]>
Commit | Line | Data |
---|---|---|
23b6e230 RA |
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 | ExtractorError, | |
0d0c9e82 | 10 | get_element_by_id, |
574e9db2 | 11 | int_or_none, |
23b6e230 RA |
12 | parse_iso8601, |
13 | parse_duration, | |
de0359c0 | 14 | str_or_none, |
0d0c9e82 | 15 | try_get, |
23b6e230 | 16 | update_url_query, |
de0359c0 | 17 | urljoin, |
23b6e230 RA |
18 | ) |
19 | ||
20 | ||
21 | class TVNowBaseIE(InfoExtractor): | |
22 | _VIDEO_FIELDS = ( | |
23 | 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', | |
574e9db2 | 24 | 'broadcastStartDate', 'isDrm', 'duration', 'season', 'episode', |
8ba84e46 RA |
25 | 'manifest.dashclear', 'manifest.hlsclear', 'manifest.smoothclear', |
26 | 'format.title', 'format.defaultImage169Format', 'format.defaultImage169Logo') | |
23b6e230 RA |
27 | |
28 | def _call_api(self, path, video_id, query): | |
29 | return self._download_json( | |
de0359c0 | 30 | 'https://api.tvnow.de/v3/' + path, video_id, query=query) |
23b6e230 RA |
31 | |
32 | def _extract_video(self, info, display_id): | |
33 | video_id = compat_str(info['id']) | |
34 | title = info['title'] | |
35 | ||
8ba84e46 RA |
36 | paths = [] |
37 | for manifest_url in (info.get('manifest') or {}).values(): | |
38 | if not manifest_url: | |
39 | continue | |
40 | manifest_url = update_url_query(manifest_url, {'filter': ''}) | |
41 | path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path') | |
42 | if path in paths: | |
43 | continue | |
44 | paths.append(path) | |
45 | ||
46 | def url_repl(proto, suffix): | |
47 | return re.sub( | |
48 | r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub( | |
49 | r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)', | |
50 | '.ism/' + suffix, manifest_url)) | |
51 | ||
e75220b1 S |
52 | def make_urls(proto, suffix): |
53 | urls = [url_repl(proto, suffix)] | |
54 | hd_url = urls[0].replace('/manifest/', '/ngvod/') | |
55 | if hd_url != urls[0]: | |
56 | urls.append(hd_url) | |
57 | return urls | |
58 | ||
59 | for man_url in make_urls('dash', '.mpd'): | |
60 | formats = self._extract_mpd_formats( | |
61 | man_url, video_id, mpd_id='dash', fatal=False) | |
62 | for man_url in make_urls('hss', 'Manifest'): | |
63 | formats.extend(self._extract_ism_formats( | |
64 | man_url, video_id, ism_id='mss', fatal=False)) | |
65 | for man_url in make_urls('hls', '.m3u8'): | |
66 | formats.extend(self._extract_m3u8_formats( | |
67 | man_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', | |
68 | fatal=False)) | |
8ba84e46 RA |
69 | if formats: |
70 | break | |
71 | else: | |
a06916d9 | 72 | if not self.get_param('allow_unplayable_formats') and info.get('isDrm'): |
23b6e230 RA |
73 | raise ExtractorError( |
74 | 'Video %s is DRM protected' % video_id, expected=True) | |
75 | if info.get('geoblocked'): | |
8ba84e46 | 76 | raise self.raise_geo_restricted() |
23b6e230 RA |
77 | if not info.get('free', True): |
78 | raise ExtractorError( | |
79 | 'Video %s is not available for free' % video_id, expected=True) | |
23b6e230 RA |
80 | self._sort_formats(formats) |
81 | ||
82 | description = info.get('articleLong') or info.get('articleShort') | |
83 | timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') | |
84 | duration = parse_duration(info.get('duration')) | |
85 | ||
86 | f = info.get('format', {}) | |
ea6679fb S |
87 | |
88 | thumbnails = [{ | |
89 | 'url': 'https://aistvnow-a.akamaihd.net/tvnow/movie/%s' % video_id, | |
90 | }] | |
91 | thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') | |
92 | if thumbnail: | |
93 | thumbnails.append({ | |
94 | 'url': thumbnail, | |
95 | }) | |
23b6e230 RA |
96 | |
97 | return { | |
98 | 'id': video_id, | |
99 | 'display_id': display_id, | |
100 | 'title': title, | |
101 | 'description': description, | |
ea6679fb | 102 | 'thumbnails': thumbnails, |
23b6e230 RA |
103 | 'timestamp': timestamp, |
104 | 'duration': duration, | |
574e9db2 S |
105 | 'series': f.get('title'), |
106 | 'season_number': int_or_none(info.get('season')), | |
107 | 'episode_number': int_or_none(info.get('episode')), | |
108 | 'episode': title, | |
23b6e230 RA |
109 | 'formats': formats, |
110 | } | |
111 | ||
112 | ||
113 | class TVNowIE(TVNowBaseIE): | |
ea6679fb S |
114 | _VALID_URL = r'''(?x) |
115 | https?:// | |
8ba84e46 | 116 | (?:www\.)?tvnow\.(?:de|at|ch)/(?P<station>[^/]+)/ |
ea6679fb S |
117 | (?P<show_id>[^/]+)/ |
118 | (?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+) | |
119 | ''' | |
23b6e230 | 120 | |
de0359c0 S |
121 | @classmethod |
122 | def suitable(cls, url): | |
123 | return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) or TVNowShowIE.suitable(url) | |
124 | else super(TVNowIE, cls).suitable(url)) | |
125 | ||
23b6e230 | 126 | _TESTS = [{ |
574e9db2 | 127 | 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player', |
23b6e230 | 128 | 'info_dict': { |
574e9db2 S |
129 | 'id': '331082', |
130 | 'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3', | |
23b6e230 | 131 | 'ext': 'mp4', |
574e9db2 S |
132 | 'title': 'Der neue Porsche 911 GT 3', |
133 | 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', | |
574e9db2 S |
134 | 'timestamp': 1495994400, |
135 | 'upload_date': '20170528', | |
136 | 'duration': 5283, | |
137 | 'series': 'GRIP - Das Motormagazin', | |
138 | 'season_number': 14, | |
139 | 'episode_number': 405, | |
140 | 'episode': 'Der neue Porsche 911 GT 3', | |
23b6e230 RA |
141 | }, |
142 | }, { | |
143 | # rtl2 | |
144 | 'url': 'https://www.tvnow.de/rtl2/armes-deutschland/episode-0008/player', | |
ea6679fb | 145 | 'only_matching': True, |
23b6e230 RA |
146 | }, { |
147 | # rtlnitro | |
148 | 'url': 'https://www.tvnow.de/nitro/alarm-fuer-cobra-11-die-autobahnpolizei/auf-eigene-faust-pilot/player', | |
ea6679fb | 149 | 'only_matching': True, |
23b6e230 RA |
150 | }, { |
151 | # superrtl | |
152 | 'url': 'https://www.tvnow.de/superrtl/die-lustigsten-schlamassel-der-welt/u-a-ketchup-effekt/player', | |
ea6679fb | 153 | 'only_matching': True, |
23b6e230 RA |
154 | }, { |
155 | # ntv | |
156 | 'url': 'https://www.tvnow.de/ntv/startup-news/goetter-in-weiss/player', | |
ea6679fb | 157 | 'only_matching': True, |
23b6e230 RA |
158 | }, { |
159 | # vox | |
160 | 'url': 'https://www.tvnow.de/vox/auto-mobil/neues-vom-automobilmarkt-2017-11-19-17-00-00/player', | |
ea6679fb | 161 | 'only_matching': True, |
23b6e230 RA |
162 | }, { |
163 | # rtlplus | |
164 | 'url': 'https://www.tvnow.de/rtlplus/op-ruft-dr-bruckner/die-vernaehte-frau/player', | |
ea6679fb S |
165 | 'only_matching': True, |
166 | }, { | |
167 | 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3', | |
168 | 'only_matching': True, | |
23b6e230 RA |
169 | }] |
170 | ||
171 | def _real_extract(self, url): | |
8ba84e46 RA |
172 | mobj = re.match(self._VALID_URL, url) |
173 | display_id = '%s/%s' % mobj.group(2, 3) | |
23b6e230 RA |
174 | |
175 | info = self._call_api( | |
176 | 'movies/' + display_id, display_id, query={ | |
177 | 'fields': ','.join(self._VIDEO_FIELDS), | |
178 | }) | |
179 | ||
180 | return self._extract_video(info, display_id) | |
181 | ||
182 | ||
de0359c0 S |
183 | class TVNowNewIE(InfoExtractor): |
184 | _VALID_URL = r'''(?x) | |
185 | (?P<base_url>https?:// | |
186 | (?:www\.)?tvnow\.(?:de|at|ch)/ | |
187 | (?:shows|serien))/ | |
188 | (?P<show>[^/]+)-\d+/ | |
189 | [^/]+/ | |
190 | episode-\d+-(?P<episode>[^/?$&]+)-(?P<id>\d+) | |
ea6679fb S |
191 | ''' |
192 | ||
de0359c0 S |
193 | _TESTS = [{ |
194 | 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', | |
195 | 'only_matching': True, | |
196 | }] | |
23b6e230 | 197 | |
de0359c0 S |
198 | def _real_extract(self, url): |
199 | mobj = re.match(self._VALID_URL, url) | |
200 | base_url = re.sub(r'(?:shows|serien)', '_', mobj.group('base_url')) | |
201 | show, episode = mobj.group('show', 'episode') | |
202 | return self.url_result( | |
203 | # Rewrite new URLs to the old format and use extraction via old API | |
204 | # at api.tvnow.de as a loophole for bypassing premium content checks | |
205 | '%s/%s/%s' % (base_url, show, episode), | |
206 | ie=TVNowIE.ie_key(), video_id=mobj.group('id')) | |
207 | ||
208 | ||
0d0c9e82 T |
209 | class TVNowFilmIE(TVNowBaseIE): |
210 | _VALID_URL = r'''(?x) | |
211 | (?P<base_url>https?:// | |
212 | (?:www\.)?tvnow\.(?:de|at|ch)/ | |
213 | (?:filme))/ | |
214 | (?P<title>[^/?$&]+)-(?P<id>\d+) | |
215 | ''' | |
216 | _TESTS = [{ | |
217 | 'url': 'https://www.tvnow.de/filme/lord-of-war-haendler-des-todes-7959', | |
218 | 'info_dict': { | |
219 | 'id': '1426690', | |
220 | 'display_id': 'lord-of-war-haendler-des-todes', | |
221 | 'ext': 'mp4', | |
222 | 'title': 'Lord of War', | |
223 | 'description': 'md5:5eda15c0d5b8cb70dac724c8a0ff89a9', | |
224 | 'timestamp': 1550010000, | |
225 | 'upload_date': '20190212', | |
226 | 'duration': 7016, | |
227 | }, | |
228 | }, { | |
229 | 'url': 'https://www.tvnow.de/filme/the-machinist-12157', | |
230 | 'info_dict': { | |
231 | 'id': '328160', | |
232 | 'display_id': 'the-machinist', | |
233 | 'ext': 'mp4', | |
234 | 'title': 'The Machinist', | |
235 | 'description': 'md5:9a0e363fdd74b3a9e1cdd9e21d0ecc28', | |
236 | 'timestamp': 1496469720, | |
237 | 'upload_date': '20170603', | |
238 | 'duration': 5836, | |
239 | }, | |
240 | }, { | |
241 | 'url': 'https://www.tvnow.de/filme/horst-schlaemmer-isch-kandidiere-17777', | |
242 | 'only_matching': True, # DRM protected | |
243 | }] | |
244 | ||
245 | def _real_extract(self, url): | |
246 | mobj = re.match(self._VALID_URL, url) | |
247 | display_id = mobj.group('title') | |
248 | ||
249 | webpage = self._download_webpage(url, display_id, fatal=False) | |
250 | if not webpage: | |
251 | raise ExtractorError('Cannot download "%s"' % url, expected=True) | |
252 | ||
253 | json_text = get_element_by_id('now-web-state', webpage) | |
254 | if not json_text: | |
255 | raise ExtractorError('Cannot read video data', expected=True) | |
256 | ||
257 | json_data = self._parse_json( | |
258 | json_text, | |
259 | display_id, | |
260 | transform_source=lambda x: x.replace('&q;', '"'), | |
261 | fatal=False) | |
262 | if not json_data: | |
263 | raise ExtractorError('Cannot read video data', expected=True) | |
264 | ||
265 | player_key = next( | |
266 | (key for key in json_data.keys() if 'module/player' in key), | |
267 | None) | |
268 | page_key = next( | |
269 | (key for key in json_data.keys() if 'page/filme' in key), | |
270 | None) | |
271 | movie_id = try_get( | |
272 | json_data, | |
273 | [ | |
274 | lambda x: x[player_key]['body']['id'], | |
275 | lambda x: x[page_key]['body']['modules'][0]['id'], | |
276 | lambda x: x[page_key]['body']['modules'][1]['id']], | |
277 | int) | |
278 | if not movie_id: | |
279 | raise ExtractorError('Cannot extract movie ID', expected=True) | |
280 | ||
281 | info = self._call_api( | |
282 | 'movies/%d' % movie_id, | |
283 | display_id, | |
284 | query={'fields': ','.join(self._VIDEO_FIELDS)}) | |
285 | ||
286 | return self._extract_video(info, display_id) | |
287 | ||
288 | ||
de0359c0 S |
289 | class TVNowNewBaseIE(InfoExtractor): |
290 | def _call_api(self, path, video_id, query={}): | |
291 | result = self._download_json( | |
292 | 'https://apigw.tvnow.de/module/' + path, video_id, query=query) | |
293 | error = result.get('error') | |
294 | if error: | |
295 | raise ExtractorError( | |
296 | '%s said: %s' % (self.IE_NAME, error), expected=True) | |
297 | return result | |
298 | ||
299 | ||
d23e8551 | 300 | r""" |
de0359c0 S |
301 | TODO: new apigw.tvnow.de based version of TVNowIE. Replace old TVNowIE with it |
302 | when api.tvnow.de is shut down. This version can't bypass premium checks though. | |
303 | class TVNowIE(TVNowNewBaseIE): | |
304 | _VALID_URL = r'''(?x) | |
305 | https?:// | |
306 | (?:www\.)?tvnow\.(?:de|at|ch)/ | |
307 | (?:shows|serien)/[^/]+/ | |
308 | (?:[^/]+/)+ | |
309 | (?P<display_id>[^/?$&]+)-(?P<id>\d+) | |
310 | ''' | |
23b6e230 RA |
311 | |
312 | _TESTS = [{ | |
de0359c0 S |
313 | # episode with annual navigation |
314 | 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', | |
23b6e230 | 315 | 'info_dict': { |
de0359c0 S |
316 | 'id': '331082', |
317 | 'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3', | |
318 | 'ext': 'mp4', | |
319 | 'title': 'Der neue Porsche 911 GT 3', | |
320 | 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', | |
321 | 'thumbnail': r're:^https?://.*\.jpg$', | |
322 | 'timestamp': 1495994400, | |
323 | 'upload_date': '20170528', | |
324 | 'duration': 5283, | |
325 | 'series': 'GRIP - Das Motormagazin', | |
326 | 'season_number': 14, | |
327 | 'episode_number': 405, | |
328 | 'episode': 'Der neue Porsche 911 GT 3', | |
23b6e230 | 329 | }, |
ea6679fb | 330 | }, { |
de0359c0 S |
331 | # rtl2, episode with season navigation |
332 | 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471/staffel-3/episode-14-bernd-steht-seit-der-trennung-von-seiner-frau-allein-da-526124', | |
ea6679fb S |
333 | 'only_matching': True, |
334 | }, { | |
de0359c0 S |
335 | # rtlnitro |
336 | 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13/episode-5-auf-eigene-faust-pilot-366822', | |
337 | 'only_matching': True, | |
338 | }, { | |
339 | # superrtl | |
340 | 'url': 'https://www.tvnow.de/shows/die-lustigsten-schlamassel-der-welt-1221/staffel-2/episode-14-u-a-ketchup-effekt-364120', | |
341 | 'only_matching': True, | |
342 | }, { | |
343 | # ntv | |
344 | 'url': 'https://www.tvnow.de/shows/startup-news-10674/staffel-2/episode-39-goetter-in-weiss-387630', | |
345 | 'only_matching': True, | |
346 | }, { | |
347 | # vox | |
348 | 'url': 'https://www.tvnow.de/shows/auto-mobil-174/2017-11/episode-46-neues-vom-automobilmarkt-2017-11-19-17-00-00-380072', | |
349 | 'only_matching': True, | |
350 | }, { | |
351 | 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', | |
ea6679fb | 352 | 'only_matching': True, |
23b6e230 RA |
353 | }] |
354 | ||
de0359c0 S |
355 | def _extract_video(self, info, url, display_id): |
356 | config = info['config'] | |
357 | source = config['source'] | |
ea6679fb | 358 | |
de0359c0 S |
359 | video_id = compat_str(info.get('id') or source['videoId']) |
360 | title = source['title'].strip() | |
23b6e230 | 361 | |
de0359c0 S |
362 | paths = [] |
363 | for manifest_url in (info.get('manifest') or {}).values(): | |
364 | if not manifest_url: | |
365 | continue | |
366 | manifest_url = update_url_query(manifest_url, {'filter': ''}) | |
367 | path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path') | |
368 | if path in paths: | |
369 | continue | |
370 | paths.append(path) | |
23b6e230 | 371 | |
de0359c0 S |
372 | def url_repl(proto, suffix): |
373 | return re.sub( | |
374 | r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub( | |
375 | r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)', | |
376 | '.ism/' + suffix, manifest_url)) | |
23b6e230 | 377 | |
de0359c0 S |
378 | formats = self._extract_mpd_formats( |
379 | url_repl('dash', '.mpd'), video_id, | |
380 | mpd_id='dash', fatal=False) | |
381 | formats.extend(self._extract_ism_formats( | |
382 | url_repl('hss', 'Manifest'), | |
383 | video_id, ism_id='mss', fatal=False)) | |
384 | formats.extend(self._extract_m3u8_formats( | |
385 | url_repl('hls', '.m3u8'), video_id, 'mp4', | |
386 | 'm3u8_native', m3u8_id='hls', fatal=False)) | |
387 | if formats: | |
388 | break | |
ea6679fb | 389 | else: |
de0359c0 S |
390 | if try_get(info, lambda x: x['rights']['isDrm']): |
391 | raise ExtractorError( | |
392 | 'Video %s is DRM protected' % video_id, expected=True) | |
393 | if try_get(config, lambda x: x['boards']['geoBlocking']['block']): | |
394 | raise self.raise_geo_restricted() | |
395 | if not info.get('free', True): | |
396 | raise ExtractorError( | |
397 | 'Video %s is not available for free' % video_id, expected=True) | |
398 | self._sort_formats(formats) | |
399 | ||
400 | description = source.get('description') | |
401 | thumbnail = url_or_none(source.get('poster')) | |
402 | timestamp = unified_timestamp(source.get('previewStart')) | |
403 | duration = parse_duration(source.get('length')) | |
404 | ||
405 | series = source.get('format') | |
406 | season_number = int_or_none(self._search_regex( | |
407 | r'staffel-(\d+)', url, 'season number', default=None)) | |
408 | episode_number = int_or_none(self._search_regex( | |
409 | r'episode-(\d+)', url, 'episode number', default=None)) | |
410 | ||
411 | return { | |
412 | 'id': video_id, | |
413 | 'display_id': display_id, | |
414 | 'title': title, | |
415 | 'description': description, | |
416 | 'thumbnail': thumbnail, | |
417 | 'timestamp': timestamp, | |
418 | 'duration': duration, | |
419 | 'series': series, | |
420 | 'season_number': season_number, | |
421 | 'episode_number': episode_number, | |
422 | 'episode': title, | |
423 | 'formats': formats, | |
424 | } | |
425 | ||
426 | def _real_extract(self, url): | |
427 | display_id, video_id = re.match(self._VALID_URL, url).groups() | |
428 | info = self._call_api('player/' + video_id, video_id) | |
429 | return self._extract_video(info, video_id, display_id) | |
0d0c9e82 T |
430 | |
431 | ||
432 | class TVNowFilmIE(TVNowIE): | |
433 | _VALID_URL = r'''(?x) | |
434 | (?P<base_url>https?:// | |
435 | (?:www\.)?tvnow\.(?:de|at|ch)/ | |
436 | (?:filme))/ | |
437 | (?P<title>[^/?$&]+)-(?P<id>\d+) | |
438 | ''' | |
439 | _TESTS = [{ | |
440 | 'url': 'https://www.tvnow.de/filme/lord-of-war-haendler-des-todes-7959', | |
441 | 'info_dict': { | |
442 | 'id': '1426690', | |
443 | 'display_id': 'lord-of-war-haendler-des-todes', | |
444 | 'ext': 'mp4', | |
445 | 'title': 'Lord of War', | |
446 | 'description': 'md5:5eda15c0d5b8cb70dac724c8a0ff89a9', | |
447 | 'timestamp': 1550010000, | |
448 | 'upload_date': '20190212', | |
449 | 'duration': 7016, | |
450 | }, | |
451 | }, { | |
452 | 'url': 'https://www.tvnow.de/filme/the-machinist-12157', | |
453 | 'info_dict': { | |
454 | 'id': '328160', | |
455 | 'display_id': 'the-machinist', | |
456 | 'ext': 'mp4', | |
457 | 'title': 'The Machinist', | |
458 | 'description': 'md5:9a0e363fdd74b3a9e1cdd9e21d0ecc28', | |
459 | 'timestamp': 1496469720, | |
460 | 'upload_date': '20170603', | |
461 | 'duration': 5836, | |
462 | }, | |
463 | }, { | |
464 | 'url': 'https://www.tvnow.de/filme/horst-schlaemmer-isch-kandidiere-17777', | |
465 | 'only_matching': True, # DRM protected | |
466 | }] | |
467 | ||
468 | def _real_extract(self, url): | |
469 | mobj = re.match(self._VALID_URL, url) | |
470 | display_id = mobj.group('title') | |
471 | ||
472 | webpage = self._download_webpage(url, display_id, fatal=False) | |
473 | if not webpage: | |
474 | raise ExtractorError('Cannot download "%s"' % url, expected=True) | |
475 | ||
476 | json_text = get_element_by_id('now-web-state', webpage) | |
477 | if not json_text: | |
478 | raise ExtractorError('Cannot read video data', expected=True) | |
479 | ||
480 | json_data = self._parse_json( | |
481 | json_text, | |
482 | display_id, | |
483 | transform_source=lambda x: x.replace('&q;', '"'), | |
484 | fatal=False) | |
485 | if not json_data: | |
486 | raise ExtractorError('Cannot read video data', expected=True) | |
487 | ||
488 | player_key = next( | |
489 | (key for key in json_data.keys() if 'module/player' in key), | |
490 | None) | |
491 | page_key = next( | |
492 | (key for key in json_data.keys() if 'page/filme' in key), | |
493 | None) | |
494 | movie_id = try_get( | |
495 | json_data, | |
496 | [ | |
497 | lambda x: x[player_key]['body']['id'], | |
498 | lambda x: x[page_key]['body']['modules'][0]['id'], | |
499 | lambda x: x[page_key]['body']['modules'][1]['id']], | |
500 | int) | |
501 | if not movie_id: | |
502 | raise ExtractorError('Cannot extract movie ID', expected=True) | |
503 | ||
504 | info = self._call_api('player/%d' % movie_id, display_id) | |
505 | return self._extract_video(info, url, display_id) | |
de0359c0 S |
506 | """ |
507 | ||
508 | ||
509 | class TVNowListBaseIE(TVNowNewBaseIE): | |
510 | _SHOW_VALID_URL = r'''(?x) | |
511 | (?P<base_url> | |
512 | https?:// | |
513 | (?:www\.)?tvnow\.(?:de|at|ch)/(?:shows|serien)/ | |
514 | [^/?#&]+-(?P<show_id>\d+) | |
515 | ) | |
516 | ''' | |
517 | ||
518 | @classmethod | |
519 | def suitable(cls, url): | |
520 | return (False if TVNowNewIE.suitable(url) | |
521 | else super(TVNowListBaseIE, cls).suitable(url)) | |
522 | ||
523 | def _extract_items(self, url, show_id, list_id, query): | |
524 | items = self._call_api( | |
525 | 'teaserrow/format/episode/' + show_id, list_id, | |
526 | query=query)['items'] | |
23b6e230 RA |
527 | |
528 | entries = [] | |
de0359c0 S |
529 | for item in items: |
530 | if not isinstance(item, dict): | |
531 | continue | |
532 | item_url = urljoin(url, item.get('url')) | |
533 | if not item_url: | |
534 | continue | |
535 | video_id = str_or_none(item.get('id') or item.get('videoId')) | |
536 | item_title = item.get('subheadline') or item.get('text') | |
537 | entries.append(self.url_result( | |
538 | item_url, ie=TVNowNewIE.ie_key(), video_id=video_id, | |
539 | video_title=item_title)) | |
23b6e230 | 540 | |
de0359c0 | 541 | return self.playlist_result(entries, '%s/%s' % (show_id, list_id)) |
3acae1e0 A |
542 | |
543 | ||
de0359c0 S |
544 | class TVNowSeasonIE(TVNowListBaseIE): |
545 | _VALID_URL = r'%s/staffel-(?P<id>\d+)' % TVNowListBaseIE._SHOW_VALID_URL | |
546 | _TESTS = [{ | |
547 | 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13', | |
548 | 'info_dict': { | |
549 | 'id': '1815/13', | |
550 | }, | |
551 | 'playlist_mincount': 22, | |
552 | }] | |
553 | ||
554 | def _real_extract(self, url): | |
555 | _, show_id, season_id = re.match(self._VALID_URL, url).groups() | |
556 | return self._extract_items( | |
557 | url, show_id, season_id, {'season': season_id}) | |
3acae1e0 | 558 | |
3acae1e0 | 559 | |
de0359c0 S |
560 | class TVNowAnnualIE(TVNowListBaseIE): |
561 | _VALID_URL = r'%s/(?P<year>\d{4})-(?P<month>\d{2})' % TVNowListBaseIE._SHOW_VALID_URL | |
3acae1e0 | 562 | _TESTS = [{ |
de0359c0 | 563 | 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05', |
ea6679fb | 564 | 'info_dict': { |
de0359c0 | 565 | 'id': '1669/2017-05', |
ea6679fb | 566 | }, |
de0359c0 S |
567 | 'playlist_mincount': 2, |
568 | }] | |
569 | ||
570 | def _real_extract(self, url): | |
571 | _, show_id, year, month = re.match(self._VALID_URL, url).groups() | |
572 | return self._extract_items( | |
573 | url, show_id, '%s-%s' % (year, month), { | |
574 | 'year': int(year), | |
575 | 'month': int(month), | |
576 | }) | |
577 | ||
578 | ||
579 | class TVNowShowIE(TVNowListBaseIE): | |
580 | _VALID_URL = TVNowListBaseIE._SHOW_VALID_URL | |
581 | _TESTS = [{ | |
582 | # annual navigationType | |
583 | 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669', | |
584 | 'info_dict': { | |
585 | 'id': '1669', | |
586 | }, | |
587 | 'playlist_mincount': 73, | |
ea6679fb | 588 | }, { |
de0359c0 S |
589 | # season navigationType |
590 | 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471', | |
591 | 'info_dict': { | |
592 | 'id': '11471', | |
593 | }, | |
594 | 'playlist_mincount': 3, | |
3acae1e0 A |
595 | }] |
596 | ||
597 | @classmethod | |
598 | def suitable(cls, url): | |
de0359c0 | 599 | return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) |
ea6679fb | 600 | else super(TVNowShowIE, cls).suitable(url)) |
3acae1e0 A |
601 | |
602 | def _real_extract(self, url): | |
603 | base_url, show_id = re.match(self._VALID_URL, url).groups() | |
604 | ||
de0359c0 S |
605 | result = self._call_api( |
606 | 'teaserrow/format/navigation/' + show_id, show_id) | |
607 | ||
608 | items = result['items'] | |
3acae1e0 A |
609 | |
610 | entries = [] | |
de0359c0 S |
611 | navigation = result.get('navigationType') |
612 | if navigation == 'annual': | |
613 | for item in items: | |
614 | if not isinstance(item, dict): | |
615 | continue | |
616 | year = int_or_none(item.get('year')) | |
617 | if year is None: | |
618 | continue | |
619 | months = item.get('months') | |
620 | if not isinstance(months, list): | |
621 | continue | |
622 | for month_dict in months: | |
623 | if not isinstance(month_dict, dict) or not month_dict: | |
624 | continue | |
625 | month_number = int_or_none(list(month_dict.keys())[0]) | |
626 | if month_number is None: | |
627 | continue | |
628 | entries.append(self.url_result( | |
629 | '%s/%04d-%02d' % (base_url, year, month_number), | |
630 | ie=TVNowAnnualIE.ie_key())) | |
631 | elif navigation == 'season': | |
632 | for item in items: | |
633 | if not isinstance(item, dict): | |
634 | continue | |
635 | season_number = int_or_none(item.get('season')) | |
636 | if season_number is None: | |
637 | continue | |
638 | entries.append(self.url_result( | |
639 | '%s/staffel-%d' % (base_url, season_number), | |
640 | ie=TVNowSeasonIE.ie_key())) | |
641 | else: | |
642 | raise ExtractorError('Unknown navigationType') | |
3acae1e0 | 643 | |
de0359c0 | 644 | return self.playlist_result(entries, show_id) |