2 from __future__ import unicode_literals
6 from .common import InfoExtractor
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']
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}]}
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())
53 geoprotection = xpath_text(
54 relinker, './geoprotection', default=None) == 'Y'
58 relinker, './is_live', default=None) == 'Y'
60 duration = parse_duration(xpath_text(
61 relinker, './duration', default=None))
63 url_elem = find_xpath_attr(relinker, './url', 'type', 'content')
67 media_url = url_elem.text
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:
74 ext = determine_ext(media_url)
75 if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
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))
89 bitrate = int_or_none(xpath_text(relinker, 'bitrate'))
92 'tbr': bitrate if bitrate > 0 else None,
93 'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
96 if not formats and geoprotection is True:
97 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
99 return dict((k, v) for k, v in {
101 'duration': duration,
103 }.items() if v is not None)
106 def _extract_subtitles(url, video_data):
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({
123 if STL_EXT == sub_ext:
124 subtitles[sub_lang].append({
126 'url': sub_url[:-len(STL_EXT)] + SRT_EXT,
131 class RaiPlayIE(RaiBaseIE):
132 _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE
134 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
135 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
137 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
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',
152 'skip_download': True,
155 'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
156 'only_matching': True,
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,
163 def _real_extract(self, url):
164 base, video_id = re.match(self._VALID_URL, url).groups()
166 media = self._download_json(
167 base + '.json', video_id, 'Downloading video JSON')
169 title = media['name']
171 video = media['video']
173 relinker_info = self._extract_relinker_info(video['content_url'], video_id)
174 self._sort_formats(relinker_info['formats'])
177 for _, value in media.get('images', {}).items():
180 'url': urljoin(url, value),
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
188 subtitles = self._extract_subtitles(url, video)
190 program_info = media.get('program_info') or {}
191 season = media.get('season')
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,
213 info.update(relinker_info)
217 class RaiPlayLiveIE(RaiPlayIE):
218 _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
220 'url': 'http://www.raiplay.it/dirette/rainews24',
222 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
223 'display_id': 'rainews24',
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',
232 'skip_download': True,
237 class RaiPlayPlaylistIE(InfoExtractor):
238 _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
240 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
242 'id': 'nondirloalmiocapo',
243 'title': 'Non dirlo al mio capo',
244 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
246 'playlist_mincount': 12,
249 def _real_extract(self, url):
250 base, playlist_id = re.match(self._VALID_URL, url).groups()
252 program = self._download_json(
253 base + '.json', playlist_id, 'Downloading program JSON')
256 for b in (program.get('blocks') or []):
257 for s in (b.get('sets') or []):
261 medias = self._download_json(
262 '%s/%s.json' % (base, s_id), s_id,
263 'Downloading content set JSON', fatal=False)
266 for m in (medias.get('items') or []):
267 path_id = m.get('path_id')
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)))
275 return self.playlist_result(
276 entries, playlist_id, program.get('name'),
277 try_get(program, lambda x: x['program_info']['description']))
280 class RaiIE(RaiBaseIE):
281 _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
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',
287 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
289 'title': 'TG PRIMO TEMPO',
290 'thumbnail': r're:^https?://.*\.jpg$',
292 'upload_date': '20140612',
294 'skip': 'This content is available only in Italy',
296 # with ContentItem in many metas
297 'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
299 'id': '1632c009-c843-4836-bb65-80c33084a64b',
301 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
302 'description': 'I film in uscita questa settimana.',
303 'thumbnail': r're:^https?://.*\.png$',
305 'upload_date': '20161103',
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',
312 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
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$',
318 'upload_date': '20161103',
321 # initEdizione('ContentItem-...'
322 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
324 'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
326 'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
328 'upload_date': '20170401',
330 'skip': 'Changes daily',
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',
335 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
337 'title': 'La diretta di Rainews24',
340 'skip_download': True,
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',
346 'id': '1ad6dc64-444a-42a4-9bea-e5419ad2f5fd',
348 'title': 'Partiti acchiappavoti - Presa diretta del 13/09/2015',
349 'description': 'md5:d291b03407ec505f95f27970c0b025f4',
350 'upload_date': '20150913',
356 'skip_download': True,
360 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
361 'only_matching': True,
363 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html',
364 'only_matching': True,
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')
372 title = media['name'].strip()
374 media_type = media['type']
375 if 'Audio' in media_type:
378 'format_id': media.get('formatoAudio'),
379 'url': media['audioUrl'],
380 'ext': media.get('formatoAudio'),
383 elif 'Video' in media_type:
384 relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)
386 raise ExtractorError('not a media file')
388 self._sort_formats(relinker_info['formats'])
391 for image_type in ('image', 'image_medium', 'image_300'):
392 thumbnail_url = media.get(image_type)
395 'url': compat_urlparse.urljoin(url, thumbnail_url),
398 subtitles = self._extract_subtitles(url, media)
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,
411 info.update(relinker_info)
415 def _real_extract(self, url):
416 video_id = self._match_id(url)
418 webpage = self._download_webpage(url, video_id)
420 content_item_id = None
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)
426 content_item_id = self._search_regex(
427 r'ContentItem-(%s)' % self._UUID_RE, content_item_url,
428 'content item id', default=None)
430 if not content_item_id:
431 content_item_id = self._search_regex(
434 (?:initEdizione|drawMediaRaiTV)\(|
435 <(?:[^>]+\bdata-id|var\s+uniquename)=|
439 (?:(?!\1).)*\bContentItem-(?P<id>%s)
441 webpage, 'content item id', default=None, group='id')
443 content_item_ids = set()
445 content_item_ids.add(content_item_id)
446 if video_id not in content_item_ids:
447 content_item_ids.add(video_id)
449 for content_item_id in content_item_ids:
451 return self._extract_from_content_id(content_item_id, url)
452 except GeoRestrictedError:
454 except ExtractorError:
457 relinker_url = self._proto_relative_url(self._search_regex(
466 //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
467 (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
469 webpage, 'relinker URL', group='url'))
471 relinker_info = self._extract_relinker_info(
472 urljoin(url, relinker_url), video_id)
473 self._sort_formats(relinker_info['formats'])
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)
485 info.update(relinker_info)