1 from __future__ import unicode_literals
5 from .common import InfoExtractor
28 class RaiBaseIE(InfoExtractor):
29 _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
30 _GEO_COUNTRIES = ['IT']
33 def _extract_relinker_info(self, relinker_url, video_id):
39 for platform in ('mon', 'flash', 'native'):
40 relinker = self._download_xml(
41 relinker_url, video_id,
42 note='Downloading XML metadata for platform %s' % platform,
43 transform_source=fix_xml_ampersands,
44 query={'output': 45, 'pl': platform},
45 headers=self.geo_verification_headers())
48 geoprotection = xpath_text(
49 relinker, './geoprotection', default=None) == 'Y'
53 relinker, './is_live', default=None) == 'Y'
55 duration = parse_duration(xpath_text(
56 relinker, './duration', default=None))
58 url_elem = find_xpath_attr(relinker, './url', 'type', 'content')
62 media_url = url_elem.text
64 # This does not imply geo restriction (e.g.
65 # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
66 if media_url == 'http://download.rai.it/video_no_available.mp4':
69 ext = determine_ext(media_url)
70 if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
74 formats.extend(self._extract_m3u8_formats(
75 media_url, video_id, 'mp4', 'm3u8_native',
76 m3u8_id='hls', fatal=False))
78 manifest_url = update_url_query(
79 media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'),
80 {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'})
81 formats.extend(self._extract_f4m_formats(
82 manifest_url, video_id, f4m_id='hds', fatal=False))
84 bitrate = int_or_none(xpath_text(relinker, 'bitrate'))
87 'tbr': bitrate if bitrate > 0 else None,
88 'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
91 if not formats and geoprotection is True:
92 self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
94 return dict((k, v) for k, v in {
98 }.items() if v is not None)
101 def _extract_subtitles(url, subtitle_url):
103 if subtitle_url and isinstance(subtitle_url, compat_str):
104 subtitle_url = urljoin(url, subtitle_url)
111 if subtitle_url.endswith(STL_EXT):
112 srt_url = subtitle_url[:-len(STL_EXT)] + SRT_EXT
113 subtitles['it'].append({
120 class RaiPlayIE(RaiBaseIE):
121 _VALID_URL = r'(?P<url>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s)\.html)' % RaiBaseIE._UUID_RE
123 'url': 'http://www.raiplay.it/video/2016/10/La-Casa-Bianca-e06118bb-59a9-4636-b914-498e4cfd2c66.html?source=twitter',
124 'md5': '340aa3b7afb54bfd14a8c11786450d76',
126 'id': 'e06118bb-59a9-4636-b914-498e4cfd2c66',
128 'title': 'La Casa Bianca',
129 'alt_title': 'S2016 - Puntata del 23/10/2016',
130 'description': 'md5:a09d45890850458077d1f68bb036e0a5',
131 'thumbnail': r're:^https?://.*\.jpg$',
135 'timestamp': 1477764300,
136 'upload_date': '20161029',
137 'series': 'La Casa Bianca',
141 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
142 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
144 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
146 'title': 'Report del 07/04/2014',
147 'alt_title': 'S2013/14 - Puntata del 07/04/2014',
148 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
149 'thumbnail': r're:^https?://.*\.jpg$',
158 'skip_download': True,
161 'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
162 'only_matching': True,
165 def _real_extract(self, url):
166 mobj = re.match(self._VALID_URL, url)
167 url, video_id = mobj.group('url', 'id')
169 media = self._download_json(
170 '%s?json' % url, video_id, 'Downloading video JSON')
172 title = media['name']
174 video = media['video']
176 relinker_info = self._extract_relinker_info(video['contentUrl'], video_id)
177 self._sort_formats(relinker_info['formats'])
180 if 'images' in media:
181 for _, value in media.get('images').items():
184 'url': value.replace('[RESOLUTION]', '600x400')
187 timestamp = unified_timestamp(try_get(
188 media, lambda x: x['availabilities'][0]['start'], compat_str))
190 subtitles = self._extract_subtitles(url, video.get('subtitles'))
195 'alt_title': media.get('subtitle'),
196 'description': media.get('description'),
197 'uploader': media.get('channel'),
198 'creator': media.get('editor'),
199 'duration': parse_duration(video.get('duration')),
200 'timestamp': timestamp,
201 'thumbnails': thumbnails,
203 media, lambda x: x['isPartOf']['name'], compat_str),
204 'season_number': int_or_none(try_get(
205 media, lambda x: x['isPartOf']['numeroStagioni'])),
206 'season': media.get('stagione') or None,
207 'subtitles': subtitles,
210 info.update(relinker_info)
214 class RaiPlayLiveIE(RaiBaseIE):
215 _VALID_URL = r'https?://(?:www\.)?raiplay\.it/dirette/(?P<id>\w*)'
217 'url': 'http://www.raiplay.it/dirette/rai3',
218 'only_matching': True,
221 def _real_extract(self, url):
222 channel = self._match_id(url)
224 webpage = self._download_webpage(url, channel)
225 re_id = r'<div([^>]*)data-uniquename=(["\'])[\w-]*(?P<id>%s)(\2)([^>]*?)>' % RaiBaseIE._UUID_RE
226 video_id = self._html_search_regex(re_id, webpage, 'livestream-id', group='id')
228 return self.url_result('http://www.raiplay.it/dirette/ContentItem-%s.html' % video_id,
229 RaiPlayIE.ie_key(), video_id)
232 class RaiIE(RaiBaseIE):
233 _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
235 # var uniquename = "ContentItem-..."
236 # data-id="ContentItem-..."
237 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
239 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
241 'title': 'TG PRIMO TEMPO',
242 'thumbnail': r're:^https?://.*\.jpg$',
244 'upload_date': '20140612',
247 # with ContentItem in many metas
248 'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
250 'id': '1632c009-c843-4836-bb65-80c33084a64b',
252 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
253 'description': 'I film in uscita questa settimana.',
254 'thumbnail': r're:^https?://.*\.png$',
256 'upload_date': '20161103',
259 # with ContentItem in og:url
260 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
261 'md5': '11959b4e44fa74de47011b5799490adf',
263 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
265 'title': 'TG1 ore 20:00 del 03/11/2016',
266 'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
267 'thumbnail': r're:^https?://.*\.jpg$',
269 'upload_date': '20161103',
272 # drawMediaRaiTV(...)
273 'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
274 'md5': '2dd727e61114e1ee9c47f0da6914e178',
276 'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
279 'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
280 'thumbnail': r're:^https?://.*\.jpg$',
281 'upload_date': '20141221',
284 # initEdizione('ContentItem-...'
285 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
287 'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
289 'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
291 'upload_date': '20170401',
293 'skip': 'Changes daily',
295 # HDS live stream with only relinker URL
296 'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
298 'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
303 'skip_download': True,
306 # HLS live stream with ContentItem in og:url
307 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
309 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
311 'title': 'La diretta di Rainews24',
314 'skip_download': True,
318 def _extract_from_content_id(self, content_id, url):
319 media = self._download_json(
320 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id,
321 content_id, 'Downloading video JSON')
323 title = media['name'].strip()
325 media_type = media['type']
326 if 'Audio' in media_type:
329 'format_id': media.get('formatoAudio'),
330 'url': media['audioUrl'],
331 'ext': media.get('formatoAudio'),
334 elif 'Video' in media_type:
335 relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)
337 raise ExtractorError('not a media file')
339 self._sort_formats(relinker_info['formats'])
342 for image_type in ('image', 'image_medium', 'image_300'):
343 thumbnail_url = media.get(image_type)
346 'url': compat_urlparse.urljoin(url, thumbnail_url),
349 subtitles = self._extract_subtitles(url, media.get('subtitlesUrl'))
354 'description': strip_or_none(media.get('desc')),
355 'thumbnails': thumbnails,
356 'uploader': media.get('author'),
357 'upload_date': unified_strdate(media.get('date')),
358 'duration': parse_duration(media.get('length')),
359 'subtitles': subtitles,
362 info.update(relinker_info)
366 def _real_extract(self, url):
367 video_id = self._match_id(url)
369 webpage = self._download_webpage(url, video_id)
371 content_item_id = None
373 content_item_url = self._html_search_meta(
374 ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
375 'twitter:player', 'jsonlink'), webpage, default=None)
377 content_item_id = self._search_regex(
378 r'ContentItem-(%s)' % self._UUID_RE, content_item_url,
379 'content item id', default=None)
381 if not content_item_id:
382 content_item_id = self._search_regex(
385 (?:initEdizione|drawMediaRaiTV)\(|
386 <(?:[^>]+\bdata-id|var\s+uniquename)=
389 (?:(?!\1).)*\bContentItem-(?P<id>%s)
391 webpage, 'content item id', default=None, group='id')
393 content_item_ids = set()
395 content_item_ids.add(content_item_id)
396 if video_id not in content_item_ids:
397 content_item_ids.add(video_id)
399 for content_item_id in content_item_ids:
401 return self._extract_from_content_id(content_item_id, url)
402 except GeoRestrictedError:
404 except ExtractorError:
407 relinker_url = self._search_regex(
416 //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
417 (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
419 webpage, 'relinker URL', group='url')
421 relinker_info = self._extract_relinker_info(
422 urljoin(url, relinker_url), video_id)
423 self._sort_formats(relinker_info['formats'])
425 title = self._search_regex(
426 r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1',
427 webpage, 'title', group='title',
428 default=None) or self._og_search_title(webpage)
435 info.update(relinker_info)