]>
Commit | Line | Data |
---|---|---|
3cdcebf5 | 1 | # coding: utf-8 |
32dac694 PH |
2 | from __future__ import unicode_literals |
3 | ||
fc287219 | 4 | import re |
fc287219 | 5 | |
0af25f78 | 6 | from .common import InfoExtractor |
1cc79574 | 7 | from ..compat import ( |
e525d9a3 | 8 | compat_str, |
20a6a154 | 9 | compat_xpath, |
1cc79574 PH |
10 | ) |
11 | from ..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, |
34921b43 | 18 | join_nonempty, |
0c75abbb | 19 | RegexNotFoundError, |
5c2266df | 20 | sanitized_Request, |
7cdfc4c9 | 21 | strip_or_none, |
712c7530 | 22 | timeconvert, |
adf063da | 23 | try_get, |
340b0468 | 24 | unescapeHTML, |
0c75abbb | 25 | update_url_query, |
8d9453b9 | 26 | url_basename, |
5767b4ee | 27 | xpath_text, |
fc287219 PH |
28 | ) |
29 | ||
90834c78 | 30 | |
300fcad8 JMF |
31 | def _media_xml_tag(tag): |
32 | return '{http://search.yahoo.com/mrss/}%s' % tag | |
fc287219 | 33 | |
f7e02595 | 34 | |
0af25f78 | 35 | class MTVServicesInfoExtractor(InfoExtractor): |
340b0468 | 36 | _MOBILE_TEMPLATE = None |
a542e372 | 37 | _LANG = None |
8940c1c0 | 38 | |
f7e02595 JMF |
39 | @staticmethod |
40 | def _id_from_uri(uri): | |
41 | return uri.split(':')[-1] | |
42 | ||
0c75abbb YCH |
43 | @staticmethod |
44 | def _remove_template_parameter(url): | |
45 | # Remove the templates, like &device={device} | |
46 | return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url) | |
47 | ||
02def271 | 48 | def _get_feed_url(self, uri, url=None): |
8940c1c0 JMF |
49 | return self._FEED_URL |
50 | ||
ab2f744b | 51 | def _get_thumbnail_url(self, uri, itemdoc): |
84db8181 JMF |
52 | search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) |
53 | thumb_node = itemdoc.find(search_path) | |
54 | if thumb_node is None: | |
55 | return None | |
70bfab0e | 56 | return thumb_node.get('url') or thumb_node.text or None |
f7e02595 | 57 | |
340b0468 JMF |
58 | def _extract_mobile_video_formats(self, mtvn_id): |
59 | webpage_url = self._MOBILE_TEMPLATE % mtvn_id | |
5c2266df | 60 | req = sanitized_Request(webpage_url) |
340b0468 | 61 | # Otherwise we get a webpage that would execute some javascript |
3fcfb8e9 | 62 | req.add_header('User-Agent', 'curl/7') |
340b0468 | 63 | webpage = self._download_webpage(req, mtvn_id, |
9e1a5b84 | 64 | 'Downloading mobile page') |
0ef68e04 JMF |
65 | metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url')) |
66 | req = HEADRequest(metrics_url) | |
67 | response = self._request_webpage(req, mtvn_id, 'Resolving url') | |
68 | url = response.geturl() | |
69 | # Transform the url to get the best quality: | |
70 | url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1) | |
5f6a1245 | 71 | return [{'url': url, 'ext': 'mp4'}] |
340b0468 | 72 | |
dbaf6016 | 73 | def _extract_video_formats(self, mdoc, mtvn_id, video_id): |
054d43bb | 74 | if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None: |
340b0468 | 75 | if mtvn_id is not None and self._MOBILE_TEMPLATE is not None: |
0ef68e04 | 76 | self.to_screen('The normal version is not available from your ' |
9e1a5b84 | 77 | 'country, trying with the mobile version') |
340b0468 | 78 | return self._extract_mobile_video_formats(mtvn_id) |
cc1db7f9 | 79 | raise ExtractorError('This video is not available from your country.', |
9e1a5b84 | 80 | expected=True) |
f7e02595 | 81 | |
f13d0933 PH |
82 | formats = [] |
83 | for rendition in mdoc.findall('.//rendition'): | |
20faad74 | 84 | if rendition.get('method') == 'hls': |
dbaf6016 | 85 | hls_url = rendition.find('./src').text |
cdd11c05 | 86 | formats.extend(self._extract_m3u8_formats( |
adf063da | 87 | hls_url, video_id, ext='mp4', entry_protocol='m3u8_native', |
e0f1fb0a | 88 | m3u8_id='hls', fatal=False)) |
dbaf6016 PH |
89 | else: |
90 | # fms | |
91 | try: | |
92 | _, _, ext = rendition.attrib['type'].partition('/') | |
93 | rtmp_video_url = rendition.find('./src').text | |
adf063da S |
94 | if 'error_not_available.swf' in rtmp_video_url: |
95 | raise ExtractorError( | |
96 | '%s said: video is not available' % self.IE_NAME, | |
97 | expected=True) | |
dbaf6016 PH |
98 | if rtmp_video_url.endswith('siteunavail.png'): |
99 | continue | |
dbaf6016 | 100 | formats.extend([{ |
adf063da S |
101 | 'ext': 'flv' if rtmp_video_url.startswith('rtmp') else ext, |
102 | 'url': rtmp_video_url, | |
34921b43 | 103 | 'format_id': join_nonempty( |
adf063da | 104 | 'rtmp' if rtmp_video_url.startswith('rtmp') else None, |
34921b43 | 105 | rendition.get('bitrate')), |
dbaf6016 PH |
106 | 'width': int(rendition.get('width')), |
107 | 'height': int(rendition.get('height')), | |
adf063da | 108 | }]) |
dbaf6016 PH |
109 | except (KeyError, TypeError): |
110 | raise ExtractorError('Invalid rendition field.') | |
e0f1fb0a S |
111 | if formats: |
112 | self._sort_formats(formats) | |
f13d0933 | 113 | return formats |
f7e02595 | 114 | |
e525d9a3 S |
115 | def _extract_subtitles(self, mdoc, mtvn_id): |
116 | subtitles = {} | |
e525d9a3 S |
117 | for transcript in mdoc.findall('.//transcript'): |
118 | if transcript.get('kind') != 'captions': | |
119 | continue | |
120 | lang = transcript.get('srclang') | |
5ea765fb RA |
121 | for typographic in transcript.findall('./typographic'): |
122 | sub_src = typographic.get('src') | |
123 | if not sub_src: | |
124 | continue | |
125 | ext = typographic.get('format') | |
126 | if ext == 'cea-608': | |
127 | ext = 'scc' | |
128 | subtitles.setdefault(lang, []).append({ | |
129 | 'url': compat_str(sub_src), | |
130 | 'ext': ext | |
131 | }) | |
0af25f78 | 132 | return subtitles |
e525d9a3 | 133 | |
67fc365b | 134 | def _get_video_info(self, itemdoc, use_hls=True): |
f7e02595 JMF |
135 | uri = itemdoc.find('guid').text |
136 | video_id = self._id_from_uri(uri) | |
137 | self.report_extraction(video_id) | |
04cbc498 | 138 | content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))) |
0c75abbb | 139 | mediagen_url = self._remove_template_parameter(content_el.attrib['url']) |
dbaf6016 | 140 | mediagen_url = mediagen_url.replace('device={device}', '') |
f7e02595 | 141 | if 'acceptMethods' not in mediagen_url: |
56f447be | 142 | mediagen_url += '&' if '?' in mediagen_url else '?' |
dbaf6016 PH |
143 | mediagen_url += 'acceptMethods=' |
144 | mediagen_url += 'hls' if use_hls else 'fms' | |
6562df76 | 145 | |
e0f1fb0a S |
146 | mediagen_doc = self._download_xml( |
147 | mediagen_url, video_id, 'Downloading video urls', fatal=False) | |
148 | ||
149 | if mediagen_doc is False: | |
150 | return None | |
f7e02595 | 151 | |
0dfe9bc9 S |
152 | item = mediagen_doc.find('./video/item') |
153 | if item is not None and item.get('type') == 'text': | |
154 | message = '%s returned error: ' % self.IE_NAME | |
155 | if item.get('code') is not None: | |
156 | message += '%s - ' % item.get('code') | |
157 | message += item.text | |
158 | raise ExtractorError(message, expected=True) | |
159 | ||
7cdfc4c9 | 160 | description = strip_or_none(xpath_text(itemdoc, 'description')) |
f13d0933 | 161 | |
712c7530 YCH |
162 | timestamp = timeconvert(xpath_text(itemdoc, 'pubDate')) |
163 | ||
90834c78 PH |
164 | title_el = None |
165 | if title_el is None: | |
166 | title_el = find_xpath_attr( | |
167 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
168 | 'scheme', 'urn:mtvn:video_title') | |
90834c78 | 169 | if title_el is None: |
20a6a154 | 170 | title_el = itemdoc.find(compat_xpath('.//{http://search.yahoo.com/mrss/}title')) |
96cb10a5 | 171 | if title_el is None: |
20a6a154 | 172 | title_el = itemdoc.find(compat_xpath('.//title')) |
1df4229b PH |
173 | if title_el.text is None: |
174 | title_el = None | |
1df4229b | 175 | |
90834c78 PH |
176 | title = title_el.text |
177 | if title is None: | |
178 | raise ExtractorError('Could not find video title') | |
780ee4e5 | 179 | title = title.strip() |
90834c78 | 180 | |
605b684c | 181 | series = find_xpath_attr( |
182 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
183 | 'scheme', 'urn:mtvn:franchise') | |
184 | season = find_xpath_attr( | |
185 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
186 | 'scheme', 'urn:mtvn:seasonN') | |
187 | episode = find_xpath_attr( | |
188 | itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
189 | 'scheme', 'urn:mtvn:episodeN') | |
190 | series = series.text if series is not None else None | |
191 | season = season.text if season is not None else None | |
192 | episode = episode.text if episode is not None else None | |
193 | if season and episode: | |
194 | # episode number includes season, so remove it | |
195 | episode = re.sub(r'^%s' % season, '', episode) | |
196 | ||
340b0468 JMF |
197 | # This a short id that's used in the webpage urls |
198 | mtvn_id = None | |
199 | mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
9e1a5b84 | 200 | 'scheme', 'urn:mtvn:id') |
340b0468 JMF |
201 | if mtvn_id_node is not None: |
202 | mtvn_id = mtvn_id_node.text | |
203 | ||
dbaf6016 PH |
204 | formats = self._extract_video_formats(mediagen_doc, mtvn_id, video_id) |
205 | ||
e0f1fb0a S |
206 | # Some parts of complete video may be missing (e.g. missing Act 3 in |
207 | # http://www.southpark.de/alle-episoden/s14e01-sexual-healing) | |
208 | if not formats: | |
209 | return None | |
210 | ||
211 | self._sort_formats(formats) | |
212 | ||
fb7abb31 | 213 | return { |
90834c78 | 214 | 'title': title, |
dbaf6016 | 215 | 'formats': formats, |
e525d9a3 | 216 | 'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id), |
f13d0933 PH |
217 | 'id': video_id, |
218 | 'thumbnail': self._get_thumbnail_url(uri, itemdoc), | |
219 | 'description': description, | |
04cbc498 | 220 | 'duration': float_or_none(content_el.attrib.get('duration')), |
712c7530 | 221 | 'timestamp': timestamp, |
605b684c | 222 | 'series': series, |
223 | 'season_number': int_or_none(season), | |
224 | 'episode_number': int_or_none(episode), | |
f13d0933 PH |
225 | } |
226 | ||
c1e90619 | 227 | def _get_feed_query(self, uri): |
228 | data = {'uri': uri} | |
229 | if self._LANG: | |
230 | data['lang'] = self._LANG | |
0c75abbb | 231 | return data |
c1e90619 | 232 | |
02def271 | 233 | def _get_videos_info(self, uri, use_hls=True, url=None): |
f7e02595 | 234 | video_id = self._id_from_uri(uri) |
02def271 | 235 | feed_url = self._get_feed_url(uri, url) |
0c75abbb | 236 | info_url = update_url_query(feed_url, self._get_feed_query(uri)) |
dbaf6016 | 237 | return self._get_videos_info_from_url(info_url, video_id, use_hls) |
79fa9db0 | 238 | |
67fc365b | 239 | def _get_videos_info_from_url(self, url, video_id, use_hls=True): |
e2b38da9 | 240 | idoc = self._download_xml( |
79fa9db0 | 241 | url, video_id, |
32dac694 | 242 | 'Downloading info', transform_source=fix_xml_ampersands) |
712c7530 YCH |
243 | |
244 | title = xpath_text(idoc, './channel/title') | |
245 | description = xpath_text(idoc, './channel/description') | |
246 | ||
e0f1fb0a S |
247 | entries = [] |
248 | for item in idoc.findall('.//item'): | |
249 | info = self._get_video_info(item, use_hls) | |
250 | if info: | |
251 | entries.append(info) | |
252 | ||
bc97cdae | 253 | # TODO: should be multi-video |
5239075b | 254 | return self.playlist_result( |
e0f1fb0a | 255 | entries, playlist_title=title, playlist_description=description) |
fc287219 | 256 | |
adf063da S |
257 | def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None): |
258 | triforce_feed = self._parse_json(self._search_regex( | |
f1e70fc2 | 259 | r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage, |
adf063da S |
260 | 'triforce feed', default='{}'), video_id, fatal=False) |
261 | ||
262 | data_zone = self._search_regex( | |
263 | r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage, | |
264 | 'data zone', default=data_zone, group='zone') | |
265 | ||
266 | feed_url = try_get( | |
267 | triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'], | |
268 | compat_str) | |
269 | if not feed_url: | |
270 | return | |
271 | ||
272 | feed = self._download_json(feed_url, video_id, fatal=False) | |
273 | if not feed: | |
274 | return | |
275 | ||
276 | return try_get(feed, lambda x: x['result']['data']['id'], compat_str) | |
277 | ||
a820dc72 RA |
278 | @staticmethod |
279 | def _extract_child_with_type(parent, t): | |
f7ad7160 | 280 | for c in parent['children']: |
281 | if c.get('type') == t: | |
282 | return c | |
a820dc72 | 283 | |
ee1e0558 | 284 | def _extract_mgid(self, webpage): |
8d9453b9 | 285 | try: |
4bbf139a JMF |
286 | # the url can be http://media.mtvnservices.com/fb/{mgid}.swf |
287 | # or http://media.mtvnservices.com/{mgid} | |
288 | og_url = self._og_search_video_url(webpage) | |
289 | mgid = url_basename(og_url) | |
290 | if mgid.endswith('.swf'): | |
291 | mgid = mgid[:-4] | |
8d9453b9 | 292 | except RegexNotFoundError: |
b1298d8e AMW |
293 | mgid = None |
294 | ||
295 | if mgid is None or ':' not in mgid: | |
b9381e43 | 296 | mgid = self._search_regex( |
197224b7 | 297 | [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'], |
fc42bc6e S |
298 | webpage, 'mgid', default=None) |
299 | ||
300 | if not mgid: | |
301 | sm4_embed = self._html_search_meta( | |
302 | 'sm4:video:embed', webpage, 'sm4 embed', default='') | |
303 | mgid = self._search_regex( | |
adf063da S |
304 | r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None) |
305 | ||
b6e0c7d2 | 306 | if not mgid: |
ee1e0558 | 307 | mgid = self._extract_triforce_mgid(webpage) |
adf063da | 308 | |
a820dc72 RA |
309 | if not mgid: |
310 | data = self._parse_json(self._search_regex( | |
311 | r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None) | |
312 | main_container = self._extract_child_with_type(data, 'MainContainer') | |
f7ad7160 | 313 | ab_testing = self._extract_child_with_type(main_container, 'ABTesting') |
314 | video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer') | |
fec41d17 S |
315 | if video_player: |
316 | mgid = try_get(video_player, lambda x: x['props']['media']['video']['config']['uri']) | |
317 | else: | |
318 | flex_wrapper = self._extract_child_with_type(ab_testing or main_container, 'FlexWrapper') | |
319 | auth_suite_wrapper = self._extract_child_with_type(flex_wrapper, 'AuthSuiteWrapper') | |
320 | player = self._extract_child_with_type(auth_suite_wrapper or flex_wrapper, 'Player') | |
321 | if player: | |
322 | mgid = try_get(player, lambda x: x['props']['videoDetail']['mgid']) | |
323 | ||
324 | if not mgid: | |
325 | raise ExtractorError('Could not extract mgid') | |
a820dc72 | 326 | |
c1e90619 | 327 | return mgid |
e525d9a3 | 328 | |
c1e90619 | 329 | def _real_extract(self, url): |
330 | title = url_basename(url) | |
331 | webpage = self._download_webpage(url, title) | |
ee1e0558 | 332 | mgid = self._extract_mgid(webpage) |
02def271 | 333 | videos_info = self._get_videos_info(mgid, url=url) |
e525d9a3 | 334 | return videos_info |
8d9453b9 | 335 | |
84db8181 | 336 | |
8940c1c0 JMF |
337 | class MTVServicesEmbeddedIE(MTVServicesInfoExtractor): |
338 | IE_NAME = 'mtvservices:embedded' | |
339 | _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)' | |
340 | ||
341 | _TEST = { | |
342 | # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/ | |
343 | 'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906', | |
344 | 'md5': 'cb349b21a7897164cede95bd7bf3fbb9', | |
345 | 'info_dict': { | |
346 | 'id': '1043906', | |
347 | 'ext': 'mp4', | |
348 | 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds', | |
349 | '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 |
350 | 'timestamp': 1400126400, |
351 | 'upload_date': '20140515', | |
8940c1c0 JMF |
352 | }, |
353 | } | |
354 | ||
fe1d858e S |
355 | @staticmethod |
356 | def _extract_url(webpage): | |
357 | mobj = re.search( | |
1418a043 | 358 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1', webpage) |
fe1d858e S |
359 | if mobj: |
360 | return mobj.group('url') | |
361 | ||
02def271 | 362 | def _get_feed_url(self, uri, url=None): |
8940c1c0 | 363 | video_id = self._id_from_uri(uri) |
0c75abbb YCH |
364 | config = self._download_json( |
365 | 'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id) | |
366 | return self._remove_template_parameter(config['feedWithQueryParams']) | |
8940c1c0 JMF |
367 | |
368 | def _real_extract(self, url): | |
5ad28e7f | 369 | mobj = self._match_valid_url(url) |
8940c1c0 JMF |
370 | mgid = mobj.group('mgid') |
371 | return self._get_videos_info(mgid) | |
372 | ||
373 | ||
84db8181 | 374 | class MTVIE(MTVServicesInfoExtractor): |
a54ffb8a | 375 | IE_NAME = 'mtv' |
cf0cabbe | 376 | _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)' |
8add4bfe RA |
377 | _FEED_URL = 'http://www.mtv.com/feeds/mrss/' |
378 | ||
379 | _TESTS = [{ | |
380 | 'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer', | |
381 | 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b', | |
382 | 'info_dict': { | |
383 | 'id': '5e14040d-18a4-47c4-a582-43ff602de88e', | |
384 | 'ext': 'mp4', | |
385 | 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer', | |
386 | 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.', | |
387 | 'timestamp': 1468846800, | |
388 | 'upload_date': '20160718', | |
389 | }, | |
390 | }, { | |
391 | 'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101', | |
392 | 'only_matching': True, | |
cf0cabbe S |
393 | }, { |
394 | 'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713', | |
395 | 'only_matching': True, | |
8add4bfe RA |
396 | }] |
397 | ||
398 | ||
3cdcebf5 RA |
399 | class MTVJapanIE(MTVServicesInfoExtractor): |
400 | IE_NAME = 'mtvjapan' | |
401 | _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)' | |
008f2470 S |
402 | |
403 | _TEST = { | |
3cdcebf5 | 404 | 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade', |
008f2470 | 405 | 'info_dict': { |
3cdcebf5 | 406 | 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5', |
008f2470 | 407 | 'ext': 'mp4', |
3cdcebf5 RA |
408 | 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition', |
409 | }, | |
410 | 'params': { | |
411 | 'skip_download': True, | |
008f2470 S |
412 | }, |
413 | } | |
3cdcebf5 RA |
414 | _GEO_COUNTRIES = ['JP'] |
415 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
008f2470 | 416 | |
3cdcebf5 RA |
417 | def _get_feed_query(self, uri): |
418 | return { | |
419 | 'arcEp': 'mtvjapan.com', | |
420 | 'mgid': uri, | |
421 | } | |
008f2470 S |
422 | |
423 | ||
8add4bfe | 424 | class MTVVideoIE(MTVServicesInfoExtractor): |
a54ffb8a | 425 | IE_NAME = 'mtv:video' |
5c541b2c JMF |
426 | _VALID_URL = r'''(?x)^https?:// |
427 | (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$| | |
428 | m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))''' | |
84db8181 JMF |
429 | |
430 | _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/' | |
431 | ||
432 | _TESTS = [ | |
433 | { | |
32dac694 | 434 | 'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml', |
32dac694 PH |
435 | 'md5': '850f3f143316b1e71fa56a4edfd6e0f8', |
436 | 'info_dict': { | |
ca0f500e PH |
437 | 'id': '853555', |
438 | 'ext': 'mp4', | |
32dac694 PH |
439 | 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"', |
440 | 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.', | |
712c7530 YCH |
441 | 'timestamp': 1352610000, |
442 | 'upload_date': '20121111', | |
84db8181 JMF |
443 | }, |
444 | }, | |
84db8181 JMF |
445 | ] |
446 | ||
447 | def _get_thumbnail_url(self, uri, itemdoc): | |
448 | return 'http://mtv.mtvnimages.com/uri/' + uri | |
449 | ||
fc287219 | 450 | def _real_extract(self, url): |
5ad28e7f | 451 | mobj = self._match_valid_url(url) |
fc287219 | 452 | video_id = mobj.group('videoid') |
c801b205 | 453 | uri = mobj.groupdict().get('mgid') |
5c541b2c JMF |
454 | if uri is None: |
455 | webpage = self._download_webpage(url, video_id) | |
5f6a1245 | 456 | |
5c541b2c | 457 | # Some videos come from Vevo.com |
ca0f500e PH |
458 | m_vevo = re.search( |
459 | r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage) | |
5c541b2c | 460 | if m_vevo: |
8bcc8756 | 461 | vevo_id = m_vevo.group(1) |
32dac694 | 462 | self.to_screen('Vevo video detected: %s' % vevo_id) |
5c541b2c | 463 | return self.url_result('vevo:%s' % vevo_id, ie='Vevo') |
5f6a1245 | 464 | |
32dac694 | 465 | uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri') |
f7e02595 | 466 | return self._get_videos_info(uri) |
bc4ba05f JMF |
467 | |
468 | ||
071c1013 PH |
469 | class MTVDEIE(MTVServicesInfoExtractor): |
470 | IE_NAME = 'mtv.de' | |
cfabc505 | 471 | _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)' |
79fa9db0 | 472 | _TESTS = [{ |
cfabc505 | 473 | 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum', |
79fa9db0 | 474 | 'info_dict': { |
cfabc505 RA |
475 | 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5', |
476 | 'ext': 'mp4', | |
477 | 'title': 'Traum', | |
478 | 'description': 'Traum', | |
071c1013 | 479 | }, |
79fa9db0 S |
480 | 'params': { |
481 | # rtmp download | |
482 | 'skip_download': True, | |
483 | }, | |
35f6e0ff | 484 | 'skip': 'Blocked at Travis CI', |
c3c9f879 S |
485 | }, { |
486 | # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97) | |
cfabc505 | 487 | 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1', |
c3c9f879 | 488 | 'info_dict': { |
cfabc505 RA |
489 | 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285', |
490 | 'ext': 'mp4', | |
491 | 'title': 'Teen Mom 2', | |
492 | 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7', | |
c3c9f879 S |
493 | }, |
494 | 'params': { | |
495 | # rtmp download | |
496 | 'skip_download': True, | |
497 | }, | |
35f6e0ff | 498 | 'skip': 'Blocked at Travis CI', |
65488b82 | 499 | }, { |
cfabc505 | 500 | 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3', |
65488b82 S |
501 | 'info_dict': { |
502 | 'id': 'local_playlist-4e760566473c4c8c5344', | |
503 | 'ext': 'mp4', | |
504 | 'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1', | |
505 | 'description': 'MTV Movies Supercut', | |
506 | }, | |
507 | 'params': { | |
508 | # rtmp download | |
509 | 'skip_download': True, | |
510 | }, | |
712c7530 | 511 | 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.', |
79fa9db0 | 512 | }] |
cfabc505 RA |
513 | _GEO_COUNTRIES = ['DE'] |
514 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
071c1013 | 515 | |
cfabc505 RA |
516 | def _get_feed_query(self, uri): |
517 | return { | |
518 | 'arcEp': 'mtv.de', | |
519 | 'mgid': uri, | |
520 | } | |
605b684c | 521 | |
522 | ||
523 | class MTVItaliaIE(MTVServicesInfoExtractor): | |
524 | IE_NAME = 'mtv.it' | |
525 | _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:episodi|video|musica)/(?P<id>[0-9a-z]+)' | |
526 | _TESTS = [{ | |
527 | 'url': 'http://www.mtv.it/episodi/24bqab/mario-una-serie-di-maccio-capatonda-cavoli-amario-episodio-completo-S1-E1', | |
528 | 'info_dict': { | |
529 | 'id': '0f0fc78e-45fc-4cce-8f24-971c25477530', | |
530 | 'ext': 'mp4', | |
531 | 'title': 'Cavoli amario (episodio completo)', | |
532 | 'description': 'md5:4962bccea8fed5b7c03b295ae1340660', | |
533 | 'series': 'Mario - Una Serie Di Maccio Capatonda', | |
534 | 'season_number': 1, | |
535 | 'episode_number': 1, | |
536 | }, | |
537 | 'params': { | |
538 | 'skip_download': True, | |
539 | }, | |
540 | }] | |
541 | _GEO_COUNTRIES = ['IT'] | |
542 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
543 | ||
544 | def _get_feed_query(self, uri): | |
545 | return { | |
546 | 'arcEp': 'mtv.it', | |
547 | 'mgid': uri, | |
548 | } | |
549 | ||
550 | ||
551 | class MTVItaliaProgrammaIE(MTVItaliaIE): | |
552 | IE_NAME = 'mtv.it:programma' | |
553 | _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:programmi|playlist)/(?P<id>[0-9a-z]+)' | |
554 | _TESTS = [{ | |
555 | # program page: general | |
556 | 'url': 'http://www.mtv.it/programmi/s2rppv/mario-una-serie-di-maccio-capatonda', | |
557 | 'info_dict': { | |
558 | 'id': 'a6f155bc-8220-4640-aa43-9b95f64ffa3d', | |
559 | 'title': 'Mario - Una Serie Di Maccio Capatonda', | |
560 | 'description': 'md5:72fbffe1f77ccf4e90757dd4e3216153', | |
561 | }, | |
562 | 'playlist_count': 2, | |
563 | 'params': { | |
564 | 'skip_download': True, | |
565 | }, | |
566 | }, { | |
567 | # program page: specific season | |
568 | 'url': 'http://www.mtv.it/programmi/d9ncjf/mario-una-serie-di-maccio-capatonda-S2', | |
569 | 'info_dict': { | |
570 | 'id': '4deeb5d8-f272-490c-bde2-ff8d261c6dd1', | |
571 | 'title': 'Mario - Una Serie Di Maccio Capatonda - Stagione 2', | |
572 | }, | |
573 | 'playlist_count': 34, | |
574 | 'params': { | |
575 | 'skip_download': True, | |
576 | }, | |
577 | }, { | |
578 | # playlist page + redirect | |
579 | 'url': 'http://www.mtv.it/playlist/sexy-videos/ilctal', | |
580 | 'info_dict': { | |
581 | 'id': 'dee8f9ee-756d-493b-bf37-16d1d2783359', | |
582 | 'title': 'Sexy Videos', | |
583 | }, | |
584 | 'playlist_mincount': 145, | |
585 | 'params': { | |
586 | 'skip_download': True, | |
587 | }, | |
588 | }] | |
589 | _GEO_COUNTRIES = ['IT'] | |
590 | _FEED_URL = 'http://www.mtv.it/feeds/triforce/manifest/v8' | |
591 | ||
592 | def _get_entries(self, title, url): | |
593 | while True: | |
594 | pg = self._search_regex(r'/(\d+)$', url, 'entries', '1') | |
595 | entries = self._download_json(url, title, 'page %s' % pg) | |
596 | url = try_get( | |
597 | entries, lambda x: x['result']['nextPageURL'], compat_str) | |
598 | entries = try_get( | |
599 | entries, ( | |
600 | lambda x: x['result']['data']['items'], | |
601 | lambda x: x['result']['data']['seasons']), | |
602 | list) | |
603 | for entry in entries or []: | |
604 | if entry.get('canonicalURL'): | |
605 | yield self.url_result(entry['canonicalURL']) | |
606 | if not url: | |
607 | break | |
608 | ||
609 | def _real_extract(self, url): | |
610 | query = {'url': url} | |
611 | info_url = update_url_query(self._FEED_URL, query) | |
612 | video_id = self._match_id(url) | |
613 | info = self._download_json(info_url, video_id).get('manifest') | |
614 | ||
615 | redirect = try_get( | |
616 | info, lambda x: x['newLocation']['url'], compat_str) | |
617 | if redirect: | |
618 | return self.url_result(redirect) | |
619 | ||
620 | title = info.get('title') | |
621 | video_id = try_get( | |
622 | info, lambda x: x['reporting']['itemId'], compat_str) | |
623 | parent_id = try_get( | |
624 | info, lambda x: x['reporting']['parentId'], compat_str) | |
625 | ||
626 | playlist_url = current_url = None | |
627 | for z in (info.get('zones') or {}).values(): | |
628 | if z.get('moduleName') in ('INTL_M304', 'INTL_M209'): | |
629 | info_url = z.get('feed') | |
630 | if z.get('moduleName') in ('INTL_M308', 'INTL_M317'): | |
631 | playlist_url = playlist_url or z.get('feed') | |
632 | if z.get('moduleName') in ('INTL_M300',): | |
633 | current_url = current_url or z.get('feed') | |
634 | ||
635 | if not info_url: | |
636 | raise ExtractorError('No info found') | |
637 | ||
638 | if video_id == parent_id: | |
639 | video_id = self._search_regex( | |
640 | r'([^\/]+)/[^\/]+$', info_url, 'video_id') | |
641 | ||
642 | info = self._download_json(info_url, video_id, 'Show infos') | |
643 | info = try_get(info, lambda x: x['result']['data'], dict) | |
644 | title = title or try_get( | |
645 | info, ( | |
646 | lambda x: x['title'], | |
647 | lambda x: x['headline']), | |
648 | compat_str) | |
649 | description = try_get(info, lambda x: x['content'], compat_str) | |
650 | ||
651 | if current_url: | |
652 | season = try_get( | |
653 | self._download_json(playlist_url, video_id, 'Seasons info'), | |
654 | lambda x: x['result']['data'], dict) | |
655 | current = try_get( | |
656 | season, lambda x: x['currentSeason'], compat_str) | |
657 | seasons = try_get( | |
658 | season, lambda x: x['seasons'], list) or [] | |
659 | ||
660 | if current in [s.get('eTitle') for s in seasons]: | |
661 | playlist_url = current_url | |
662 | ||
663 | title = re.sub( | |
664 | r'[-|]\s*(?:mtv\s*italia|programma|playlist)', | |
665 | '', title, flags=re.IGNORECASE).strip() | |
666 | ||
667 | return self.playlist_result( | |
668 | self._get_entries(title, playlist_url), | |
669 | video_id, title, description) |