]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/mtv.py
[extractors] Use new framework for existing embeds (#4307)
[yt-dlp.git] / yt_dlp / extractor / mtv.py
CommitLineData
fc287219 1import re
fc287219 2
0af25f78 3from .common import InfoExtractor
f8271158 4from ..compat import compat_str
1cc79574 5from ..utils import (
fc287219 6 ExtractorError,
90834c78 7 find_xpath_attr,
5aafe895 8 fix_xml_ampersands,
8765151c 9 float_or_none,
0ef68e04 10 HEADRequest,
605b684c 11 int_or_none,
34921b43 12 join_nonempty,
0c75abbb 13 RegexNotFoundError,
5c2266df 14 sanitized_Request,
7cdfc4c9 15 strip_or_none,
712c7530 16 timeconvert,
adf063da 17 try_get,
340b0468 18 unescapeHTML,
0c75abbb 19 update_url_query,
8d9453b9 20 url_basename,
5767b4ee 21 xpath_text,
fc287219
PH
22)
23
90834c78 24
300fcad8
JMF
25def _media_xml_tag(tag):
26 return '{http://search.yahoo.com/mrss/}%s' % tag
fc287219 27
f7e02595 28
0af25f78 29class MTVServicesInfoExtractor(InfoExtractor):
340b0468 30 _MOBILE_TEMPLATE = None
a542e372 31 _LANG = None
8940c1c0 32
f7e02595
JMF
33 @staticmethod
34 def _id_from_uri(uri):
35 return uri.split(':')[-1]
36
0c75abbb
YCH
37 @staticmethod
38 def _remove_template_parameter(url):
39 # Remove the templates, like &device={device}
40 return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
41
02def271 42 def _get_feed_url(self, uri, url=None):
8940c1c0
JMF
43 return self._FEED_URL
44
ab2f744b 45 def _get_thumbnail_url(self, uri, itemdoc):
84db8181
JMF
46 search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
47 thumb_node = itemdoc.find(search_path)
48 if thumb_node is None:
49 return None
70bfab0e 50 return thumb_node.get('url') or thumb_node.text or None
f7e02595 51
340b0468
JMF
52 def _extract_mobile_video_formats(self, mtvn_id):
53 webpage_url = self._MOBILE_TEMPLATE % mtvn_id
5c2266df 54 req = sanitized_Request(webpage_url)
340b0468 55 # Otherwise we get a webpage that would execute some javascript
3fcfb8e9 56 req.add_header('User-Agent', 'curl/7')
340b0468 57 webpage = self._download_webpage(req, mtvn_id,
9e1a5b84 58 'Downloading mobile page')
0ef68e04
JMF
59 metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
60 req = HEADRequest(metrics_url)
61 response = self._request_webpage(req, mtvn_id, 'Resolving url')
62 url = response.geturl()
63 # Transform the url to get the best quality:
64 url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
5f6a1245 65 return [{'url': url, 'ext': 'mp4'}]
340b0468 66
dbaf6016 67 def _extract_video_formats(self, mdoc, mtvn_id, video_id):
054d43bb 68 if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:
340b0468 69 if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
0ef68e04 70 self.to_screen('The normal version is not available from your '
9e1a5b84 71 'country, trying with the mobile version')
340b0468 72 return self._extract_mobile_video_formats(mtvn_id)
cc1db7f9 73 raise ExtractorError('This video is not available from your country.',
9e1a5b84 74 expected=True)
f7e02595 75
f13d0933
PH
76 formats = []
77 for rendition in mdoc.findall('.//rendition'):
20faad74 78 if rendition.get('method') == 'hls':
dbaf6016 79 hls_url = rendition.find('./src').text
cdd11c05 80 formats.extend(self._extract_m3u8_formats(
adf063da 81 hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
e0f1fb0a 82 m3u8_id='hls', fatal=False))
dbaf6016
PH
83 else:
84 # fms
85 try:
86 _, _, ext = rendition.attrib['type'].partition('/')
87 rtmp_video_url = rendition.find('./src').text
adf063da
S
88 if 'error_not_available.swf' in rtmp_video_url:
89 raise ExtractorError(
90 '%s said: video is not available' % self.IE_NAME,
91 expected=True)
dbaf6016
PH
92 if rtmp_video_url.endswith('siteunavail.png'):
93 continue
dbaf6016 94 formats.extend([{
adf063da
S
95 'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext,
96 'url': rtmp_video_url,
34921b43 97 'format_id': join_nonempty(
adf063da 98 'rtmp' if rtmp_video_url.startswith('rtmp') else None,
34921b43 99 rendition.get('bitrate')),
dbaf6016
PH
100 'width': int(rendition.get('width')),
101 'height': int(rendition.get('height')),
adf063da 102 }])
dbaf6016
PH
103 except (KeyError, TypeError):
104 raise ExtractorError('Invalid rendition field.')
e0f1fb0a
S
105 if formats:
106 self._sort_formats(formats)
f13d0933 107 return formats
f7e02595 108
e525d9a3
S
109 def _extract_subtitles(self, mdoc, mtvn_id):
110 subtitles = {}
e525d9a3
S
111 for transcript in mdoc.findall('.//transcript'):
112 if transcript.get('kind') != 'captions':
113 continue
114 lang = transcript.get('srclang')
5ea765fb
RA
115 for typographic in transcript.findall('./typographic'):
116 sub_src = typographic.get('src')
117 if not sub_src:
118 continue
119 ext = typographic.get('format')
120 if ext == 'cea-608':
121 ext = 'scc'
122 subtitles.setdefault(lang, []).append({
123 'url': compat_str(sub_src),
124 'ext': ext
125 })
0af25f78 126 return subtitles
e525d9a3 127
67fc365b 128 def _get_video_info(self, itemdoc, use_hls=True):
f7e02595
JMF
129 uri = itemdoc.find('guid').text
130 video_id = self._id_from_uri(uri)
131 self.report_extraction(video_id)
04cbc498 132 content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content')))
0c75abbb 133 mediagen_url = self._remove_template_parameter(content_el.attrib['url'])
dbaf6016 134 mediagen_url = mediagen_url.replace('device={device}', '')
f7e02595 135 if 'acceptMethods' not in mediagen_url:
56f447be 136 mediagen_url += '&' if '?' in mediagen_url else '?'
dbaf6016
PH
137 mediagen_url += 'acceptMethods='
138 mediagen_url += 'hls' if use_hls else 'fms'
6562df76 139
e0f1fb0a
S
140 mediagen_doc = self._download_xml(
141 mediagen_url, video_id, 'Downloading video urls', fatal=False)
142
143 if mediagen_doc is False:
144 return None
f7e02595 145
0dfe9bc9
S
146 item = mediagen_doc.find('./video/item')
147 if item is not None and item.get('type') == 'text':
148 message = '%s returned error: ' % self.IE_NAME
149 if item.get('code') is not None:
150 message += '%s - ' % item.get('code')
151 message += item.text
152 raise ExtractorError(message, expected=True)
153
7cdfc4c9 154 description = strip_or_none(xpath_text(itemdoc, 'description'))
f13d0933 155
712c7530
YCH
156 timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
157
90834c78
PH
158 title_el = None
159 if title_el is None:
160 title_el = find_xpath_attr(
161 itemdoc, './/{http://search.yahoo.com/mrss/}category',
162 'scheme', 'urn:mtvn:video_title')
90834c78 163 if title_el is None:
f9934b96 164 title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
96cb10a5 165 if title_el is None:
f9934b96 166 title_el = itemdoc.find('.//title')
1df4229b
PH
167 if title_el.text is None:
168 title_el = None
1df4229b 169
90834c78
PH
170 title = title_el.text
171 if title is None:
172 raise ExtractorError('Could not find video title')
780ee4e5 173 title = title.strip()
90834c78 174
605b684c 175 series = find_xpath_attr(
176 itemdoc, './/{http://search.yahoo.com/mrss/}category',
177 'scheme', 'urn:mtvn:franchise')
178 season = find_xpath_attr(
179 itemdoc, './/{http://search.yahoo.com/mrss/}category',
180 'scheme', 'urn:mtvn:seasonN')
181 episode = find_xpath_attr(
182 itemdoc, './/{http://search.yahoo.com/mrss/}category',
183 'scheme', 'urn:mtvn:episodeN')
184 series = series.text if series is not None else None
185 season = season.text if season is not None else None
186 episode = episode.text if episode is not None else None
187 if season and episode:
188 # episode number includes season, so remove it
189 episode = re.sub(r'^%s' % season, '', episode)
190
340b0468
JMF
191 # This a short id that's used in the webpage urls
192 mtvn_id = None
193 mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
9e1a5b84 194 'scheme', 'urn:mtvn:id')
340b0468
JMF
195 if mtvn_id_node is not None:
196 mtvn_id = mtvn_id_node.text
197
dbaf6016
PH
198 formats = self._extract_video_formats(mediagen_doc, mtvn_id, video_id)
199
e0f1fb0a
S
200 # Some parts of complete video may be missing (e.g. missing Act 3 in
201 # http://www.southpark.de/alle-episoden/s14e01-sexual-healing)
202 if not formats:
203 return None
204
205 self._sort_formats(formats)
206
fb7abb31 207 return {
90834c78 208 'title': title,
dbaf6016 209 'formats': formats,
e525d9a3 210 'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
f13d0933
PH
211 'id': video_id,
212 'thumbnail': self._get_thumbnail_url(uri, itemdoc),
213 'description': description,
04cbc498 214 'duration': float_or_none(content_el.attrib.get('duration')),
712c7530 215 'timestamp': timestamp,
605b684c 216 'series': series,
217 'season_number': int_or_none(season),
218 'episode_number': int_or_none(episode),
f13d0933
PH
219 }
220
c1e90619 221 def _get_feed_query(self, uri):
222 data = {'uri': uri}
223 if self._LANG:
224 data['lang'] = self._LANG
0c75abbb 225 return data
c1e90619 226
02def271 227 def _get_videos_info(self, uri, use_hls=True, url=None):
f7e02595 228 video_id = self._id_from_uri(uri)
02def271 229 feed_url = self._get_feed_url(uri, url)
0c75abbb 230 info_url = update_url_query(feed_url, self._get_feed_query(uri))
dbaf6016 231 return self._get_videos_info_from_url(info_url, video_id, use_hls)
79fa9db0 232
67fc365b 233 def _get_videos_info_from_url(self, url, video_id, use_hls=True):
e2b38da9 234 idoc = self._download_xml(
79fa9db0 235 url, video_id,
32dac694 236 'Downloading info', transform_source=fix_xml_ampersands)
712c7530
YCH
237
238 title = xpath_text(idoc, './channel/title')
239 description = xpath_text(idoc, './channel/description')
240
e0f1fb0a
S
241 entries = []
242 for item in idoc.findall('.//item'):
243 info = self._get_video_info(item, use_hls)
244 if info:
245 entries.append(info)
246
bc97cdae 247 # TODO: should be multi-video
5239075b 248 return self.playlist_result(
e0f1fb0a 249 entries, playlist_title=title, playlist_description=description)
fc287219 250
adf063da
S
251 def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
252 triforce_feed = self._parse_json(self._search_regex(
f1e70fc2 253 r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
adf063da
S
254 'triforce feed', default='{}'), video_id, fatal=False)
255
256 data_zone = self._search_regex(
257 r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
258 'data zone', default=data_zone, group='zone')
259
260 feed_url = try_get(
261 triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
262 compat_str)
263 if not feed_url:
264 return
265
266 feed = self._download_json(feed_url, video_id, fatal=False)
267 if not feed:
268 return
269
270 return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
271
a820dc72
RA
272 @staticmethod
273 def _extract_child_with_type(parent, t):
f7ad7160 274 for c in parent['children']:
275 if c.get('type') == t:
276 return c
a820dc72 277
ee1e0558 278 def _extract_mgid(self, webpage):
8d9453b9 279 try:
4bbf139a
JMF
280 # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
281 # or http://media.mtvnservices.com/{mgid}
282 og_url = self._og_search_video_url(webpage)
283 mgid = url_basename(og_url)
284 if mgid.endswith('.swf'):
285 mgid = mgid[:-4]
8d9453b9 286 except RegexNotFoundError:
b1298d8e
AMW
287 mgid = None
288
289 if mgid is None or ':' not in mgid:
b9381e43 290 mgid = self._search_regex(
197224b7 291 [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
fc42bc6e
S
292 webpage, 'mgid', default=None)
293
294 if not mgid:
295 sm4_embed = self._html_search_meta(
296 'sm4:video:embed', webpage, 'sm4 embed', default='')
297 mgid = self._search_regex(
adf063da
S
298 r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
299
b6e0c7d2 300 if not mgid:
ee1e0558 301 mgid = self._extract_triforce_mgid(webpage)
adf063da 302
a820dc72
RA
303 if not mgid:
304 data = self._parse_json(self._search_regex(
305 r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
306 main_container = self._extract_child_with_type(data, 'MainContainer')
f7ad7160 307 ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
308 video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
fec41d17
S
309 if video_player:
310 mgid = try_get(video_player, lambda x: x['props']['media']['video']['config']['uri'])
311 else:
312 flex_wrapper = self._extract_child_with_type(ab_testing or main_container, 'FlexWrapper')
313 auth_suite_wrapper = self._extract_child_with_type(flex_wrapper, 'AuthSuiteWrapper')
314 player = self._extract_child_with_type(auth_suite_wrapper or flex_wrapper, 'Player')
315 if player:
316 mgid = try_get(player, lambda x: x['props']['videoDetail']['mgid'])
317
318 if not mgid:
319 raise ExtractorError('Could not extract mgid')
a820dc72 320
c1e90619 321 return mgid
e525d9a3 322
c1e90619 323 def _real_extract(self, url):
324 title = url_basename(url)
325 webpage = self._download_webpage(url, title)
ee1e0558 326 mgid = self._extract_mgid(webpage)
02def271 327 videos_info = self._get_videos_info(mgid, url=url)
e525d9a3 328 return videos_info
8d9453b9 329
84db8181 330
8940c1c0
JMF
331class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
332 IE_NAME = 'mtvservices:embedded'
333 _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
bfd973ec 334 _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1']
8940c1c0
JMF
335
336 _TEST = {
337 # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
338 'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
339 'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
340 'info_dict': {
341 'id': '1043906',
342 'ext': 'mp4',
343 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
344 'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
712c7530
YCH
345 'timestamp': 1400126400,
346 'upload_date': '20140515',
8940c1c0
JMF
347 },
348 }
349
02def271 350 def _get_feed_url(self, uri, url=None):
8940c1c0 351 video_id = self._id_from_uri(uri)
0c75abbb
YCH
352 config = self._download_json(
353 'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id)
354 return self._remove_template_parameter(config['feedWithQueryParams'])
8940c1c0
JMF
355
356 def _real_extract(self, url):
5ad28e7f 357 mobj = self._match_valid_url(url)
8940c1c0
JMF
358 mgid = mobj.group('mgid')
359 return self._get_videos_info(mgid)
360
361
84db8181 362class MTVIE(MTVServicesInfoExtractor):
a54ffb8a 363 IE_NAME = 'mtv'
cf0cabbe 364 _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
8add4bfe
RA
365 _FEED_URL = 'http://www.mtv.com/feeds/mrss/'
366
367 _TESTS = [{
368 'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer',
369 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
370 'info_dict': {
371 'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
372 'ext': 'mp4',
373 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
374 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
375 'timestamp': 1468846800,
376 'upload_date': '20160718',
377 },
378 }, {
379 'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
380 'only_matching': True,
cf0cabbe
S
381 }, {
382 'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
383 'only_matching': True,
8add4bfe
RA
384 }]
385
386
3cdcebf5
RA
387class MTVJapanIE(MTVServicesInfoExtractor):
388 IE_NAME = 'mtvjapan'
389 _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)'
008f2470
S
390
391 _TEST = {
3cdcebf5 392 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade',
008f2470 393 'info_dict': {
3cdcebf5 394 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5',
008f2470 395 'ext': 'mp4',
3cdcebf5
RA
396 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition',
397 },
398 'params': {
399 'skip_download': True,
008f2470
S
400 },
401 }
3cdcebf5
RA
402 _GEO_COUNTRIES = ['JP']
403 _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
008f2470 404
3cdcebf5
RA
405 def _get_feed_query(self, uri):
406 return {
407 'arcEp': 'mtvjapan.com',
408 'mgid': uri,
409 }
008f2470
S
410
411
8add4bfe 412class MTVVideoIE(MTVServicesInfoExtractor):
a54ffb8a 413 IE_NAME = 'mtv:video'
5c541b2c
JMF
414 _VALID_URL = r'''(?x)^https?://
415 (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
416 m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''
84db8181
JMF
417
418 _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
419
420 _TESTS = [
421 {
32dac694 422 'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
32dac694
PH
423 'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
424 'info_dict': {
ca0f500e
PH
425 'id': '853555',
426 'ext': 'mp4',
32dac694
PH
427 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
428 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
712c7530
YCH
429 'timestamp': 1352610000,
430 'upload_date': '20121111',
84db8181
JMF
431 },
432 },
84db8181
JMF
433 ]
434
435 def _get_thumbnail_url(self, uri, itemdoc):
436 return 'http://mtv.mtvnimages.com/uri/' + uri
437
fc287219 438 def _real_extract(self, url):
5ad28e7f 439 mobj = self._match_valid_url(url)
fc287219 440 video_id = mobj.group('videoid')
c801b205 441 uri = mobj.groupdict().get('mgid')
5c541b2c
JMF
442 if uri is None:
443 webpage = self._download_webpage(url, video_id)
5f6a1245 444
5c541b2c 445 # Some videos come from Vevo.com
ca0f500e
PH
446 m_vevo = re.search(
447 r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
5c541b2c 448 if m_vevo:
8bcc8756 449 vevo_id = m_vevo.group(1)
32dac694 450 self.to_screen('Vevo video detected: %s' % vevo_id)
5c541b2c 451 return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
5f6a1245 452
32dac694 453 uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri')
f7e02595 454 return self._get_videos_info(uri)
bc4ba05f
JMF
455
456
071c1013
PH
457class MTVDEIE(MTVServicesInfoExtractor):
458 IE_NAME = 'mtv.de'
cfabc505 459 _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)'
79fa9db0 460 _TESTS = [{
cfabc505 461 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum',
79fa9db0 462 'info_dict': {
cfabc505
RA
463 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5',
464 'ext': 'mp4',
465 'title': 'Traum',
466 'description': 'Traum',
071c1013 467 },
79fa9db0
S
468 'params': {
469 # rtmp download
470 'skip_download': True,
471 },
35f6e0ff 472 'skip': 'Blocked at Travis CI',
c3c9f879
S
473 }, {
474 # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
cfabc505 475 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1',
c3c9f879 476 'info_dict': {
cfabc505
RA
477 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285',
478 'ext': 'mp4',
479 'title': 'Teen Mom 2',
480 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7',
c3c9f879
S
481 },
482 'params': {
483 # rtmp download
484 'skip_download': True,
485 },
35f6e0ff 486 'skip': 'Blocked at Travis CI',
65488b82 487 }, {
cfabc505 488 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3',
65488b82
S
489 'info_dict': {
490 'id': 'local_playlist-4e760566473c4c8c5344',
491 'ext': 'mp4',
492 'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1',
493 'description': 'MTV Movies Supercut',
494 },
495 'params': {
496 # rtmp download
497 'skip_download': True,
498 },
712c7530 499 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
79fa9db0 500 }]
cfabc505
RA
501 _GEO_COUNTRIES = ['DE']
502 _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
071c1013 503
cfabc505
RA
504 def _get_feed_query(self, uri):
505 return {
506 'arcEp': 'mtv.de',
507 'mgid': uri,
508 }
605b684c 509
510
511class MTVItaliaIE(MTVServicesInfoExtractor):
512 IE_NAME = 'mtv.it'
513 _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:episodi|video|musica)/(?P<id>[0-9a-z]+)'
514 _TESTS = [{
515 'url': 'http://www.mtv.it/episodi/24bqab/mario-una-serie-di-maccio-capatonda-cavoli-amario-episodio-completo-S1-E1',
516 'info_dict': {
517 'id': '0f0fc78e-45fc-4cce-8f24-971c25477530',
518 'ext': 'mp4',
519 'title': 'Cavoli amario (episodio completo)',
520 'description': 'md5:4962bccea8fed5b7c03b295ae1340660',
521 'series': 'Mario - Una Serie Di Maccio Capatonda',
522 'season_number': 1,
523 'episode_number': 1,
524 },
525 'params': {
526 'skip_download': True,
527 },
528 }]
529 _GEO_COUNTRIES = ['IT']
530 _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
531
532 def _get_feed_query(self, uri):
533 return {
534 'arcEp': 'mtv.it',
535 'mgid': uri,
536 }
537
538
539class MTVItaliaProgrammaIE(MTVItaliaIE):
540 IE_NAME = 'mtv.it:programma'
541 _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:programmi|playlist)/(?P<id>[0-9a-z]+)'
542 _TESTS = [{
543 # program page: general
544 'url': 'http://www.mtv.it/programmi/s2rppv/mario-una-serie-di-maccio-capatonda',
545 'info_dict': {
546 'id': 'a6f155bc-8220-4640-aa43-9b95f64ffa3d',
547 'title': 'Mario - Una Serie Di Maccio Capatonda',
548 'description': 'md5:72fbffe1f77ccf4e90757dd4e3216153',
549 },
550 'playlist_count': 2,
551 'params': {
552 'skip_download': True,
553 },
554 }, {
555 # program page: specific season
556 'url': 'http://www.mtv.it/programmi/d9ncjf/mario-una-serie-di-maccio-capatonda-S2',
557 'info_dict': {
558 'id': '4deeb5d8-f272-490c-bde2-ff8d261c6dd1',
559 'title': 'Mario - Una Serie Di Maccio Capatonda - Stagione 2',
560 },
561 'playlist_count': 34,
562 'params': {
563 'skip_download': True,
564 },
565 }, {
566 # playlist page + redirect
567 'url': 'http://www.mtv.it/playlist/sexy-videos/ilctal',
568 'info_dict': {
569 'id': 'dee8f9ee-756d-493b-bf37-16d1d2783359',
570 'title': 'Sexy Videos',
571 },
572 'playlist_mincount': 145,
573 'params': {
574 'skip_download': True,
575 },
576 }]
577 _GEO_COUNTRIES = ['IT']
578 _FEED_URL = 'http://www.mtv.it/feeds/triforce/manifest/v8'
579
580 def _get_entries(self, title, url):
581 while True:
582 pg = self._search_regex(r'/(\d+)$', url, 'entries', '1')
583 entries = self._download_json(url, title, 'page %s' % pg)
584 url = try_get(
585 entries, lambda x: x['result']['nextPageURL'], compat_str)
586 entries = try_get(
587 entries, (
588 lambda x: x['result']['data']['items'],
589 lambda x: x['result']['data']['seasons']),
590 list)
591 for entry in entries or []:
592 if entry.get('canonicalURL'):
593 yield self.url_result(entry['canonicalURL'])
594 if not url:
595 break
596
597 def _real_extract(self, url):
598 query = {'url': url}
599 info_url = update_url_query(self._FEED_URL, query)
600 video_id = self._match_id(url)
601 info = self._download_json(info_url, video_id).get('manifest')
602
603 redirect = try_get(
604 info, lambda x: x['newLocation']['url'], compat_str)
605 if redirect:
606 return self.url_result(redirect)
607
608 title = info.get('title')
609 video_id = try_get(
610 info, lambda x: x['reporting']['itemId'], compat_str)
611 parent_id = try_get(
612 info, lambda x: x['reporting']['parentId'], compat_str)
613
614 playlist_url = current_url = None
615 for z in (info.get('zones') or {}).values():
616 if z.get('moduleName') in ('INTL_M304', 'INTL_M209'):
617 info_url = z.get('feed')
618 if z.get('moduleName') in ('INTL_M308', 'INTL_M317'):
619 playlist_url = playlist_url or z.get('feed')
620 if z.get('moduleName') in ('INTL_M300',):
621 current_url = current_url or z.get('feed')
622
623 if not info_url:
624 raise ExtractorError('No info found')
625
626 if video_id == parent_id:
627 video_id = self._search_regex(
628 r'([^\/]+)/[^\/]+$', info_url, 'video_id')
629
630 info = self._download_json(info_url, video_id, 'Show infos')
631 info = try_get(info, lambda x: x['result']['data'], dict)
632 title = title or try_get(
633 info, (
634 lambda x: x['title'],
635 lambda x: x['headline']),
636 compat_str)
637 description = try_get(info, lambda x: x['content'], compat_str)
638
639 if current_url:
640 season = try_get(
641 self._download_json(playlist_url, video_id, 'Seasons info'),
642 lambda x: x['result']['data'], dict)
643 current = try_get(
644 season, lambda x: x['currentSeason'], compat_str)
645 seasons = try_get(
646 season, lambda x: x['seasons'], list) or []
647
648 if current in [s.get('eTitle') for s in seasons]:
649 playlist_url = current_url
650
651 title = re.sub(
652 r'[-|]\s*(?:mtv\s*italia|programma|playlist)',
653 '', title, flags=re.IGNORECASE).strip()
654
655 return self.playlist_result(
656 self._get_entries(title, playlist_url),
657 video_id, title, description)