]>
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 ( | |
8 | compat_urlparse, | |
9 | compat_str, | |
10 | ) | |
11 | from ..utils import ( | |
12 | ExtractorError, | |
13 | determine_ext, | |
14 | find_xpath_attr, | |
15 | fix_xml_ampersands, | |
16 | GeoRestrictedError, | |
17 | int_or_none, | |
18 | parse_duration, | |
19 | remove_start, | |
20 | strip_or_none, | |
21 | try_get, | |
22 | unified_strdate, | |
23 | unified_timestamp, | |
24 | update_url_query, | |
25 | urljoin, | |
26 | xpath_text, | |
27 | ) | |
28 | ||
29 | ||
30 | class RaiBaseIE(InfoExtractor): | |
31 | _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}' | |
32 | _GEO_COUNTRIES = ['IT'] | |
33 | _GEO_BYPASS = False | |
34 | ||
35 | def _extract_relinker_info(self, relinker_url, video_id): | |
36 | if not re.match(r'https?://', relinker_url): | |
37 | return {'formats': [{'url': relinker_url}]} | |
38 | ||
39 | formats = [] | |
40 | geoprotection = None | |
41 | is_live = None | |
42 | duration = None | |
43 | ||
44 | for platform in ('mon', 'flash', 'native'): | |
45 | relinker = self._download_xml( | |
46 | relinker_url, video_id, | |
47 | note='Downloading XML metadata for platform %s' % platform, | |
48 | transform_source=fix_xml_ampersands, | |
49 | query={'output': 45, 'pl': platform}, | |
50 | headers=self.geo_verification_headers()) | |
51 | ||
52 | if not geoprotection: | |
53 | geoprotection = xpath_text( | |
54 | relinker, './geoprotection', default=None) == 'Y' | |
55 | ||
56 | if not is_live: | |
57 | is_live = xpath_text( | |
58 | relinker, './is_live', default=None) == 'Y' | |
59 | if not duration: | |
60 | duration = parse_duration(xpath_text( | |
61 | relinker, './duration', default=None)) | |
62 | ||
63 | url_elem = find_xpath_attr(relinker, './url', 'type', 'content') | |
64 | if url_elem is None: | |
65 | continue | |
66 | ||
67 | media_url = url_elem.text | |
68 | ||
69 | # This does not imply geo restriction (e.g. | |
70 | # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html) | |
71 | if '/video_no_available.mp4' in media_url: | |
72 | continue | |
73 | ||
74 | ext = determine_ext(media_url) | |
75 | if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'): | |
76 | continue | |
77 | ||
78 | if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon': | |
79 | formats.extend(self._extract_m3u8_formats( | |
80 | media_url, video_id, 'mp4', 'm3u8_native', | |
81 | m3u8_id='hls', fatal=False)) | |
82 | elif ext == 'f4m' or platform == 'flash': | |
83 | manifest_url = update_url_query( | |
84 | media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'), | |
85 | {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'}) | |
86 | formats.extend(self._extract_f4m_formats( | |
87 | manifest_url, video_id, f4m_id='hds', fatal=False)) | |
88 | else: | |
89 | bitrate = int_or_none(xpath_text(relinker, 'bitrate')) | |
90 | formats.append({ | |
91 | 'url': media_url, | |
92 | 'tbr': bitrate if bitrate > 0 else None, | |
93 | 'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http', | |
94 | }) | |
95 | ||
96 | if not formats and geoprotection is True: | |
97 | self.raise_geo_restricted(countries=self._GEO_COUNTRIES) | |
98 | ||
99 | return dict((k, v) for k, v in { | |
100 | 'is_live': is_live, | |
101 | 'duration': duration, | |
102 | 'formats': formats, | |
103 | }.items() if v is not None) | |
104 | ||
105 | @staticmethod | |
106 | def _extract_subtitles(url, video_data): | |
107 | STL_EXT = 'stl' | |
108 | SRT_EXT = 'srt' | |
109 | subtitles = {} | |
110 | subtitles_array = video_data.get('subtitlesArray') or [] | |
111 | for k in ('subtitles', 'subtitlesUrl'): | |
112 | subtitles_array.append({'url': video_data.get(k)}) | |
113 | for subtitle in subtitles_array: | |
114 | sub_url = subtitle.get('url') | |
115 | if sub_url and isinstance(sub_url, compat_str): | |
116 | sub_lang = subtitle.get('language') or 'it' | |
117 | sub_url = urljoin(url, sub_url) | |
118 | sub_ext = determine_ext(sub_url, SRT_EXT) | |
119 | subtitles.setdefault(sub_lang, []).append({ | |
120 | 'ext': sub_ext, | |
121 | 'url': sub_url, | |
122 | }) | |
123 | if STL_EXT == sub_ext: | |
124 | subtitles[sub_lang].append({ | |
125 | 'ext': SRT_EXT, | |
126 | 'url': sub_url[:-len(STL_EXT)] + SRT_EXT, | |
127 | }) | |
128 | return subtitles | |
129 | ||
130 | ||
131 | class RaiPlayIE(RaiBaseIE): | |
132 | _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE | |
133 | _TESTS = [{ | |
134 | 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html', | |
135 | 'md5': '8970abf8caf8aef4696e7b1f2adfc696', | |
136 | 'info_dict': { | |
137 | 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391', | |
138 | 'ext': 'mp4', | |
139 | 'title': 'Report del 07/04/2014', | |
140 | 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014', | |
141 | 'description': 'md5:d730c168a58f4bb35600fc2f881ec04e', | |
142 | 'thumbnail': r're:^https?://.*\.jpg$', | |
143 | 'uploader': 'Rai Gulp', | |
144 | 'duration': 6160, | |
145 | 'series': 'Report', | |
146 | 'season': '2013/14', | |
147 | 'subtitles': { | |
148 | 'it': 'count:2', | |
149 | }, | |
150 | }, | |
151 | 'params': { | |
152 | 'skip_download': True, | |
153 | }, | |
154 | }, { | |
155 | 'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?', | |
156 | 'only_matching': True, | |
157 | }, { | |
158 | # subtitles at 'subtitlesArray' key (see #27698) | |
159 | 'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html', | |
160 | 'only_matching': True, | |
161 | }] | |
162 | ||
163 | def _real_extract(self, url): | |
164 | base, video_id = re.match(self._VALID_URL, url).groups() | |
165 | ||
166 | media = self._download_json( | |
167 | base + '.json', video_id, 'Downloading video JSON') | |
168 | ||
169 | title = media['name'] | |
170 | video = media['video'] | |
171 | ||
172 | relinker_info = self._extract_relinker_info(video['content_url'], video_id) | |
173 | self._sort_formats(relinker_info['formats']) | |
174 | ||
175 | thumbnails = [] | |
176 | for _, value in media.get('images', {}).items(): | |
177 | if value: | |
178 | thumbnails.append({ | |
179 | 'url': urljoin(url, value), | |
180 | }) | |
181 | ||
182 | date_published = media.get('date_published') | |
183 | time_published = media.get('time_published') | |
184 | if date_published and time_published: | |
185 | date_published += ' ' + time_published | |
186 | ||
187 | subtitles = self._extract_subtitles(url, video) | |
188 | ||
189 | program_info = media.get('program_info') or {} | |
190 | season = media.get('season') | |
191 | ||
192 | info = { | |
193 | 'id': remove_start(media.get('id'), 'ContentItem-') or video_id, | |
194 | 'display_id': video_id, | |
195 | 'title': self._live_title(title) if relinker_info.get( | |
196 | 'is_live') else title, | |
197 | 'alt_title': strip_or_none(media.get('subtitle')), | |
198 | 'description': media.get('description'), | |
199 | 'uploader': strip_or_none(media.get('channel')), | |
200 | 'creator': strip_or_none(media.get('editor') or None), | |
201 | 'duration': parse_duration(video.get('duration')), | |
202 | 'timestamp': unified_timestamp(date_published), | |
203 | 'thumbnails': thumbnails, | |
204 | 'series': program_info.get('name'), | |
205 | 'season_number': int_or_none(season), | |
206 | 'season': season if (season and not season.isdigit()) else None, | |
207 | 'episode': media.get('episode_title'), | |
208 | 'episode_number': int_or_none(media.get('episode')), | |
209 | 'subtitles': subtitles, | |
210 | } | |
211 | ||
212 | info.update(relinker_info) | |
213 | return info | |
214 | ||
215 | ||
216 | class RaiPlayLiveIE(RaiPlayIE): | |
217 | _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))' | |
218 | _TESTS = [{ | |
219 | 'url': 'http://www.raiplay.it/dirette/rainews24', | |
220 | 'info_dict': { | |
221 | 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c', | |
222 | 'display_id': 'rainews24', | |
223 | 'ext': 'mp4', | |
224 | 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', | |
225 | 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497', | |
226 | 'uploader': 'Rai News 24', | |
227 | 'creator': 'Rai News 24', | |
228 | 'is_live': True, | |
229 | }, | |
230 | 'params': { | |
231 | 'skip_download': True, | |
232 | }, | |
233 | }] | |
234 | ||
235 | ||
236 | class RaiPlayPlaylistIE(InfoExtractor): | |
237 | _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))' | |
238 | _TESTS = [{ | |
239 | 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', | |
240 | 'info_dict': { | |
241 | 'id': 'nondirloalmiocapo', | |
242 | 'title': 'Non dirlo al mio capo', | |
243 | 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b', | |
244 | }, | |
245 | 'playlist_mincount': 12, | |
246 | }] | |
247 | ||
248 | def _real_extract(self, url): | |
249 | base, playlist_id = re.match(self._VALID_URL, url).groups() | |
250 | ||
251 | program = self._download_json( | |
252 | base + '.json', playlist_id, 'Downloading program JSON') | |
253 | ||
254 | entries = [] | |
255 | for b in (program.get('blocks') or []): | |
256 | for s in (b.get('sets') or []): | |
257 | s_id = s.get('id') | |
258 | if not s_id: | |
259 | continue | |
260 | medias = self._download_json( | |
261 | '%s/%s.json' % (base, s_id), s_id, | |
262 | 'Downloading content set JSON', fatal=False) | |
263 | if not medias: | |
264 | continue | |
265 | for m in (medias.get('items') or []): | |
266 | path_id = m.get('path_id') | |
267 | if not path_id: | |
268 | continue | |
269 | video_url = urljoin(url, path_id) | |
270 | entries.append(self.url_result( | |
271 | video_url, ie=RaiPlayIE.ie_key(), | |
272 | video_id=RaiPlayIE._match_id(video_url))) | |
273 | ||
274 | return self.playlist_result( | |
275 | entries, playlist_id, program.get('name'), | |
276 | try_get(program, lambda x: x['program_info']['description'])) | |
277 | ||
278 | ||
279 | class RaiIE(RaiBaseIE): | |
280 | _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE | |
281 | _TESTS = [{ | |
282 | # var uniquename = "ContentItem-..." | |
283 | # data-id="ContentItem-..." | |
284 | 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html', | |
285 | 'info_dict': { | |
286 | 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9', | |
287 | 'ext': 'mp4', | |
288 | 'title': 'TG PRIMO TEMPO', | |
289 | 'thumbnail': r're:^https?://.*\.jpg$', | |
290 | 'duration': 1758, | |
291 | 'upload_date': '20140612', | |
292 | }, | |
293 | 'skip': 'This content is available only in Italy', | |
294 | }, { | |
295 | # with ContentItem in many metas | |
296 | 'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html', | |
297 | 'info_dict': { | |
298 | 'id': '1632c009-c843-4836-bb65-80c33084a64b', | |
299 | 'ext': 'mp4', | |
300 | 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"', | |
301 | 'description': 'I film in uscita questa settimana.', | |
302 | 'thumbnail': r're:^https?://.*\.png$', | |
303 | 'duration': 833, | |
304 | 'upload_date': '20161103', | |
305 | } | |
306 | }, { | |
307 | # with ContentItem in og:url | |
308 | 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html', | |
309 | 'md5': '6865dd00cf0bbf5772fdd89d59bd768a', | |
310 | 'info_dict': { | |
311 | 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c', | |
312 | 'ext': 'mp4', | |
313 | 'title': 'TG1 ore 20:00 del 03/11/2016', | |
314 | 'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016', | |
315 | 'thumbnail': r're:^https?://.*\.jpg$', | |
316 | 'duration': 2214, | |
317 | 'upload_date': '20161103', | |
318 | } | |
319 | }, { | |
320 | # initEdizione('ContentItem-...' | |
321 | 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined', | |
322 | 'info_dict': { | |
323 | 'id': 'c2187016-8484-4e3a-8ac8-35e475b07303', | |
324 | 'ext': 'mp4', | |
325 | 'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}', | |
326 | 'duration': 2274, | |
327 | 'upload_date': '20170401', | |
328 | }, | |
329 | 'skip': 'Changes daily', | |
330 | }, { | |
331 | # HLS live stream with ContentItem in og:url | |
332 | 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html', | |
333 | 'info_dict': { | |
334 | 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9', | |
335 | 'ext': 'mp4', | |
336 | 'title': 'La diretta di Rainews24', | |
337 | }, | |
338 | 'params': { | |
339 | 'skip_download': True, | |
340 | }, | |
341 | }, { | |
342 | # ContentItem in iframe (see #12652) and subtitle at 'subtitlesUrl' key | |
343 | 'url': 'http://www.presadiretta.rai.it/dl/portali/site/puntata/ContentItem-3ed19d13-26c2-46ff-a551-b10828262f1b.html', | |
344 | 'info_dict': { | |
345 | 'id': '1ad6dc64-444a-42a4-9bea-e5419ad2f5fd', | |
346 | 'ext': 'mp4', | |
347 | 'title': 'Partiti acchiappavoti - Presa diretta del 13/09/2015', | |
348 | 'description': 'md5:d291b03407ec505f95f27970c0b025f4', | |
349 | 'upload_date': '20150913', | |
350 | 'subtitles': { | |
351 | 'it': 'count:2', | |
352 | }, | |
353 | }, | |
354 | 'params': { | |
355 | 'skip_download': True, | |
356 | }, | |
357 | }, { | |
358 | # Direct MMS URL | |
359 | 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html', | |
360 | 'only_matching': True, | |
361 | }, { | |
362 | 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html', | |
363 | 'only_matching': True, | |
364 | }] | |
365 | ||
366 | def _extract_from_content_id(self, content_id, url): | |
367 | media = self._download_json( | |
368 | 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id, | |
369 | content_id, 'Downloading video JSON') | |
370 | ||
371 | title = media['name'].strip() | |
372 | ||
373 | media_type = media['type'] | |
374 | if 'Audio' in media_type: | |
375 | relinker_info = { | |
376 | 'formats': [{ | |
377 | 'format_id': media.get('formatoAudio'), | |
378 | 'url': media['audioUrl'], | |
379 | 'ext': media.get('formatoAudio'), | |
380 | }] | |
381 | } | |
382 | elif 'Video' in media_type: | |
383 | relinker_info = self._extract_relinker_info(media['mediaUri'], content_id) | |
384 | else: | |
385 | raise ExtractorError('not a media file') | |
386 | ||
387 | self._sort_formats(relinker_info['formats']) | |
388 | ||
389 | thumbnails = [] | |
390 | for image_type in ('image', 'image_medium', 'image_300'): | |
391 | thumbnail_url = media.get(image_type) | |
392 | if thumbnail_url: | |
393 | thumbnails.append({ | |
394 | 'url': compat_urlparse.urljoin(url, thumbnail_url), | |
395 | }) | |
396 | ||
397 | subtitles = self._extract_subtitles(url, media) | |
398 | ||
399 | info = { | |
400 | 'id': content_id, | |
401 | 'title': title, | |
402 | 'description': strip_or_none(media.get('desc')), | |
403 | 'thumbnails': thumbnails, | |
404 | 'uploader': media.get('author'), | |
405 | 'upload_date': unified_strdate(media.get('date')), | |
406 | 'duration': parse_duration(media.get('length')), | |
407 | 'subtitles': subtitles, | |
408 | } | |
409 | ||
410 | info.update(relinker_info) | |
411 | ||
412 | return info | |
413 | ||
414 | def _real_extract(self, url): | |
415 | video_id = self._match_id(url) | |
416 | ||
417 | webpage = self._download_webpage(url, video_id) | |
418 | ||
419 | content_item_id = None | |
420 | ||
421 | content_item_url = self._html_search_meta( | |
422 | ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url', | |
423 | 'twitter:player', 'jsonlink'), webpage, default=None) | |
424 | if content_item_url: | |
425 | content_item_id = self._search_regex( | |
426 | r'ContentItem-(%s)' % self._UUID_RE, content_item_url, | |
427 | 'content item id', default=None) | |
428 | ||
429 | if not content_item_id: | |
430 | content_item_id = self._search_regex( | |
431 | r'''(?x) | |
432 | (?: | |
433 | (?:initEdizione|drawMediaRaiTV)\(| | |
434 | <(?:[^>]+\bdata-id|var\s+uniquename)=| | |
435 | <iframe[^>]+\bsrc= | |
436 | ) | |
437 | (["\']) | |
438 | (?:(?!\1).)*\bContentItem-(?P<id>%s) | |
439 | ''' % self._UUID_RE, | |
440 | webpage, 'content item id', default=None, group='id') | |
441 | ||
442 | content_item_ids = set() | |
443 | if content_item_id: | |
444 | content_item_ids.add(content_item_id) | |
445 | if video_id not in content_item_ids: | |
446 | content_item_ids.add(video_id) | |
447 | ||
448 | for content_item_id in content_item_ids: | |
449 | try: | |
450 | return self._extract_from_content_id(content_item_id, url) | |
451 | except GeoRestrictedError: | |
452 | raise | |
453 | except ExtractorError: | |
454 | pass | |
455 | ||
456 | relinker_url = self._proto_relative_url(self._search_regex( | |
457 | r'''(?x) | |
458 | (?: | |
459 | var\s+videoURL| | |
460 | mediaInfo\.mediaUri | |
461 | )\s*=\s* | |
462 | ([\'"]) | |
463 | (?P<url> | |
464 | (?:https?:)? | |
465 | //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\? | |
466 | (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1 | |
467 | ''', | |
468 | webpage, 'relinker URL', group='url')) | |
469 | ||
470 | relinker_info = self._extract_relinker_info( | |
471 | urljoin(url, relinker_url), video_id) | |
472 | self._sort_formats(relinker_info['formats']) | |
473 | ||
474 | title = self._search_regex( | |
475 | r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1', | |
476 | webpage, 'title', group='title', | |
477 | default=None) or self._og_search_title(webpage) | |
478 | ||
479 | info = { | |
480 | 'id': video_id, | |
481 | 'title': title, | |
482 | } | |
483 | ||
484 | info.update(relinker_info) | |
485 | ||
486 | return info |