]>
Commit | Line | Data |
---|---|---|
abea9145 | 1 | # coding: utf-8 |
b0adbe98 S |
2 | from __future__ import unicode_literals |
3 | ||
b8d8cced S |
4 | import re |
5 | ||
afbdd3ac | 6 | from .common import InfoExtractor |
b8d8cced S |
7 | from ..compat import ( |
8 | compat_urlparse, | |
9 | compat_str, | |
10 | ) | |
b0adbe98 | 11 | from ..utils import ( |
f1388739 | 12 | ExtractorError, |
51342717 | 13 | determine_ext, |
f1388739 YCH |
14 | find_xpath_attr, |
15 | fix_xml_ampersands, | |
b8d8cced | 16 | GeoRestrictedError, |
f1388739 | 17 | int_or_none, |
b0adbe98 | 18 | parse_duration, |
a0566bbf | 19 | remove_start, |
b8d8cced | 20 | strip_or_none, |
a0566bbf | 21 | try_get, |
b0adbe98 | 22 | unified_strdate, |
b8d8cced | 23 | unified_timestamp, |
f1388739 | 24 | update_url_query, |
b8d8cced | 25 | urljoin, |
06d5556d | 26 | xpath_text, |
b0adbe98 S |
27 | ) |
28 | ||
29 | ||
034a8849 | 30 | class RaiBaseIE(InfoExtractor): |
b8d8cced S |
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): | |
0c7b4f49 RA |
36 | if not re.match(r'https?://', relinker_url): |
37 | return {'formats': [{'url': relinker_url}]} | |
38 | ||
034a8849 | 39 | formats = [] |
b8d8cced S |
40 | geoprotection = None |
41 | is_live = None | |
42 | duration = None | |
034a8849 YCH |
43 | |
44 | for platform in ('mon', 'flash', 'native'): | |
034a8849 YCH |
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, | |
38cce791 YCH |
49 | query={'output': 45, 'pl': platform}, |
50 | headers=self.geo_verification_headers()) | |
034a8849 | 51 | |
b8d8cced S |
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) | |
a0566bbf | 71 | if '/video_no_available.mp4' in media_url: |
b8d8cced | 72 | continue |
034a8849 YCH |
73 | |
74 | ext = determine_ext(media_url) | |
75 | if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'): | |
76 | continue | |
77 | ||
c17eb5b4 | 78 | if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon': |
034a8849 YCH |
79 | formats.extend(self._extract_m3u8_formats( |
80 | media_url, video_id, 'mp4', 'm3u8_native', | |
81 | m3u8_id='hls', fatal=False)) | |
c17eb5b4 | 82 | elif ext == 'f4m' or platform == 'flash': |
034a8849 YCH |
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 | ||
b8d8cced | 96 | if not formats and geoprotection is True: |
b7da73eb | 97 | self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True) |
b8d8cced S |
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) | |
034a8849 | 104 | |
1b3feca0 | 105 | @staticmethod |
00dd0cd5 | 106 | def _extract_subtitles(url, video_data): |
107 | STL_EXT = 'stl' | |
108 | SRT_EXT = 'srt' | |
1b3feca0 | 109 | subtitles = {} |
00dd0cd5 | 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, | |
1b3feca0 | 122 | }) |
00dd0cd5 | 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 | }) | |
1b3feca0 S |
128 | return subtitles |
129 | ||
2b28b892 | 130 | |
51342717 | 131 | class RaiPlayIE(RaiBaseIE): |
a0566bbf | 132 | _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE |
51342717 | 133 | _TESTS = [{ |
51342717 T |
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', | |
b8d8cced | 139 | 'title': 'Report del 07/04/2014', |
8bdd16b4 | 140 | 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014', |
abea9145 | 141 | 'description': 'md5:d730c168a58f4bb35600fc2f881ec04e', |
51342717 | 142 | 'thumbnail': r're:^https?://.*\.jpg$', |
abea9145 | 143 | 'uploader': 'Rai Gulp', |
b8d8cced | 144 | 'duration': 6160, |
8bdd16b4 | 145 | 'series': 'Report', |
146 | 'season': '2013/14', | |
00dd0cd5 | 147 | 'subtitles': { |
148 | 'it': 'count:2', | |
149 | }, | |
b8d8cced S |
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, | |
00dd0cd5 | 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, | |
0852947f | 161 | }, { |
162 | # DRM protected | |
163 | 'url': 'https://www.raiplay.it/video/2020/09/Lo-straordinario-mondo-di-Zoey-S1E1-Lo-straordinario-potere-di-Zoey-ed493918-1d32-44b7-8454-862e473d00ff.html', | |
164 | 'only_matching': True, | |
51342717 | 165 | }] |
2b28b892 | 166 | |
51342717 | 167 | def _real_extract(self, url): |
a0566bbf | 168 | base, video_id = re.match(self._VALID_URL, url).groups() |
2b28b892 | 169 | |
b8d8cced | 170 | media = self._download_json( |
a0566bbf | 171 | base + '.json', video_id, 'Downloading video JSON') |
2b28b892 | 172 | |
8eec0120 | 173 | if not self._downloader.params.get('allow_unplayable_formats'): |
0852947f | 174 | if try_get( |
175 | media, | |
176 | (lambda x: x['rights_management']['rights']['drm'], | |
177 | lambda x: x['program_info']['rights_management']['rights']['drm']), | |
178 | dict): | |
179 | raise ExtractorError('This video is DRM protected.', expected=True) | |
180 | ||
b8d8cced | 181 | title = media['name'] |
b8d8cced S |
182 | video = media['video'] |
183 | ||
abea9145 | 184 | relinker_info = self._extract_relinker_info(video['content_url'], video_id) |
b8d8cced | 185 | self._sort_formats(relinker_info['formats']) |
2b28b892 | 186 | |
51342717 | 187 | thumbnails = [] |
8bdd16b4 | 188 | for _, value in media.get('images', {}).items(): |
189 | if value: | |
190 | thumbnails.append({ | |
191 | 'url': urljoin(url, value), | |
192 | }) | |
034a8849 | 193 | |
8bdd16b4 | 194 | date_published = media.get('date_published') |
195 | time_published = media.get('time_published') | |
196 | if date_published and time_published: | |
197 | date_published += ' ' + time_published | |
b0adbe98 | 198 | |
00dd0cd5 | 199 | subtitles = self._extract_subtitles(url, video) |
1b3feca0 | 200 | |
8bdd16b4 | 201 | program_info = media.get('program_info') or {} |
202 | season = media.get('season') | |
203 | ||
b8d8cced | 204 | info = { |
a0566bbf | 205 | 'id': remove_start(media.get('id'), 'ContentItem-') or video_id, |
206 | 'display_id': video_id, | |
9c48b5a1 S |
207 | 'title': self._live_title(title) if relinker_info.get( |
208 | 'is_live') else title, | |
8bdd16b4 | 209 | 'alt_title': strip_or_none(media.get('subtitle')), |
b8d8cced | 210 | 'description': media.get('description'), |
9c48b5a1 | 211 | 'uploader': strip_or_none(media.get('channel')), |
8bdd16b4 | 212 | 'creator': strip_or_none(media.get('editor') or None), |
b8d8cced | 213 | 'duration': parse_duration(video.get('duration')), |
8bdd16b4 | 214 | 'timestamp': unified_timestamp(date_published), |
51342717 | 215 | 'thumbnails': thumbnails, |
8bdd16b4 | 216 | 'series': program_info.get('name'), |
217 | 'season_number': int_or_none(season), | |
218 | 'season': season if (season and not season.isdigit()) else None, | |
219 | 'episode': media.get('episode_title'), | |
220 | 'episode_number': int_or_none(media.get('episode')), | |
1b3feca0 | 221 | 'subtitles': subtitles, |
51342717 | 222 | } |
b0adbe98 | 223 | |
b8d8cced | 224 | info.update(relinker_info) |
b8d8cced S |
225 | return info |
226 | ||
06d5556d | 227 | |
a0566bbf | 228 | class RaiPlayLiveIE(RaiPlayIE): |
229 | _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))' | |
230 | _TESTS = [{ | |
9c48b5a1 S |
231 | 'url': 'http://www.raiplay.it/dirette/rainews24', |
232 | 'info_dict': { | |
233 | 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c', | |
234 | 'display_id': 'rainews24', | |
235 | 'ext': 'mp4', | |
236 | 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', | |
a0566bbf | 237 | 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497', |
9c48b5a1 S |
238 | 'uploader': 'Rai News 24', |
239 | 'creator': 'Rai News 24', | |
240 | 'is_live': True, | |
241 | }, | |
242 | 'params': { | |
243 | 'skip_download': True, | |
244 | }, | |
a0566bbf | 245 | }] |
449c6657 | 246 | |
247 | ||
1115271a | 248 | class RaiPlayPlaylistIE(InfoExtractor): |
a0566bbf | 249 | _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))' |
1115271a S |
250 | _TESTS = [{ |
251 | 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', | |
252 | 'info_dict': { | |
253 | 'id': 'nondirloalmiocapo', | |
254 | 'title': 'Non dirlo al mio capo', | |
a0566bbf | 255 | 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b', |
1115271a S |
256 | }, |
257 | 'playlist_mincount': 12, | |
258 | }] | |
259 | ||
260 | def _real_extract(self, url): | |
a0566bbf | 261 | base, playlist_id = re.match(self._VALID_URL, url).groups() |
1115271a | 262 | |
a0566bbf | 263 | program = self._download_json( |
264 | base + '.json', playlist_id, 'Downloading program JSON') | |
1115271a S |
265 | |
266 | entries = [] | |
a0566bbf | 267 | for b in (program.get('blocks') or []): |
268 | for s in (b.get('sets') or []): | |
269 | s_id = s.get('id') | |
270 | if not s_id: | |
271 | continue | |
272 | medias = self._download_json( | |
273 | '%s/%s.json' % (base, s_id), s_id, | |
274 | 'Downloading content set JSON', fatal=False) | |
275 | if not medias: | |
276 | continue | |
277 | for m in (medias.get('items') or []): | |
278 | path_id = m.get('path_id') | |
279 | if not path_id: | |
280 | continue | |
281 | video_url = urljoin(url, path_id) | |
282 | entries.append(self.url_result( | |
283 | video_url, ie=RaiPlayIE.ie_key(), | |
284 | video_id=RaiPlayIE._match_id(video_url))) | |
285 | ||
286 | return self.playlist_result( | |
287 | entries, playlist_id, program.get('name'), | |
288 | try_get(program, lambda x: x['program_info']['description'])) | |
1115271a S |
289 | |
290 | ||
034a8849 | 291 | class RaiIE(RaiBaseIE): |
2b2da3ba | 292 | _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE |
51342717 | 293 | _TESTS = [{ |
b8d8cced S |
294 | # var uniquename = "ContentItem-..." |
295 | # data-id="ContentItem-..." | |
51342717 T |
296 | 'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html', |
297 | 'info_dict': { | |
298 | 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9', | |
299 | 'ext': 'mp4', | |
300 | 'title': 'TG PRIMO TEMPO', | |
b8d8cced | 301 | 'thumbnail': r're:^https?://.*\.jpg$', |
51342717 | 302 | 'duration': 1758, |
b8d8cced | 303 | 'upload_date': '20140612', |
8bdd16b4 | 304 | }, |
305 | 'skip': 'This content is available only in Italy', | |
51342717 | 306 | }, { |
b8d8cced | 307 | # with ContentItem in many metas |
51342717 T |
308 | 'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html', |
309 | 'info_dict': { | |
310 | 'id': '1632c009-c843-4836-bb65-80c33084a64b', | |
311 | 'ext': 'mp4', | |
b8d8cced S |
312 | 'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"', |
313 | 'description': 'I film in uscita questa settimana.', | |
51342717 | 314 | 'thumbnail': r're:^https?://.*\.png$', |
b8d8cced S |
315 | 'duration': 833, |
316 | 'upload_date': '20161103', | |
51342717 T |
317 | } |
318 | }, { | |
b8d8cced | 319 | # with ContentItem in og:url |
51342717 | 320 | 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html', |
abea9145 | 321 | 'md5': '6865dd00cf0bbf5772fdd89d59bd768a', |
51342717 T |
322 | 'info_dict': { |
323 | 'id': 'efb17665-691c-45d5-a60c-5301333cbb0c', | |
324 | 'ext': 'mp4', | |
325 | 'title': 'TG1 ore 20:00 del 03/11/2016', | |
b8d8cced | 326 | 'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016', |
51342717 | 327 | 'thumbnail': r're:^https?://.*\.jpg$', |
b8d8cced | 328 | 'duration': 2214, |
51342717 | 329 | 'upload_date': '20161103', |
51342717 | 330 | } |
51342717 | 331 | }, { |
b8d8cced S |
332 | # initEdizione('ContentItem-...' |
333 | 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined', | |
334 | 'info_dict': { | |
335 | 'id': 'c2187016-8484-4e3a-8ac8-35e475b07303', | |
336 | 'ext': 'mp4', | |
337 | 'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}', | |
338 | 'duration': 2274, | |
339 | 'upload_date': '20170401', | |
340 | }, | |
341 | 'skip': 'Changes daily', | |
51342717 | 342 | }, { |
b8d8cced | 343 | # HLS live stream with ContentItem in og:url |
51342717 | 344 | 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html', |
51342717 T |
345 | 'info_dict': { |
346 | 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9', | |
347 | 'ext': 'mp4', | |
348 | 'title': 'La diretta di Rainews24', | |
15e4b6b7 | 349 | }, |
b8d8cced S |
350 | 'params': { |
351 | 'skip_download': True, | |
352 | }, | |
00dd0cd5 | 353 | }, { |
354 | # ContentItem in iframe (see #12652) and subtitle at 'subtitlesUrl' key | |
355 | 'url': 'http://www.presadiretta.rai.it/dl/portali/site/puntata/ContentItem-3ed19d13-26c2-46ff-a551-b10828262f1b.html', | |
356 | 'info_dict': { | |
357 | 'id': '1ad6dc64-444a-42a4-9bea-e5419ad2f5fd', | |
358 | 'ext': 'mp4', | |
359 | 'title': 'Partiti acchiappavoti - Presa diretta del 13/09/2015', | |
360 | 'description': 'md5:d291b03407ec505f95f27970c0b025f4', | |
361 | 'upload_date': '20150913', | |
362 | 'subtitles': { | |
363 | 'it': 'count:2', | |
364 | }, | |
365 | }, | |
366 | 'params': { | |
367 | 'skip_download': True, | |
368 | }, | |
0c7b4f49 RA |
369 | }, { |
370 | # Direct MMS URL | |
371 | 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html', | |
372 | 'only_matching': True, | |
2b2da3ba S |
373 | }, { |
374 | 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html', | |
375 | 'only_matching': True, | |
51342717 | 376 | }] |
06d5556d | 377 | |
51342717 T |
378 | def _extract_from_content_id(self, content_id, url): |
379 | media = self._download_json( | |
380 | 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id, | |
381 | content_id, 'Downloading video JSON') | |
382 | ||
b8d8cced S |
383 | title = media['name'].strip() |
384 | ||
385 | media_type = media['type'] | |
386 | if 'Audio' in media_type: | |
387 | relinker_info = { | |
085d9dd9 | 388 | 'formats': [{ |
b8d8cced S |
389 | 'format_id': media.get('formatoAudio'), |
390 | 'url': media['audioUrl'], | |
391 | 'ext': media.get('formatoAudio'), | |
085d9dd9 | 392 | }] |
b8d8cced S |
393 | } |
394 | elif 'Video' in media_type: | |
395 | relinker_info = self._extract_relinker_info(media['mediaUri'], content_id) | |
396 | else: | |
397 | raise ExtractorError('not a media file') | |
398 | ||
399 | self._sort_formats(relinker_info['formats']) | |
400 | ||
51342717 T |
401 | thumbnails = [] |
402 | for image_type in ('image', 'image_medium', 'image_300'): | |
403 | thumbnail_url = media.get(image_type) | |
404 | if thumbnail_url: | |
405 | thumbnails.append({ | |
406 | 'url': compat_urlparse.urljoin(url, thumbnail_url), | |
407 | }) | |
408 | ||
00dd0cd5 | 409 | subtitles = self._extract_subtitles(url, media) |
51342717 | 410 | |
b8d8cced | 411 | info = { |
51342717 | 412 | 'id': content_id, |
b8d8cced S |
413 | 'title': title, |
414 | 'description': strip_or_none(media.get('desc')), | |
51342717 T |
415 | 'thumbnails': thumbnails, |
416 | 'uploader': media.get('author'), | |
417 | 'upload_date': unified_strdate(media.get('date')), | |
418 | 'duration': parse_duration(media.get('length')), | |
51342717 T |
419 | 'subtitles': subtitles, |
420 | } | |
b8d8cced S |
421 | |
422 | info.update(relinker_info) | |
423 | ||
424 | return info | |
425 | ||
426 | def _real_extract(self, url): | |
427 | video_id = self._match_id(url) | |
428 | ||
429 | webpage = self._download_webpage(url, video_id) | |
430 | ||
431 | content_item_id = None | |
432 | ||
433 | content_item_url = self._html_search_meta( | |
434 | ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url', | |
435 | 'twitter:player', 'jsonlink'), webpage, default=None) | |
436 | if content_item_url: | |
437 | content_item_id = self._search_regex( | |
438 | r'ContentItem-(%s)' % self._UUID_RE, content_item_url, | |
439 | 'content item id', default=None) | |
440 | ||
441 | if not content_item_id: | |
442 | content_item_id = self._search_regex( | |
443 | r'''(?x) | |
444 | (?: | |
445 | (?:initEdizione|drawMediaRaiTV)\(| | |
00dd0cd5 | 446 | <(?:[^>]+\bdata-id|var\s+uniquename)=| |
447 | <iframe[^>]+\bsrc= | |
b8d8cced S |
448 | ) |
449 | (["\']) | |
450 | (?:(?!\1).)*\bContentItem-(?P<id>%s) | |
451 | ''' % self._UUID_RE, | |
452 | webpage, 'content item id', default=None, group='id') | |
453 | ||
454 | content_item_ids = set() | |
361f293a S |
455 | if content_item_id: |
456 | content_item_ids.add(content_item_id) | |
b8d8cced S |
457 | if video_id not in content_item_ids: |
458 | content_item_ids.add(video_id) | |
459 | ||
460 | for content_item_id in content_item_ids: | |
461 | try: | |
462 | return self._extract_from_content_id(content_item_id, url) | |
463 | except GeoRestrictedError: | |
464 | raise | |
465 | except ExtractorError: | |
466 | pass | |
467 | ||
a0566bbf | 468 | relinker_url = self._proto_relative_url(self._search_regex( |
b8d8cced S |
469 | r'''(?x) |
470 | (?: | |
471 | var\s+videoURL| | |
472 | mediaInfo\.mediaUri | |
473 | )\s*=\s* | |
474 | ([\'"]) | |
475 | (?P<url> | |
476 | (?:https?:)? | |
477 | //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\? | |
478 | (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1 | |
479 | ''', | |
a0566bbf | 480 | webpage, 'relinker URL', group='url')) |
b8d8cced S |
481 | |
482 | relinker_info = self._extract_relinker_info( | |
483 | urljoin(url, relinker_url), video_id) | |
484 | self._sort_formats(relinker_info['formats']) | |
485 | ||
486 | title = self._search_regex( | |
487 | r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1', | |
488 | webpage, 'title', group='title', | |
489 | default=None) or self._og_search_title(webpage) | |
490 | ||
491 | info = { | |
492 | 'id': video_id, | |
493 | 'title': title, | |
494 | } | |
495 | ||
496 | info.update(relinker_info) | |
497 | ||
498 | return info |