]>
Commit | Line | Data |
---|---|---|
4e826cd9 S |
1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
d91dd0ce S |
4 | import hashlib |
5 | import random | |
4e826cd9 | 6 | import re |
d91dd0ce | 7 | import time |
4e826cd9 S |
8 | |
9 | from .common import InfoExtractor | |
10 | from ..compat import compat_str | |
11 | from ..utils import ( | |
d91dd0ce | 12 | ExtractorError, |
4e826cd9 S |
13 | int_or_none, |
14 | parse_duration, | |
0931ba94 | 15 | srt_subtitles_timecode, |
5f969a78 | 16 | traverse_obj, |
4e826cd9 | 17 | try_get, |
d91dd0ce | 18 | urlencode_postdata, |
4e826cd9 S |
19 | ) |
20 | ||
21 | ||
22 | class NexxIE(InfoExtractor): | |
694b6154 S |
23 | _VALID_URL = r'''(?x) |
24 | (?: | |
0931ba94 | 25 | https?://api\.nexx(?:\.cloud|cdn\.com)/v3(?:\.\d)?/(?P<domain_id>\d+)/videos/byid/| |
b5434b5c | 26 | nexx:(?:(?P<domain_id_s>\d+):)?| |
0704306e | 27 | https?://arc\.nexx\.cloud/api/video/ |
694b6154 S |
28 | ) |
29 | (?P<id>\d+) | |
30 | ''' | |
4e826cd9 S |
31 | _TESTS = [{ |
32 | # movie | |
33 | 'url': 'https://api.nexx.cloud/v3/748/videos/byid/128907', | |
2e697530 | 34 | 'md5': '31899fd683de49ad46f4ee67e53e83fe', |
4e826cd9 S |
35 | 'info_dict': { |
36 | 'id': '128907', | |
37 | 'ext': 'mp4', | |
38 | 'title': 'Stiftung Warentest', | |
39 | 'alt_title': 'Wie ein Test abläuft', | |
40 | 'description': 'md5:d1ddb1ef63de721132abd38639cc2fd2', | |
4e826cd9 S |
41 | 'creator': 'SPIEGEL TV', |
42 | 'thumbnail': r're:^https?://.*\.jpg$', | |
43 | 'duration': 2509, | |
44 | 'timestamp': 1384264416, | |
45 | 'upload_date': '20131112', | |
46 | }, | |
0931ba94 | 47 | 'skip': 'Spiegel nexx CDNs are now disabled' |
4e826cd9 | 48 | }, { |
0931ba94 M |
49 | # episode with captions |
50 | 'url': 'https://api.nexx.cloud/v3.1/741/videos/byid/1701834', | |
4e826cd9 | 51 | 'info_dict': { |
0931ba94 | 52 | 'id': '1701834', |
4e826cd9 | 53 | 'ext': 'mp4', |
0931ba94 M |
54 | 'title': 'Mein Leben mit \'nem TikTok E-Boy 😤', |
55 | 'alt_title': 'Mein Leben mit \'nem TikTok E-Boy 😤', | |
56 | 'description': 'md5:f84f395a881fd143f952c892deab528d', | |
4e826cd9 | 57 | 'thumbnail': r're:^https?://.*\.jpg$', |
0931ba94 M |
58 | 'duration': 770, |
59 | 'timestamp': 1595600027, | |
60 | 'upload_date': '20200724', | |
4e826cd9 S |
61 | 'episode_number': 2, |
62 | 'season_number': 2, | |
0931ba94 M |
63 | 'episode': 'Episode 2', |
64 | 'season': 'Season 2', | |
4e826cd9 S |
65 | }, |
66 | 'params': { | |
4e826cd9 S |
67 | 'skip_download': True, |
68 | }, | |
d91dd0ce | 69 | }, { |
d91dd0ce | 70 | 'url': 'nexx:741:1269984', |
0931ba94 | 71 | 'md5': 'd5f14e14b592501e51addd5abef95a7f', |
d91dd0ce S |
72 | 'info_dict': { |
73 | 'id': '1269984', | |
74 | 'ext': 'mp4', | |
0931ba94 M |
75 | 'title': '1 TAG ohne KLO... wortwörtlich! ?', |
76 | 'alt_title': '1 TAG ohne KLO... wortwörtlich! ?', | |
77 | 'description': 'md5:2016393a31991a900946432ccdd09a6f', | |
d91dd0ce S |
78 | 'thumbnail': r're:^https?://.*\.jpg$', |
79 | 'duration': 607, | |
80 | 'timestamp': 1518614955, | |
81 | 'upload_date': '20180214', | |
82 | }, | |
06ea7bdd S |
83 | }, { |
84 | # free cdn from http://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html | |
85 | 'url': 'nexx:747:1533779', | |
86 | 'md5': '6bf6883912b82b7069fb86c2297e9893', | |
87 | 'info_dict': { | |
88 | 'id': '1533779', | |
89 | 'ext': 'mp4', | |
90 | 'title': 'Aufregung um ausgebrochene Raubtiere', | |
91 | 'alt_title': 'Eifel-Zoo', | |
92 | 'description': 'md5:f21375c91c74ad741dcb164c427999d2', | |
93 | 'thumbnail': r're:^https?://.*\.jpg$', | |
94 | 'duration': 111, | |
95 | 'timestamp': 1527874460, | |
96 | 'upload_date': '20180601', | |
97 | }, | |
0931ba94 | 98 | 'skip': 'Spiegel nexx CDNs are now disabled' |
4e826cd9 S |
99 | }, { |
100 | 'url': 'https://api.nexxcdn.com/v3/748/videos/byid/128907', | |
101 | 'only_matching': True, | |
694b6154 S |
102 | }, { |
103 | 'url': 'nexx:748:128907', | |
104 | 'only_matching': True, | |
9dc7ea32 S |
105 | }, { |
106 | 'url': 'nexx:128907', | |
107 | 'only_matching': True, | |
0704306e S |
108 | }, { |
109 | 'url': 'https://arc.nexx.cloud/api/video/128907.json', | |
110 | 'only_matching': True, | |
4e826cd9 S |
111 | }] |
112 | ||
694b6154 S |
113 | @staticmethod |
114 | def _extract_domain_id(webpage): | |
115 | mobj = re.search( | |
eb22d1b5 | 116 | r'<script\b[^>]+\bsrc=["\'](?:https?:)?//(?:require|arc)\.nexx(?:\.cloud|cdn\.com)/(?:sdk/)?(?P<id>\d+)', |
694b6154 S |
117 | webpage) |
118 | return mobj.group('id') if mobj else None | |
119 | ||
4e826cd9 S |
120 | @staticmethod |
121 | def _extract_urls(webpage): | |
122 | # Reference: | |
123 | # 1. https://nx-s.akamaized.net/files/201510/44.pdf | |
124 | ||
125 | entries = [] | |
126 | ||
127 | # JavaScript Integration | |
694b6154 S |
128 | domain_id = NexxIE._extract_domain_id(webpage) |
129 | if domain_id: | |
089b97cf | 130 | for video_id in re.findall( |
eb22d1b5 | 131 | r'(?is)onPLAYReady.+?_play\.(?:init|(?:control\.)?addPlayer)\s*\(.+?\s*,\s*["\']?(\d+)', |
089b97cf S |
132 | webpage): |
133 | entries.append( | |
134 | 'https://api.nexx.cloud/v3/%s/videos/byid/%s' | |
135 | % (domain_id, video_id)) | |
4e826cd9 S |
136 | |
137 | # TODO: support more embed formats | |
138 | ||
139 | return entries | |
140 | ||
3f59b015 S |
141 | @staticmethod |
142 | def _extract_url(webpage): | |
143 | return NexxIE._extract_urls(webpage)[0] | |
144 | ||
d91dd0ce | 145 | def _handle_error(self, response): |
0931ba94 M |
146 | if traverse_obj(response, ('metadata', 'notice'), expected_type=str): |
147 | self.report_warning('%s said: %s' % (self.IE_NAME, response['metadata']['notice'])) | |
d91dd0ce S |
148 | status = int_or_none(try_get( |
149 | response, lambda x: x['metadata']['status']) or 200) | |
150 | if 200 <= status < 300: | |
151 | return | |
152 | raise ExtractorError( | |
153 | '%s said: %s' % (self.IE_NAME, response['metadata']['errorhint']), | |
154 | expected=True) | |
155 | ||
156 | def _call_api(self, domain_id, path, video_id, data=None, headers={}): | |
157 | headers['Content-Type'] = 'application/x-www-form-urlencoded; charset=UTF-8' | |
158 | result = self._download_json( | |
159 | 'https://api.nexx.cloud/v3/%s/%s' % (domain_id, path), video_id, | |
160 | 'Downloading %s JSON' % path, data=urlencode_postdata(data), | |
161 | headers=headers) | |
162 | self._handle_error(result) | |
163 | return result['result'] | |
164 | ||
06ea7bdd S |
165 | def _extract_free_formats(self, video, video_id): |
166 | stream_data = video['streamdata'] | |
167 | cdn = stream_data['cdnType'] | |
168 | assert cdn == 'free' | |
169 | ||
170 | hash = video['general']['hash'] | |
171 | ||
172 | ps = compat_str(stream_data['originalDomain']) | |
173 | if stream_data['applyFolderHierarchy'] == 1: | |
174 | s = ('%04d' % int(video_id))[::-1] | |
175 | ps += '/%s/%s' % (s[0:2], s[2:4]) | |
176 | ps += '/%s/%s_' % (video_id, hash) | |
177 | ||
9afd74d7 RA |
178 | t = 'http://%s' + ps |
179 | fd = stream_data['azureFileDistribution'].split(',') | |
180 | cdn_provider = stream_data['cdnProvider'] | |
181 | ||
182 | def p0(p): | |
183 | return '_%s' % p if stream_data['applyAzureStructure'] == 1 else '' | |
184 | ||
185 | formats = [] | |
186 | if cdn_provider == 'ak': | |
187 | t += ',' | |
188 | for i in fd: | |
189 | p = i.split(':') | |
190 | t += p[1] + p0(int(p[0])) + ',' | |
191 | t += '.mp4.csmil/master.%s' | |
192 | elif cdn_provider == 'ce': | |
193 | k = t.split('/') | |
194 | h = k.pop() | |
195 | http_base = t = '/'.join(k) | |
196 | http_base = http_base % stream_data['cdnPathHTTP'] | |
197 | t += '/asset.ism/manifest.%s?dcp_ver=aos4&videostream=' | |
198 | for i in fd: | |
199 | p = i.split(':') | |
200 | tbr = int(p[0]) | |
201 | filename = '%s%s%s.mp4' % (h, p[1], p0(tbr)) | |
202 | f = { | |
203 | 'url': http_base + '/' + filename, | |
204 | 'format_id': '%s-http-%d' % (cdn, tbr), | |
205 | 'tbr': tbr, | |
206 | } | |
207 | width_height = p[1].split('x') | |
208 | if len(width_height) == 2: | |
209 | f.update({ | |
210 | 'width': int_or_none(width_height[0]), | |
211 | 'height': int_or_none(width_height[1]), | |
212 | }) | |
213 | formats.append(f) | |
214 | a = filename + ':%s' % (tbr * 1000) | |
215 | t += a + ',' | |
216 | t = t[:-1] + '&audiostream=' + a.split(':')[0] | |
217 | else: | |
218 | assert False | |
219 | ||
220 | if cdn_provider == 'ce': | |
221 | formats.extend(self._extract_mpd_formats( | |
222 | t % (stream_data['cdnPathDASH'], 'mpd'), video_id, | |
223 | mpd_id='%s-dash' % cdn, fatal=False)) | |
06ea7bdd | 224 | formats.extend(self._extract_m3u8_formats( |
9afd74d7 | 225 | t % (stream_data['cdnPathHLS'], 'm3u8'), video_id, 'mp4', |
06ea7bdd S |
226 | entry_protocol='m3u8_native', m3u8_id='%s-hls' % cdn, fatal=False)) |
227 | ||
228 | return formats | |
229 | ||
5f969a78 M |
230 | def _extract_3q_formats(self, video, video_id): |
231 | stream_data = video['streamdata'] | |
232 | cdn = stream_data['cdnType'] | |
233 | assert cdn == '3q' | |
234 | ||
235 | q_acc, q_prefix, q_locator, q_hash = stream_data['qAccount'], stream_data['qPrefix'], stream_data['qLocator'], stream_data['qHash'] | |
236 | protection_key = traverse_obj( | |
237 | video, ('protectiondata', 'key'), expected_type=str) | |
238 | ||
239 | def get_cdn_shield_base(shield_type=''): | |
240 | for secure in ('', 's'): | |
241 | cdn_shield = stream_data.get('cdnShield%sHTTP%s' % (shield_type, secure.upper())) | |
242 | if cdn_shield: | |
243 | return 'http%s://%s' % (secure, cdn_shield) | |
244 | return f'http://sdn-global-{"prog" if shield_type.lower() == "prog" else "streaming"}-cache.3qsdn.com/' + (f's/{protection_key}/' if protection_key else '') | |
245 | ||
246 | stream_base = get_cdn_shield_base() | |
247 | ||
248 | formats = [] | |
249 | formats.extend(self._extract_m3u8_formats( | |
250 | f'{stream_base}{q_acc}/files/{q_prefix}/{q_locator}/{q_acc}-{stream_data.get("qHEVCHash") or q_hash}.ism/manifest.m3u8', | |
251 | video_id, 'mp4', m3u8_id=f'{cdn}-hls', fatal=False)) | |
252 | formats.extend(self._extract_mpd_formats( | |
253 | f'{stream_base}{q_acc}/files/{q_prefix}/{q_locator}/{q_acc}-{q_hash}.ism/manifest.mpd', | |
254 | video_id, mpd_id=f'{cdn}-dash', fatal=False)) | |
255 | ||
256 | progressive_base = get_cdn_shield_base('Prog') | |
257 | q_references = stream_data.get('qReferences') or '' | |
258 | fds = q_references.split(',') | |
259 | for fd in fds: | |
260 | ss = fd.split(':') | |
261 | if len(ss) != 3: | |
262 | continue | |
263 | tbr = int_or_none(ss[1], scale=1000) | |
264 | formats.append({ | |
265 | 'url': f'{progressive_base}{q_acc}/uploads/{q_acc}-{ss[2]}.webm', | |
266 | 'format_id': f'{cdn}-{ss[0]}{"-%s" % tbr if tbr else ""}', | |
267 | 'tbr': tbr, | |
268 | }) | |
269 | ||
270 | azure_file_distribution = stream_data.get('azureFileDistribution') or '' | |
271 | fds = azure_file_distribution.split(',') | |
272 | for fd in fds: | |
273 | ss = fd.split(':') | |
274 | if len(ss) != 3: | |
275 | continue | |
276 | tbr = int_or_none(ss[0]) | |
277 | width, height = ss[1].split('x') if len(ss[1].split('x')) == 2 else (None, None) | |
278 | f = { | |
279 | 'url': f'{progressive_base}{q_acc}/files/{q_prefix}/{q_locator}/{ss[2]}.mp4', | |
280 | 'format_id': f'{cdn}-http-{"-%s" % tbr if tbr else ""}', | |
281 | 'tbr': tbr, | |
282 | 'width': int_or_none(width), | |
283 | 'height': int_or_none(height), | |
284 | } | |
285 | formats.append(f) | |
286 | ||
287 | return formats | |
288 | ||
06ea7bdd S |
289 | def _extract_azure_formats(self, video, video_id): |
290 | stream_data = video['streamdata'] | |
291 | cdn = stream_data['cdnType'] | |
292 | assert cdn == 'azure' | |
293 | ||
294 | azure_locator = stream_data['azureLocator'] | |
295 | ||
296 | def get_cdn_shield_base(shield_type='', static=False): | |
297 | for secure in ('', 's'): | |
298 | cdn_shield = stream_data.get('cdnShield%sHTTP%s' % (shield_type, secure.upper())) | |
299 | if cdn_shield: | |
300 | return 'http%s://%s' % (secure, cdn_shield) | |
301 | else: | |
302 | if 'fb' in stream_data['azureAccount']: | |
303 | prefix = 'df' if static else 'f' | |
304 | else: | |
305 | prefix = 'd' if static else 'p' | |
306 | account = int(stream_data['azureAccount'].replace('nexxplayplus', '').replace('nexxplayfb', '')) | |
307 | return 'http://nx-%s%02d.akamaized.net/' % (prefix, account) | |
308 | ||
309 | language = video['general'].get('language_raw') or '' | |
310 | ||
311 | azure_stream_base = get_cdn_shield_base() | |
312 | is_ml = ',' in language | |
313 | azure_manifest_url = '%s%s/%s_src%s.ism/Manifest' % ( | |
314 | azure_stream_base, azure_locator, video_id, ('_manifest' if is_ml else '')) + '%s' | |
315 | ||
316 | protection_token = try_get( | |
317 | video, lambda x: x['protectiondata']['token'], compat_str) | |
318 | if protection_token: | |
319 | azure_manifest_url += '?hdnts=%s' % protection_token | |
320 | ||
321 | formats = self._extract_m3u8_formats( | |
322 | azure_manifest_url % '(format=m3u8-aapl)', | |
323 | video_id, 'mp4', 'm3u8_native', | |
324 | m3u8_id='%s-hls' % cdn, fatal=False) | |
325 | formats.extend(self._extract_mpd_formats( | |
326 | azure_manifest_url % '(format=mpd-time-csf)', | |
327 | video_id, mpd_id='%s-dash' % cdn, fatal=False)) | |
328 | formats.extend(self._extract_ism_formats( | |
329 | azure_manifest_url % '', video_id, ism_id='%s-mss' % cdn, fatal=False)) | |
330 | ||
331 | azure_progressive_base = get_cdn_shield_base('Prog', True) | |
332 | azure_file_distribution = stream_data.get('azureFileDistribution') | |
333 | if azure_file_distribution: | |
334 | fds = azure_file_distribution.split(',') | |
335 | if fds: | |
336 | for fd in fds: | |
337 | ss = fd.split(':') | |
338 | if len(ss) == 2: | |
339 | tbr = int_or_none(ss[0]) | |
340 | if tbr: | |
341 | f = { | |
342 | 'url': '%s%s/%s_src_%s_%d.mp4' % ( | |
343 | azure_progressive_base, azure_locator, video_id, ss[1], tbr), | |
344 | 'format_id': '%s-http-%d' % (cdn, tbr), | |
345 | 'tbr': tbr, | |
346 | } | |
347 | width_height = ss[1].split('x') | |
348 | if len(width_height) == 2: | |
349 | f.update({ | |
350 | 'width': int_or_none(width_height[0]), | |
351 | 'height': int_or_none(width_height[1]), | |
352 | }) | |
353 | formats.append(f) | |
354 | ||
355 | return formats | |
356 | ||
4e826cd9 | 357 | def _real_extract(self, url): |
5ad28e7f | 358 | mobj = self._match_valid_url(url) |
d91dd0ce S |
359 | domain_id = mobj.group('domain_id') or mobj.group('domain_id_s') |
360 | video_id = mobj.group('id') | |
361 | ||
362 | video = None | |
4e826cd9 | 363 | |
7e05df71 RA |
364 | def find_video(result): |
365 | if isinstance(result, dict): | |
366 | return result | |
367 | elif isinstance(result, list): | |
368 | vid = int(video_id) | |
369 | for v in result: | |
370 | if try_get(v, lambda x: x['general']['ID'], int) == vid: | |
371 | return v | |
372 | return None | |
373 | ||
d91dd0ce | 374 | response = self._download_json( |
e231afb1 | 375 | 'https://arc.nexx.cloud/api/video/%s.json' % video_id, |
d91dd0ce S |
376 | video_id, fatal=False) |
377 | if response and isinstance(response, dict): | |
378 | result = response.get('result') | |
7e05df71 RA |
379 | if result: |
380 | video = find_video(result) | |
d91dd0ce S |
381 | |
382 | # not all videos work via arc, e.g. nexx:741:1269984 | |
383 | if not video: | |
384 | # Reverse engineered from JS code (see getDeviceID function) | |
385 | device_id = '%d:%d:%d%d' % ( | |
386 | random.randint(1, 4), int(time.time()), | |
387 | random.randint(1e4, 99999), random.randint(1, 9)) | |
388 | ||
389 | result = self._call_api(domain_id, 'session/init', video_id, data={ | |
390 | 'nxp_devh': device_id, | |
391 | 'nxp_userh': '', | |
392 | 'precid': '0', | |
393 | 'playlicense': '0', | |
394 | 'screenx': '1920', | |
395 | 'screeny': '1080', | |
396 | 'playerversion': '6.0.00', | |
397 | 'gateway': 'html5', | |
398 | 'adGateway': '', | |
399 | 'explicitlanguage': 'en-US', | |
400 | 'addTextTemplates': '1', | |
401 | 'addDomainData': '1', | |
402 | 'addAdModel': '1', | |
403 | }, headers={ | |
404 | 'X-Request-Enable-Auth-Fallback': '1', | |
405 | }) | |
406 | ||
407 | cid = result['general']['cid'] | |
408 | ||
409 | # As described in [1] X-Request-Token generation algorithm is | |
410 | # as follows: | |
411 | # md5( operation + domain_id + domain_secret ) | |
412 | # where domain_secret is a static value that will be given by nexx.tv | |
413 | # as per [1]. Here is how this "secret" is generated (reversed | |
0931ba94 M |
414 | # from _play._factory.data.getDomainData function, search for |
415 | # domaintoken or enableAPIAccess). So it's actually not static | |
416 | # and not that much of a secret. | |
d91dd0ce | 417 | # 1. https://nexxtvstorage.blob.core.windows.net/files/201610/27.pdf |
0931ba94 | 418 | secret = result['device']['domaintoken'][int(device_id[0]):] |
d91dd0ce S |
419 | secret = secret[0:len(secret) - int(device_id[-1])] |
420 | ||
421 | op = 'byid' | |
422 | ||
423 | # Reversed from JS code for _play.api.call function (search for | |
424 | # X-Request-Token) | |
425 | request_token = hashlib.md5( | |
426 | ''.join((op, domain_id, secret)).encode('utf-8')).hexdigest() | |
427 | ||
7e05df71 | 428 | result = self._call_api( |
d91dd0ce | 429 | domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={ |
0931ba94 | 430 | 'additionalfields': 'language,channel,format,licenseby,slug,fileversion,episode,season', |
d91dd0ce S |
431 | 'addInteractionOptions': '1', |
432 | 'addStatusDetails': '1', | |
433 | 'addStreamDetails': '1', | |
0931ba94 M |
434 | 'addFeatures': '1', |
435 | # Caption format selection doesn't seem to be enforced? | |
436 | 'addCaptions': 'vtt', | |
d91dd0ce | 437 | 'addScenes': '1', |
0931ba94 | 438 | 'addChapters': '1', |
d91dd0ce | 439 | 'addHotSpots': '1', |
0931ba94 | 440 | 'addConnectedMedia': 'persons', |
d91dd0ce | 441 | 'addBumpers': '1', |
d91dd0ce S |
442 | }, headers={ |
443 | 'X-Request-CID': cid, | |
444 | 'X-Request-Token': request_token, | |
445 | }) | |
7e05df71 | 446 | video = find_video(result) |
4e826cd9 S |
447 | |
448 | general = video['general'] | |
449 | title = general['title'] | |
450 | ||
06ea7bdd | 451 | cdn = video['streamdata']['cdnType'] |
4e826cd9 | 452 | |
06ea7bdd S |
453 | if cdn == 'azure': |
454 | formats = self._extract_azure_formats(video, video_id) | |
455 | elif cdn == 'free': | |
456 | formats = self._extract_free_formats(video, video_id) | |
5f969a78 M |
457 | elif cdn == '3q': |
458 | formats = self._extract_3q_formats(video, video_id) | |
06ea7bdd | 459 | else: |
48e93106 | 460 | self.raise_no_formats(f'{cdn} formats are currently not supported', video_id) |
c0f647a1 | 461 | |
4e826cd9 S |
462 | self._sort_formats(formats) |
463 | ||
0931ba94 M |
464 | subtitles = {} |
465 | for sub in video.get('captiondata') or []: | |
466 | if sub.get('data'): | |
467 | subtitles.setdefault(sub.get('language', 'en'), []).append({ | |
468 | 'ext': 'srt', | |
469 | 'data': '\n\n'.join( | |
470 | f'{i + 1}\n{srt_subtitles_timecode(line["fromms"] / 1000)} --> {srt_subtitles_timecode(line["toms"] / 1000)}\n{line["caption"]}' | |
471 | for i, line in enumerate(sub['data'])), | |
472 | 'name': sub.get('language_long') or sub.get('title') | |
473 | }) | |
474 | elif sub.get('url'): | |
475 | subtitles.setdefault(sub.get('language', 'en'), []).append({ | |
476 | 'url': sub['url'], | |
477 | 'ext': sub.get('format'), | |
478 | 'name': sub.get('language_long') or sub.get('title') | |
479 | }) | |
480 | ||
4e826cd9 S |
481 | return { |
482 | 'id': video_id, | |
483 | 'title': title, | |
484 | 'alt_title': general.get('subtitle'), | |
485 | 'description': general.get('description'), | |
486 | 'release_year': int_or_none(general.get('year')), | |
0931ba94 | 487 | 'creator': general.get('studio') or general.get('studio_adref') or None, |
4e826cd9 S |
488 | 'thumbnail': try_get( |
489 | video, lambda x: x['imagedata']['thumb'], compat_str), | |
490 | 'duration': parse_duration(general.get('runtime')), | |
491 | 'timestamp': int_or_none(general.get('uploaded')), | |
0931ba94 M |
492 | 'episode_number': traverse_obj( |
493 | video, (('episodedata', 'general'), 'episode'), expected_type=int, get_all=False), | |
494 | 'season_number': traverse_obj( | |
495 | video, (('episodedata', 'general'), 'season'), expected_type=int, get_all=False), | |
496 | 'cast': traverse_obj(video, ('connectedmedia', ..., 'title'), expected_type=str), | |
4e826cd9 | 497 | 'formats': formats, |
0931ba94 | 498 | 'subtitles': subtitles, |
4e826cd9 | 499 | } |
3f59b015 S |
500 | |
501 | ||
502 | class NexxEmbedIE(InfoExtractor): | |
eb22d1b5 RA |
503 | _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:video/)?(?P<id>[^/?#&]+)' |
504 | _TESTS = [{ | |
3f59b015 S |
505 | 'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1', |
506 | 'md5': '16746bfc28c42049492385c989b26c4a', | |
507 | 'info_dict': { | |
508 | 'id': '161464', | |
509 | 'ext': 'mp4', | |
510 | 'title': 'Nervenkitzel Achterbahn', | |
511 | 'alt_title': 'Karussellbauer in Deutschland', | |
512 | 'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc', | |
3f59b015 S |
513 | 'creator': 'SPIEGEL TV', |
514 | 'thumbnail': r're:^https?://.*\.jpg$', | |
515 | 'duration': 2761, | |
516 | 'timestamp': 1394021479, | |
517 | 'upload_date': '20140305', | |
518 | }, | |
519 | 'params': { | |
3f59b015 S |
520 | 'skip_download': True, |
521 | }, | |
eb22d1b5 RA |
522 | }, { |
523 | 'url': 'https://embed.nexx.cloud/11888/video/DSRTO7UVOX06S7', | |
524 | 'only_matching': True, | |
525 | }] | |
3f59b015 S |
526 | |
527 | @staticmethod | |
528 | def _extract_urls(webpage): | |
529 | # Reference: | |
530 | # 1. https://nx-s.akamaized.net/files/201510/44.pdf | |
531 | ||
532 | # iFrame Embed Integration | |
533 | return [mobj.group('url') for mobj in re.finditer( | |
13eb526f | 534 | r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:(?!\1).)+)\1', |
3f59b015 S |
535 | webpage)] |
536 | ||
537 | def _real_extract(self, url): | |
538 | embed_id = self._match_id(url) | |
539 | ||
540 | webpage = self._download_webpage(url, embed_id) | |
541 | ||
542 | return self.url_result(NexxIE._extract_url(webpage), ie=NexxIE.ie_key()) |