rai.py (18246B)
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'] 170 171 video = media['video'] 172 173 relinker_info = self._extract_relinker_info(video['content_url'], video_id) 174 self._sort_formats(relinker_info['formats']) 175 176 thumbnails = [] 177 for _, value in media.get('images', {}).items(): 178 if value: 179 thumbnails.append({ 180 'url': urljoin(url, value), 181 }) 182 183 date_published = media.get('date_published') 184 time_published = media.get('time_published') 185 if date_published and time_published: 186 date_published += ' ' + time_published 187 188 subtitles = self._extract_subtitles(url, video) 189 190 program_info = media.get('program_info') or {} 191 season = media.get('season') 192 193 info = { 194 'id': remove_start(media.get('id'), 'ContentItem-') or video_id, 195 'display_id': video_id, 196 'title': self._live_title(title) if relinker_info.get( 197 'is_live') else title, 198 'alt_title': strip_or_none(media.get('subtitle')), 199 'description': media.get('description'), 200 'uploader': strip_or_none(media.get('channel')), 201 'creator': strip_or_none(media.get('editor') or None), 202 'duration': parse_duration(video.get('duration')), 203 'timestamp': unified_timestamp(date_published), 204 'thumbnails': thumbnails, 205 'series': program_info.get('name'), 206 'season_number': int_or_none(season), 207 'season': season if (season and not season.isdigit()) else None, 208 'episode': media.get('episode_title'), 209 'episode_number': int_or_none(media.get('episode')), 210 'subtitles': subtitles, 211 } 212 213 info.update(relinker_info) 214 return info 215 216 217 class RaiPlayLiveIE(RaiPlayIE): 218 _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))' 219 _TESTS = [{ 220 'url': 'http://www.raiplay.it/dirette/rainews24', 221 'info_dict': { 222 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c', 223 'display_id': 'rainews24', 224 'ext': 'mp4', 225 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 226 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497', 227 'uploader': 'Rai News 24', 228 'creator': 'Rai News 24', 229 'is_live': True, 230 }, 231 'params': { 232 'skip_download': True, 233 }, 234 }] 235 236 237 class RaiPlayPlaylistIE(InfoExtractor): 238 _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))' 239 _TESTS = [{ 240 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', 241 'info_dict': { 242 'id': 'nondirloalmiocapo', 243 'title': 'Non dirlo al mio capo', 244 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b', 245 }, 246 'playlist_mincount': 12, 247 }] 248 249 def _real_extract(self, url): 250 base, playlist_id = re.match(self._VALID_URL, url).groups() 251 252 program = self._download_json( 253 base + '.json', playlist_id, 'Downloading program JSON') 254 255 entries = [] 256 for b in (program.get('blocks') or []): 257 for s in (b.get('sets') or []): 258 s_id = s.get('id') 259 if not s_id: 260 continue 261 medias = self._download_json( 262 '%s/%s.json' % (base, s_id), s_id, 263 'Downloading content set JSON', fatal=False) 264 if not medias: 265 continue 266 for m in (medias.get('items') or []): 267 path_id = m.get('path_id') 268 if not path_id: 269 continue 270 video_url = urljoin(url, path_id) 271 entries.append(self.url_result( 272 video_url, ie=RaiPlayIE.ie_key(), 273 video_id=RaiPlayIE._match_id(video_url))) 274 275 return self.playlist_result( 276 entries, playlist_id, program.get('name'), 277 try_get(program, lambda x: x['program_info']['description'])) 278 279 280 class RaiIE(RaiBaseIE): 281 _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE 282 _TESTS = [{ 283 # var uniquename = "ContentItem-..." 284 # data-id="ContentItem-..." 285 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html', 286 'info_dict': { 287 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9', 288 'ext': 'mp4', 289 'title': 'TG PRIMO TEMPO', 290 'thumbnail': r're:^https?://.*\.jpg$', 291 'duration': 1758, 292 'upload_date': '20140612', 293 }, 294 'skip': 'This content is available only in Italy', 295 }, { 296 # with ContentItem in many metas 297 'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html', 298 'info_dict': { 299 'id': '1632c009-c843-4836-bb65-80c33084a64b', 300 'ext': 'mp4', 301 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"', 302 'description': 'I film in uscita questa settimana.', 303 'thumbnail': r're:^https?://.*\.png$', 304 'duration': 833, 305 'upload_date': '20161103', 306 } 307 }, { 308 # with ContentItem in og:url 309 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html', 310 'md5': '6865dd00cf0bbf5772fdd89d59bd768a', 311 'info_dict': { 312 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c', 313 'ext': 'mp4', 314 'title': 'TG1 ore 20:00 del 03/11/2016', 315 'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016', 316 'thumbnail': r're:^https?://.*\.jpg$', 317 'duration': 2214, 318 'upload_date': '20161103', 319 } 320 }, { 321 # initEdizione('ContentItem-...' 322 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined', 323 'info_dict': { 324 'id': 'c2187016-8484-4e3a-8ac8-35e475b07303', 325 'ext': 'mp4', 326 'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}', 327 'duration': 2274, 328 'upload_date': '20170401', 329 }, 330 'skip': 'Changes daily', 331 }, { 332 # HLS live stream with ContentItem in og:url 333 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html', 334 'info_dict': { 335 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9', 336 'ext': 'mp4', 337 'title': 'La diretta di Rainews24', 338 }, 339 'params': { 340 'skip_download': True, 341 }, 342 }, { 343 # ContentItem in iframe (see #12652) and subtitle at 'subtitlesUrl' key 344 'url': 'http://www.presadiretta.rai.it/dl/portali/site/puntata/ContentItem-3ed19d13-26c2-46ff-a551-b10828262f1b.html', 345 'info_dict': { 346 'id': '1ad6dc64-444a-42a4-9bea-e5419ad2f5fd', 347 'ext': 'mp4', 348 'title': 'Partiti acchiappavoti - Presa diretta del 13/09/2015', 349 'description': 'md5:d291b03407ec505f95f27970c0b025f4', 350 'upload_date': '20150913', 351 'subtitles': { 352 'it': 'count:2', 353 }, 354 }, 355 'params': { 356 'skip_download': True, 357 }, 358 }, { 359 # Direct MMS URL 360 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html', 361 'only_matching': True, 362 }, { 363 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html', 364 'only_matching': True, 365 }] 366 367 def _extract_from_content_id(self, content_id, url): 368 media = self._download_json( 369 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id, 370 content_id, 'Downloading video JSON') 371 372 title = media['name'].strip() 373 374 media_type = media['type'] 375 if 'Audio' in media_type: 376 relinker_info = { 377 'formats': [{ 378 'format_id': media.get('formatoAudio'), 379 'url': media['audioUrl'], 380 'ext': media.get('formatoAudio'), 381 }] 382 } 383 elif 'Video' in media_type: 384 relinker_info = self._extract_relinker_info(media['mediaUri'], content_id) 385 else: 386 raise ExtractorError('not a media file') 387 388 self._sort_formats(relinker_info['formats']) 389 390 thumbnails = [] 391 for image_type in ('image', 'image_medium', 'image_300'): 392 thumbnail_url = media.get(image_type) 393 if thumbnail_url: 394 thumbnails.append({ 395 'url': compat_urlparse.urljoin(url, thumbnail_url), 396 }) 397 398 subtitles = self._extract_subtitles(url, media) 399 400 info = { 401 'id': content_id, 402 'title': title, 403 'description': strip_or_none(media.get('desc')), 404 'thumbnails': thumbnails, 405 'uploader': media.get('author'), 406 'upload_date': unified_strdate(media.get('date')), 407 'duration': parse_duration(media.get('length')), 408 'subtitles': subtitles, 409 } 410 411 info.update(relinker_info) 412 413 return info 414 415 def _real_extract(self, url): 416 video_id = self._match_id(url) 417 418 webpage = self._download_webpage(url, video_id) 419 420 content_item_id = None 421 422 content_item_url = self._html_search_meta( 423 ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url', 424 'twitter:player', 'jsonlink'), webpage, default=None) 425 if content_item_url: 426 content_item_id = self._search_regex( 427 r'ContentItem-(%s)' % self._UUID_RE, content_item_url, 428 'content item id', default=None) 429 430 if not content_item_id: 431 content_item_id = self._search_regex( 432 r'''(?x) 433 (?: 434 (?:initEdizione|drawMediaRaiTV)\(| 435 <(?:[^>]+\bdata-id|var\s+uniquename)=| 436 <iframe[^>]+\bsrc= 437 ) 438 (["\']) 439 (?:(?!\1).)*\bContentItem-(?P<id>%s) 440 ''' % self._UUID_RE, 441 webpage, 'content item id', default=None, group='id') 442 443 content_item_ids = set() 444 if content_item_id: 445 content_item_ids.add(content_item_id) 446 if video_id not in content_item_ids: 447 content_item_ids.add(video_id) 448 449 for content_item_id in content_item_ids: 450 try: 451 return self._extract_from_content_id(content_item_id, url) 452 except GeoRestrictedError: 453 raise 454 except ExtractorError: 455 pass 456 457 relinker_url = self._proto_relative_url(self._search_regex( 458 r'''(?x) 459 (?: 460 var\s+videoURL| 461 mediaInfo\.mediaUri 462 )\s*=\s* 463 ([\'"]) 464 (?P<url> 465 (?:https?:)? 466 //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\? 467 (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1 468 ''', 469 webpage, 'relinker URL', group='url')) 470 471 relinker_info = self._extract_relinker_info( 472 urljoin(url, relinker_url), video_id) 473 self._sort_formats(relinker_info['formats']) 474 475 title = self._search_regex( 476 r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1', 477 webpage, 'title', group='title', 478 default=None) or self._og_search_title(webpage) 479 480 info = { 481 'id': video_id, 482 'title': title, 483 } 484 485 info.update(relinker_info) 486 487 return info