293 | def suitable(cls, url): | |
294 | return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url) | |
295 | ||
296 | def _real_extract(self, url): | |
297 | series_slug, season_id = self._match_valid_url(url).groups() | |
298 | ||
299 | series = self._download_json( | |
300 | 'https://api.svt.se/contento/graphql', series_slug, | |
301 | 'Downloading series page', query={ | |
302 | 'query': '''{ | |
303 | listablesBySlug(slugs: ["%s"]) { | |
304 | associatedContent(include: [productionPeriod, season]) { | |
305 | items { | |
306 | item { | |
307 | ... on Episode { | |
308 | videoSvtId | |
309 | } | |
310 | } | |
311 | } | |
312 | id | |
313 | name | |
314 | } | |
315 | id | |
316 | longDescription | |
317 | name | |
318 | shortDescription | |
319 | } | |
320 | }''' % series_slug, | |
321 | })['data']['listablesBySlug'][0] | |
322 | ||
323 | season_name = None | |
324 | ||
325 | entries = [] | |
326 | for season in series['associatedContent']: | |
327 | if not isinstance(season, dict): | |
328 | continue | |
329 | if season_id: | |
330 | if season.get('id') != season_id: | |
331 | continue | |
332 | season_name = season.get('name') | |
333 | items = season.get('items') | |
334 | if not isinstance(items, list): | |
335 | continue | |
336 | for item in items: | |
337 | video = item.get('item') or {} | |
338 | content_id = video.get('videoSvtId') | |
339 | if not content_id or not isinstance(content_id, compat_str): | |
340 | continue | |
341 | entries.append(self.url_result( | |
342 | 'svt:' + content_id, SVTPlayIE.ie_key(), content_id)) | |
343 | ||
344 | title = series.get('name') | |
345 | season_name = season_name or season_id | |
346 | ||
347 | if title and season_name: | |
348 | title = '%s - %s' % (title, season_name) | |
349 | elif season_id: | |
350 | title = season_id | |
351 | ||
352 | return self.playlist_result( | |
353 | entries, season_id or series.get('id'), title, | |
354 | dict_get(series, ('longDescription', 'shortDescription'))) | |
355 | ||
356 | ||
357 | class SVTPageIE(InfoExtractor): | |
358 | _VALID_URL = r'https?://(?:www\.)?svt\.se/(?P<path>(?:[^/]+/)*(?P<id>[^/?&#]+))' | |
359 | _TESTS = [{ | |
360 | 'url': 'https://www.svt.se/sport/ishockey/bakom-masken-lehners-kamp-mot-mental-ohalsa', | |
361 | 'info_dict': { | |
362 | 'id': '25298267', | |
363 | 'title': 'Bakom masken – Lehners kamp mot mental ohälsa', | |
364 | }, | |
365 | 'playlist_count': 4, | |
366 | }, { | |
367 | 'url': 'https://www.svt.se/nyheter/utrikes/svenska-andrea-ar-en-mil-fran-branderna-i-kalifornien', | |
368 | 'info_dict': { | |
369 | 'id': '24243746', | |
370 | 'title': 'Svenska Andrea redo att fly sitt hem i Kalifornien', | |
371 | }, | |
372 | 'playlist_count': 2, | |
373 | }, { | |
374 | # only programTitle | |
375 | 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', | |
376 | 'info_dict': { | |
377 | 'id': '8439V2K', | |
378 | 'ext': 'mp4', | |
379 | 'title': 'Stjärnorna skojar till det - under SVT-intervjun', | |
380 | 'duration': 27, | |
381 | 'age_limit': 0, | |
382 | }, | |
383 | }, { | |
384 | 'url': 'https://www.svt.se/nyheter/lokalt/vast/svt-testar-tar-nagon-upp-skrapet-1', | |
385 | 'only_matching': True, | |
386 | }, { | |
387 | 'url': 'https://www.svt.se/vader/manadskronikor/maj2018', | |
388 | 'only_matching': True, | |
389 | }] | |
390 | ||
391 | @classmethod | |
392 | def suitable(cls, url): | |
393 | return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTPageIE, cls).suitable(url) | |
394 | ||
395 | def _real_extract(self, url): | |
396 | path, display_id = self._match_valid_url(url).groups() | |
397 | ||
398 | article = self._download_json( | |
399 | 'https://api.svt.se/nss-api/page/' + path, display_id, | |
400 | query={'q': 'articles'})['articles']['content'][0] | |
401 | ||
402 | entries = [] | |
403 | ||
404 | def _process_content(content): | |
405 | if content.get('_type') in ('VIDEOCLIP', 'VIDEOEPISODE'): | |
406 | video_id = compat_str(content['image']['svtId']) | |
407 | entries.append(self.url_result( | |
408 | 'svt:' + video_id, SVTPlayIE.ie_key(), video_id)) | |
409 | ||
410 | for media in article.get('media', []): | |
411 | _process_content(media) | |
412 | ||
413 | for obj in article.get('structuredBody', []): | |
414 | _process_content(obj.get('content') or {}) | |
415 | ||
416 | return self.playlist_result( | |
417 | entries, str_or_none(article.get('id')), | |
418 | strip_or_none(article.get('title'))) |