]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/mtv.py
[southpark] Fix SouthParkDE (#812)
[yt-dlp.git] / yt_dlp / extractor / mtv.py
CommitLineData
3cdcebf5 1# coding: utf-8
32dac694
PH
2from __future__ import unicode_literals
3
fc287219 4import re
fc287219 5
0af25f78 6from .common import InfoExtractor
1cc79574 7from ..compat import (
e525d9a3 8 compat_str,
20a6a154 9 compat_xpath,
1cc79574
PH
10)
11from ..utils import (
fc287219 12 ExtractorError,
90834c78 13 find_xpath_attr,
5aafe895 14 fix_xml_ampersands,
8765151c 15 float_or_none,
0ef68e04 16 HEADRequest,
605b684c 17 int_or_none,
0c75abbb 18 RegexNotFoundError,
5c2266df 19 sanitized_Request,
7cdfc4c9 20 strip_or_none,
712c7530 21 timeconvert,
adf063da 22 try_get,
340b0468 23 unescapeHTML,
0c75abbb 24 update_url_query,
8d9453b9 25 url_basename,
5767b4ee 26 xpath_text,
fc287219
PH
27)
28
90834c78 29
300fcad8
JMF
30def _media_xml_tag(tag):
31 return '{http://search.yahoo.com/mrss/}%s' % tag
fc287219 32
f7e02595 33
0af25f78 34class MTVServicesInfoExtractor(InfoExtractor):
340b0468 35 _MOBILE_TEMPLATE = None
a542e372 36 _LANG = None
8940c1c0 37
f7e02595
JMF
38 @staticmethod
39 def _id_from_uri(uri):
40 return uri.split(':')[-1]
41
0c75abbb
YCH
42 @staticmethod
43 def _remove_template_parameter(url):
44 # Remove the templates, like &device={device}
45 return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
46
02def271 47 def _get_feed_url(self, uri, url=None):
8940c1c0
JMF
48 return self._FEED_URL
49
ab2f744b 50 def _get_thumbnail_url(self, uri, itemdoc):
84db8181
JMF
51 search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
52 thumb_node = itemdoc.find(search_path)
53 if thumb_node is None:
54 return None
70bfab0e 55 return thumb_node.get('url') or thumb_node.text or None
f7e02595 56
340b0468
JMF
57 def _extract_mobile_video_formats(self, mtvn_id):
58 webpage_url = self._MOBILE_TEMPLATE % mtvn_id
5c2266df 59 req = sanitized_Request(webpage_url)
340b0468 60 # Otherwise we get a webpage that would execute some javascript
3fcfb8e9 61 req.add_header('User-Agent', 'curl/7')
340b0468 62 webpage = self._download_webpage(req, mtvn_id,
9e1a5b84 63 'Downloading mobile page')
0ef68e04
JMF
64 metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
65 req = HEADRequest(metrics_url)
66 response = self._request_webpage(req, mtvn_id, 'Resolving url')
67 url = response.geturl()
68 # Transform the url to get the best quality:
69 url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
5f6a1245 70 return [{'url': url, 'ext': 'mp4'}]
340b0468 71
dbaf6016 72 def _extract_video_formats(self, mdoc, mtvn_id, video_id):
054d43bb 73 if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None:
340b0468 74 if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
0ef68e04 75 self.to_screen('The normal version is not available from your '
9e1a5b84 76 'country, trying with the mobile version')
340b0468 77 return self._extract_mobile_video_formats(mtvn_id)
cc1db7f9 78 raise ExtractorError('This video is not available from your country.',
9e1a5b84 79 expected=True)
f7e02595 80
f13d0933
PH
81 formats = []
82 for rendition in mdoc.findall('.//rendition'):
20faad74 83 if rendition.get('method') == 'hls':
dbaf6016 84 hls_url = rendition.find('./src').text
cdd11c05 85 formats.extend(self._extract_m3u8_formats(
adf063da 86 hls_url, video_id, ext='mp4', entry_protocol='m3u8_native',
e0f1fb0a 87 m3u8_id='hls', fatal=False))
dbaf6016
PH
88 else:
89 # fms
90 try:
91 _, _, ext = rendition.attrib['type'].partition('/')
92 rtmp_video_url = rendition.find('./src').text
adf063da
S
93 if 'error_not_available.swf' in rtmp_video_url:
94 raise ExtractorError(
95 '%s said: video is not available' % self.IE_NAME,
96 expected=True)
dbaf6016
PH
97 if rtmp_video_url.endswith('siteunavail.png'):
98 continue
dbaf6016 99 formats.extend([{
adf063da
S
100 'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext,
101 'url': rtmp_video_url,
102 'format_id': '-'.join(filter(None, [
103 'rtmp' if rtmp_video_url.startswith('rtmp') else None,
104 rendition.get('bitrate')])),
dbaf6016
PH
105 'width': int(rendition.get('width')),
106 'height': int(rendition.get('height')),
adf063da 107 }])
dbaf6016
PH
108 except (KeyError, TypeError):
109 raise ExtractorError('Invalid rendition field.')
e0f1fb0a
S
110 if formats:
111 self._sort_formats(formats)
f13d0933 112 return formats
f7e02595 113
e525d9a3
S
114 def _extract_subtitles(self, mdoc, mtvn_id):
115 subtitles = {}
e525d9a3
S
116 for transcript in mdoc.findall('.//transcript'):
117 if transcript.get('kind') != 'captions':
118 continue
119 lang = transcript.get('srclang')
5ea765fb
RA
120 for typographic in transcript.findall('./typographic'):
121 sub_src = typographic.get('src')
122 if not sub_src:
123 continue
124 ext = typographic.get('format')
125 if ext == 'cea-608':
126 ext = 'scc'
127 subtitles.setdefault(lang, []).append({
128 'url': compat_str(sub_src),
129 'ext': ext
130 })
0af25f78 131 return subtitles
e525d9a3 132
67fc365b 133 def _get_video_info(self, itemdoc, use_hls=True):
f7e02595
JMF
134 uri = itemdoc.find('guid').text
135 video_id = self._id_from_uri(uri)
136 self.report_extraction(video_id)
04cbc498 137 content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content')))
0c75abbb 138 mediagen_url = self._remove_template_parameter(content_el.attrib['url'])
dbaf6016 139 mediagen_url = mediagen_url.replace('device={device}', '')
f7e02595 140 if 'acceptMethods' not in mediagen_url:
56f447be 141 mediagen_url += '&' if '?' in mediagen_url else '?'
dbaf6016
PH
142 mediagen_url += 'acceptMethods='
143 mediagen_url += 'hls' if use_hls else 'fms'
6562df76 144
e0f1fb0a
S
145 mediagen_doc = self._download_xml(
146 mediagen_url, video_id, 'Downloading video urls', fatal=False)
147
148 if mediagen_doc is False:
149 return None
f7e02595 150
0dfe9bc9
S
151 item = mediagen_doc.find('./video/item')
152 if item is not None and item.get('type') == 'text':
153 message = '%s returned error: ' % self.IE_NAME
154 if item.get('code') is not None:
155 message += '%s - ' % item.get('code')
156 message += item.text
157 raise ExtractorError(message, expected=True)
158
7cdfc4c9 159 description = strip_or_none(xpath_text(itemdoc, 'description'))
f13d0933 160
712c7530
YCH
161 timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
162
90834c78
PH
163 title_el = None
164 if title_el is None:
165 title_el = find_xpath_attr(
166 itemdoc, './/{http://search.yahoo.com/mrss/}category',
167 'scheme', 'urn:mtvn:video_title')
90834c78 168 if title_el is None:
20a6a154 169 title_el = itemdoc.find(compat_xpath('.//{http://search.yahoo.com/mrss/}title'))
96cb10a5 170 if title_el is None:
20a6a154 171 title_el = itemdoc.find(compat_xpath('.//title'))
1df4229b
PH
172 if title_el.text is None:
173 title_el = None
1df4229b 174
90834c78
PH
175 title = title_el.text
176 if title is None:
177 raise ExtractorError('Could not find video title')
780ee4e5 178 title = title.strip()
90834c78 179
605b684c 180 series = find_xpath_attr(
181 itemdoc, './/{http://search.yahoo.com/mrss/}category',
182 'scheme', 'urn:mtvn:franchise')
183 season = find_xpath_attr(
184 itemdoc, './/{http://search.yahoo.com/mrss/}category',
185 'scheme', 'urn:mtvn:seasonN')
186 episode = find_xpath_attr(
187 itemdoc, './/{http://search.yahoo.com/mrss/}category',
188 'scheme', 'urn:mtvn:episodeN')
189 series = series.text if series is not None else None
190 season = season.text if season is not None else None
191 episode = episode.text if episode is not None else None
192 if season and episode:
193 # episode number includes season, so remove it
194 episode = re.sub(r'^%s' % season, '', episode)
195
340b0468
JMF
196 # This a short id that's used in the webpage urls
197 mtvn_id = None
198 mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
9e1a5b84 199 'scheme', 'urn:mtvn:id')
340b0468
JMF
200 if mtvn_id_node is not None:
201 mtvn_id = mtvn_id_node.text
202
dbaf6016
PH
203 formats = self._extract_video_formats(mediagen_doc, mtvn_id, video_id)
204
e0f1fb0a
S
205 # Some parts of complete video may be missing (e.g. missing Act 3 in
206 # http://www.southpark.de/alle-episoden/s14e01-sexual-healing)
207 if not formats:
208 return None
209
210 self._sort_formats(formats)
211
fb7abb31 212 return {
90834c78 213 'title': title,
dbaf6016 214 'formats': formats,
e525d9a3 215 'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
f13d0933
PH
216 'id': video_id,
217 'thumbnail': self._get_thumbnail_url(uri, itemdoc),
218 'description': description,
04cbc498 219 'duration': float_or_none(content_el.attrib.get('duration')),
712c7530 220 'timestamp': timestamp,
605b684c 221 'series': series,
222 'season_number': int_or_none(season),
223 'episode_number': int_or_none(episode),
f13d0933
PH
224 }
225
c1e90619 226 def _get_feed_query(self, uri):
227 data = {'uri': uri}
228 if self._LANG:
229 data['lang'] = self._LANG
0c75abbb 230 return data
c1e90619 231
02def271 232 def _get_videos_info(self, uri, use_hls=True, url=None):
f7e02595 233 video_id = self._id_from_uri(uri)
02def271 234 feed_url = self._get_feed_url(uri, url)
0c75abbb 235 info_url = update_url_query(feed_url, self._get_feed_query(uri))
dbaf6016 236 return self._get_videos_info_from_url(info_url, video_id, use_hls)
79fa9db0 237
67fc365b 238 def _get_videos_info_from_url(self, url, video_id, use_hls=True):
e2b38da9 239 idoc = self._download_xml(
79fa9db0 240 url, video_id,
32dac694 241 'Downloading info', transform_source=fix_xml_ampersands)
712c7530
YCH
242
243 title = xpath_text(idoc, './channel/title')
244 description = xpath_text(idoc, './channel/description')
245
e0f1fb0a
S
246 entries = []
247 for item in idoc.findall('.//item'):
248 info = self._get_video_info(item, use_hls)
249 if info:
250 entries.append(info)
251
bc97cdae 252 # TODO: should be multi-video
5239075b 253 return self.playlist_result(
e0f1fb0a 254 entries, playlist_title=title, playlist_description=description)
fc287219 255
adf063da
S
256 def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None):
257 triforce_feed = self._parse_json(self._search_regex(
f1e70fc2 258 r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage,
adf063da
S
259 'triforce feed', default='{}'), video_id, fatal=False)
260
261 data_zone = self._search_regex(
262 r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage,
263 'data zone', default=data_zone, group='zone')
264
265 feed_url = try_get(
266 triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'],
267 compat_str)
268 if not feed_url:
269 return
270
271 feed = self._download_json(feed_url, video_id, fatal=False)
272 if not feed:
273 return
274
275 return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
276
a820dc72
RA
277 @staticmethod
278 def _extract_child_with_type(parent, t):
f7ad7160 279 for c in parent['children']:
280 if c.get('type') == t:
281 return c
a820dc72 282
ee1e0558 283 def _extract_mgid(self, webpage):
8d9453b9 284 try:
4bbf139a
JMF
285 # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
286 # or http://media.mtvnservices.com/{mgid}
287 og_url = self._og_search_video_url(webpage)
288 mgid = url_basename(og_url)
289 if mgid.endswith('.swf'):
290 mgid = mgid[:-4]
8d9453b9 291 except RegexNotFoundError:
b1298d8e
AMW
292 mgid = None
293
294 if mgid is None or ':' not in mgid:
b9381e43 295 mgid = self._search_regex(
197224b7 296 [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
fc42bc6e
S
297 webpage, 'mgid', default=None)
298
299 if not mgid:
300 sm4_embed = self._html_search_meta(
301 'sm4:video:embed', webpage, 'sm4 embed', default='')
302 mgid = self._search_regex(
adf063da
S
303 r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
304
b6e0c7d2 305 if not mgid:
ee1e0558 306 mgid = self._extract_triforce_mgid(webpage)
adf063da 307
a820dc72
RA
308 if not mgid:
309 data = self._parse_json(self._search_regex(
310 r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
311 main_container = self._extract_child_with_type(data, 'MainContainer')
f7ad7160 312 ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
313 video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
a820dc72
RA
314 mgid = video_player['props']['media']['video']['config']['uri']
315
54153fb7
S
316 if not mgid:
317 mgid = self._search_regex(
318 r'"media":{"video":{"config":{"uri":"(mgid:.*?)"', webpage, 'mgid', default=None)
319
c1e90619 320 return mgid
e525d9a3 321
c1e90619 322 def _real_extract(self, url):
323 title = url_basename(url)
324 webpage = self._download_webpage(url, title)
ee1e0558 325 mgid = self._extract_mgid(webpage)
02def271 326 videos_info = self._get_videos_info(mgid, url=url)
e525d9a3 327 return videos_info
8d9453b9 328
84db8181 329
8940c1c0
JMF
330class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
331 IE_NAME = 'mtvservices:embedded'
332 _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
333
334 _TEST = {
335 # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
336 'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
337 'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
338 'info_dict': {
339 'id': '1043906',
340 'ext': 'mp4',
341 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
342 '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
343 'timestamp': 1400126400,
344 'upload_date': '20140515',
8940c1c0
JMF
345 },
346 }
347
fe1d858e
S
348 @staticmethod
349 def _extract_url(webpage):
350 mobj = re.search(
1418a043 351 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1', webpage)
fe1d858e
S
352 if mobj:
353 return mobj.group('url')
354
02def271 355 def _get_feed_url(self, uri, url=None):
8940c1c0 356 video_id = self._id_from_uri(uri)
0c75abbb
YCH
357 config = self._download_json(
358 'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id)
359 return self._remove_template_parameter(config['feedWithQueryParams'])
8940c1c0
JMF
360
361 def _real_extract(self, url):
5ad28e7f 362 mobj = self._match_valid_url(url)
8940c1c0
JMF
363 mgid = mobj.group('mgid')
364 return self._get_videos_info(mgid)
365
366
84db8181 367class MTVIE(MTVServicesInfoExtractor):
a54ffb8a 368 IE_NAME = 'mtv'
cf0cabbe 369 _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
8add4bfe
RA
370 _FEED_URL = 'http://www.mtv.com/feeds/mrss/'
371
372 _TESTS = [{
373 'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer',
374 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
375 'info_dict': {
376 'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
377 'ext': 'mp4',
378 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
379 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
380 'timestamp': 1468846800,
381 'upload_date': '20160718',
382 },
383 }, {
384 'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101',
385 'only_matching': True,
cf0cabbe
S
386 }, {
387 'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713',
388 'only_matching': True,
8add4bfe
RA
389 }]
390
391
3cdcebf5
RA
392class MTVJapanIE(MTVServicesInfoExtractor):
393 IE_NAME = 'mtvjapan'
394 _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)'
008f2470
S
395
396 _TEST = {
3cdcebf5 397 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade',
008f2470 398 'info_dict': {
3cdcebf5 399 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5',
008f2470 400 'ext': 'mp4',
3cdcebf5
RA
401 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition',
402 },
403 'params': {
404 'skip_download': True,
008f2470
S
405 },
406 }
3cdcebf5
RA
407 _GEO_COUNTRIES = ['JP']
408 _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
008f2470 409
3cdcebf5
RA
410 def _get_feed_query(self, uri):
411 return {
412 'arcEp': 'mtvjapan.com',
413 'mgid': uri,
414 }
008f2470
S
415
416
8add4bfe 417class MTVVideoIE(MTVServicesInfoExtractor):
a54ffb8a 418 IE_NAME = 'mtv:video'
5c541b2c
JMF
419 _VALID_URL = r'''(?x)^https?://
420 (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
421 m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''
84db8181
JMF
422
423 _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
424
425 _TESTS = [
426 {
32dac694 427 'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
32dac694
PH
428 'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
429 'info_dict': {
ca0f500e
PH
430 'id': '853555',
431 'ext': 'mp4',
32dac694
PH
432 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
433 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
712c7530
YCH
434 'timestamp': 1352610000,
435 'upload_date': '20121111',
84db8181
JMF
436 },
437 },
84db8181
JMF
438 ]
439
440 def _get_thumbnail_url(self, uri, itemdoc):
441 return 'http://mtv.mtvnimages.com/uri/' + uri
442
fc287219 443 def _real_extract(self, url):
5ad28e7f 444 mobj = self._match_valid_url(url)
fc287219 445 video_id = mobj.group('videoid')
c801b205 446 uri = mobj.groupdict().get('mgid')
5c541b2c
JMF
447 if uri is None:
448 webpage = self._download_webpage(url, video_id)
5f6a1245 449
5c541b2c 450 # Some videos come from Vevo.com
ca0f500e
PH
451 m_vevo = re.search(
452 r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
5c541b2c 453 if m_vevo:
8bcc8756 454 vevo_id = m_vevo.group(1)
32dac694 455 self.to_screen('Vevo video detected: %s' % vevo_id)
5c541b2c 456 return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
5f6a1245 457
32dac694 458 uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri')
f7e02595 459 return self._get_videos_info(uri)
bc4ba05f
JMF
460
461
071c1013
PH
462class MTVDEIE(MTVServicesInfoExtractor):
463 IE_NAME = 'mtv.de'
cfabc505 464 _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)'
79fa9db0 465 _TESTS = [{
cfabc505 466 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum',
79fa9db0 467 'info_dict': {
cfabc505
RA
468 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5',
469 'ext': 'mp4',
470 'title': 'Traum',
471 'description': 'Traum',
071c1013 472 },
79fa9db0
S
473 'params': {
474 # rtmp download
475 'skip_download': True,
476 },
35f6e0ff 477 'skip': 'Blocked at Travis CI',
c3c9f879
S
478 }, {
479 # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
cfabc505 480 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1',
c3c9f879 481 'info_dict': {
cfabc505
RA
482 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285',
483 'ext': 'mp4',
484 'title': 'Teen Mom 2',
485 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7',
c3c9f879
S
486 },
487 'params': {
488 # rtmp download
489 'skip_download': True,
490 },
35f6e0ff 491 'skip': 'Blocked at Travis CI',
65488b82 492 }, {
cfabc505 493 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3',
65488b82
S
494 'info_dict': {
495 'id': 'local_playlist-4e760566473c4c8c5344',
496 'ext': 'mp4',
497 'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1',
498 'description': 'MTV Movies Supercut',
499 },
500 'params': {
501 # rtmp download
502 'skip_download': True,
503 },
712c7530 504 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
79fa9db0 505 }]
cfabc505
RA
506 _GEO_COUNTRIES = ['DE']
507 _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
071c1013 508
cfabc505
RA
509 def _get_feed_query(self, uri):
510 return {
511 'arcEp': 'mtv.de',
512 'mgid': uri,
513 }
605b684c 514
515
516class MTVItaliaIE(MTVServicesInfoExtractor):
517 IE_NAME = 'mtv.it'
518 _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:episodi|video|musica)/(?P<id>[0-9a-z]+)'
519 _TESTS = [{
520 'url': 'http://www.mtv.it/episodi/24bqab/mario-una-serie-di-maccio-capatonda-cavoli-amario-episodio-completo-S1-E1',
521 'info_dict': {
522 'id': '0f0fc78e-45fc-4cce-8f24-971c25477530',
523 'ext': 'mp4',
524 'title': 'Cavoli amario (episodio completo)',
525 'description': 'md5:4962bccea8fed5b7c03b295ae1340660',
526 'series': 'Mario - Una Serie Di Maccio Capatonda',
527 'season_number': 1,
528 'episode_number': 1,
529 },
530 'params': {
531 'skip_download': True,
532 },
533 }]
534 _GEO_COUNTRIES = ['IT']
535 _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
536
537 def _get_feed_query(self, uri):
538 return {
539 'arcEp': 'mtv.it',
540 'mgid': uri,
541 }
542
543
544class MTVItaliaProgrammaIE(MTVItaliaIE):
545 IE_NAME = 'mtv.it:programma'
546 _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:programmi|playlist)/(?P<id>[0-9a-z]+)'
547 _TESTS = [{
548 # program page: general
549 'url': 'http://www.mtv.it/programmi/s2rppv/mario-una-serie-di-maccio-capatonda',
550 'info_dict': {
551 'id': 'a6f155bc-8220-4640-aa43-9b95f64ffa3d',
552 'title': 'Mario - Una Serie Di Maccio Capatonda',
553 'description': 'md5:72fbffe1f77ccf4e90757dd4e3216153',
554 },
555 'playlist_count': 2,
556 'params': {
557 'skip_download': True,
558 },
559 }, {
560 # program page: specific season
561 'url': 'http://www.mtv.it/programmi/d9ncjf/mario-una-serie-di-maccio-capatonda-S2',
562 'info_dict': {
563 'id': '4deeb5d8-f272-490c-bde2-ff8d261c6dd1',
564 'title': 'Mario - Una Serie Di Maccio Capatonda - Stagione 2',
565 },
566 'playlist_count': 34,
567 'params': {
568 'skip_download': True,
569 },
570 }, {
571 # playlist page + redirect
572 'url': 'http://www.mtv.it/playlist/sexy-videos/ilctal',
573 'info_dict': {
574 'id': 'dee8f9ee-756d-493b-bf37-16d1d2783359',
575 'title': 'Sexy Videos',
576 },
577 'playlist_mincount': 145,
578 'params': {
579 'skip_download': True,
580 },
581 }]
582 _GEO_COUNTRIES = ['IT']
583 _FEED_URL = 'http://www.mtv.it/feeds/triforce/manifest/v8'
584
585 def _get_entries(self, title, url):
586 while True:
587 pg = self._search_regex(r'/(\d+)$', url, 'entries', '1')
588 entries = self._download_json(url, title, 'page %s' % pg)
589 url = try_get(
590 entries, lambda x: x['result']['nextPageURL'], compat_str)
591 entries = try_get(
592 entries, (
593 lambda x: x['result']['data']['items'],
594 lambda x: x['result']['data']['seasons']),
595 list)
596 for entry in entries or []:
597 if entry.get('canonicalURL'):
598 yield self.url_result(entry['canonicalURL'])
599 if not url:
600 break
601
602 def _real_extract(self, url):
603 query = {'url': url}
604 info_url = update_url_query(self._FEED_URL, query)
605 video_id = self._match_id(url)
606 info = self._download_json(info_url, video_id).get('manifest')
607
608 redirect = try_get(
609 info, lambda x: x['newLocation']['url'], compat_str)
610 if redirect:
611 return self.url_result(redirect)
612
613 title = info.get('title')
614 video_id = try_get(
615 info, lambda x: x['reporting']['itemId'], compat_str)
616 parent_id = try_get(
617 info, lambda x: x['reporting']['parentId'], compat_str)
618
619 playlist_url = current_url = None
620 for z in (info.get('zones') or {}).values():
621 if z.get('moduleName') in ('INTL_M304', 'INTL_M209'):
622 info_url = z.get('feed')
623 if z.get('moduleName') in ('INTL_M308', 'INTL_M317'):
624 playlist_url = playlist_url or z.get('feed')
625 if z.get('moduleName') in ('INTL_M300',):
626 current_url = current_url or z.get('feed')
627
628 if not info_url:
629 raise ExtractorError('No info found')
630
631 if video_id == parent_id:
632 video_id = self._search_regex(
633 r'([^\/]+)/[^\/]+$', info_url, 'video_id')
634
635 info = self._download_json(info_url, video_id, 'Show infos')
636 info = try_get(info, lambda x: x['result']['data'], dict)
637 title = title or try_get(
638 info, (
639 lambda x: x['title'],
640 lambda x: x['headline']),
641 compat_str)
642 description = try_get(info, lambda x: x['content'], compat_str)
643
644 if current_url:
645 season = try_get(
646 self._download_json(playlist_url, video_id, 'Seasons info'),
647 lambda x: x['result']['data'], dict)
648 current = try_get(
649 season, lambda x: x['currentSeason'], compat_str)
650 seasons = try_get(
651 season, lambda x: x['seasons'], list) or []
652
653 if current in [s.get('eTitle') for s in seasons]:
654 playlist_url = current_url
655
656 title = re.sub(
657 r'[-|]\s*(?:mtv\s*italia|programma|playlist)',
658 '', title, flags=re.IGNORECASE).strip()
659
660 return self.playlist_result(
661 self._get_entries(title, playlist_url),
662 video_id, title, description)