]>
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, |
b6e0c7d2 | 10 | compat_urlparse, |
1cc79574 PH |
11 | ) |
12 | from ..utils import ( | |
fc287219 | 13 | ExtractorError, |
90834c78 | 14 | find_xpath_attr, |
5aafe895 | 15 | fix_xml_ampersands, |
8765151c | 16 | float_or_none, |
0ef68e04 | 17 | HEADRequest, |
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, |
b6e0c7d2 | 26 | get_domain, |
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'&[^=]*?={.*?}(?=(&|$))', '', url) | |
47 | ||
320724f9 | 48 | def _get_feed_url(self, uri, url=None): |
8940c1c0 JMF |
49 | return self._FEED_URL |
50 | ||
ab2f744b | 51 | def _get_thumbnail_url(self, uri, itemdoc): |
84db8181 JMF |
52 | search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail')) |
53 | thumb_node = itemdoc.find(search_path) | |
54 | if thumb_node is None: | |
55 | return None | |
70bfab0e | 56 | return thumb_node.get('url') or thumb_node.text or None |
f7e02595 | 57 | |
340b0468 JMF |
58 | def _extract_mobile_video_formats(self, mtvn_id): |
59 | webpage_url = self._MOBILE_TEMPLATE % mtvn_id | |
5c2266df | 60 | req = sanitized_Request(webpage_url) |
340b0468 | 61 | # Otherwise we get a webpage that would execute some javascript |
3fcfb8e9 | 62 | req.add_header('User-Agent', 'curl/7') |
340b0468 | 63 | webpage = self._download_webpage(req, mtvn_id, |
9e1a5b84 | 64 | 'Downloading mobile page') |
0ef68e04 JMF |
65 | metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url')) |
66 | req = HEADRequest(metrics_url) | |
67 | response = self._request_webpage(req, mtvn_id, 'Resolving url') | |
68 | url = response.geturl() | |
69 | # Transform the url to get the best quality: | |
70 | url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1) | |
5f6a1245 | 71 | return [{'url': url, 'ext': 'mp4'}] |
340b0468 | 72 | |
dbaf6016 | 73 | def _extract_video_formats(self, mdoc, mtvn_id, video_id): |
054d43bb | 74 | if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', 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, | |
103 | 'format_id': '-'.join(filter(None, [ | |
104 | 'rtmp' if rtmp_video_url.startswith('rtmp') else None, | |
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 | |
340b0468 JMF |
181 | # This a short id that's used in the webpage urls |
182 | mtvn_id = None | |
183 | mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category', | |
9e1a5b84 | 184 | 'scheme', 'urn:mtvn:id') |
340b0468 JMF |
185 | if mtvn_id_node is not None: |
186 | mtvn_id = mtvn_id_node.text | |
187 | ||
dbaf6016 PH |
188 | formats = self._extract_video_formats(mediagen_doc, mtvn_id, video_id) |
189 | ||
e0f1fb0a S |
190 | # Some parts of complete video may be missing (e.g. missing Act 3 in |
191 | # http://www.southpark.de/alle-episoden/s14e01-sexual-healing) | |
192 | if not formats: | |
193 | return None | |
194 | ||
195 | self._sort_formats(formats) | |
196 | ||
fb7abb31 | 197 | return { |
90834c78 | 198 | 'title': title, |
dbaf6016 | 199 | 'formats': formats, |
e525d9a3 | 200 | 'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id), |
f13d0933 PH |
201 | 'id': video_id, |
202 | 'thumbnail': self._get_thumbnail_url(uri, itemdoc), | |
203 | 'description': description, | |
04cbc498 | 204 | 'duration': float_or_none(content_el.attrib.get('duration')), |
712c7530 | 205 | 'timestamp': timestamp, |
f13d0933 PH |
206 | } |
207 | ||
c1e90619 | 208 | def _get_feed_query(self, uri): |
209 | data = {'uri': uri} | |
210 | if self._LANG: | |
211 | data['lang'] = self._LANG | |
0c75abbb | 212 | return data |
c1e90619 | 213 | |
320724f9 | 214 | def _get_videos_info(self, uri, use_hls=True, url=None): |
f7e02595 | 215 | video_id = self._id_from_uri(uri) |
320724f9 | 216 | feed_url = self._get_feed_url(uri, url) |
0c75abbb | 217 | info_url = update_url_query(feed_url, self._get_feed_query(uri)) |
dbaf6016 | 218 | return self._get_videos_info_from_url(info_url, video_id, use_hls) |
79fa9db0 | 219 | |
67fc365b | 220 | def _get_videos_info_from_url(self, url, video_id, use_hls=True): |
e2b38da9 | 221 | idoc = self._download_xml( |
79fa9db0 | 222 | url, video_id, |
32dac694 | 223 | 'Downloading info', transform_source=fix_xml_ampersands) |
712c7530 YCH |
224 | |
225 | title = xpath_text(idoc, './channel/title') | |
226 | description = xpath_text(idoc, './channel/description') | |
227 | ||
e0f1fb0a S |
228 | entries = [] |
229 | for item in idoc.findall('.//item'): | |
230 | info = self._get_video_info(item, use_hls) | |
231 | if info: | |
232 | entries.append(info) | |
233 | ||
5239075b | 234 | return self.playlist_result( |
e0f1fb0a | 235 | entries, playlist_title=title, playlist_description=description) |
fc287219 | 236 | |
adf063da S |
237 | def _extract_triforce_mgid(self, webpage, data_zone=None, video_id=None): |
238 | triforce_feed = self._parse_json(self._search_regex( | |
f1e70fc2 | 239 | r'triforceManifestFeed\s*=\s*({.+?})\s*;\s*\n', webpage, |
adf063da S |
240 | 'triforce feed', default='{}'), video_id, fatal=False) |
241 | ||
242 | data_zone = self._search_regex( | |
243 | r'data-zone=(["\'])(?P<zone>.+?_lc_promo.*?)\1', webpage, | |
244 | 'data zone', default=data_zone, group='zone') | |
245 | ||
246 | feed_url = try_get( | |
247 | triforce_feed, lambda x: x['manifest']['zones'][data_zone]['feed'], | |
248 | compat_str) | |
249 | if not feed_url: | |
250 | return | |
251 | ||
252 | feed = self._download_json(feed_url, video_id, fatal=False) | |
253 | if not feed: | |
254 | return | |
255 | ||
256 | return try_get(feed, lambda x: x['result']['data']['id'], compat_str) | |
257 | ||
cf7cb942 | 258 | def _extract_new_triforce_mgid(self, webpage, url='', video_id=None): |
cf7cb942 U |
259 | if url == '': |
260 | return | |
b6e0c7d2 U |
261 | domain = get_domain(url) |
262 | if domain is None: | |
263 | raise ExtractorError( | |
264 | '[%s] could not get domain' % self.IE_NAME, | |
265 | expected=True) | |
266 | url = url.replace("https://", "http://") | |
267 | enc_url = compat_urlparse.quote(url, safe='') | |
268 | _TRIFORCE_V8_TEMPLATE = 'https://%s/feeds/triforce/manifest/v8?url=%s' | |
269 | triforce_manifest_url = _TRIFORCE_V8_TEMPLATE % (domain, enc_url) | |
270 | ||
271 | manifest = self._download_json(triforce_manifest_url, video_id, fatal=False) | |
cf7cb942 U |
272 | if manifest: |
273 | if manifest.get('manifest').get('type') == 'redirect': | |
274 | self.to_screen('Found a redirect. Downloading manifest from new location') | |
275 | new_loc = manifest.get('manifest').get('newLocation') | |
276 | new_loc = new_loc.replace("https://", "http://") | |
277 | enc_new_loc = compat_urlparse.quote(new_loc, safe='') | |
278 | triforce_manifest_new_loc = _TRIFORCE_V8_TEMPLATE % (domain, enc_new_loc) | |
279 | manifest = self._download_json(triforce_manifest_new_loc, video_id, fatal=False) | |
b6e0c7d2 U |
280 | |
281 | item_id = try_get(manifest, lambda x: x['manifest']['reporting']['itemId'], compat_str) | |
282 | if not item_id: | |
320724f9 | 283 | self.to_screen('No id found!') |
b6e0c7d2 U |
284 | return |
285 | ||
286 | # 'episode' can be anything. 'content' is used often as well | |
287 | _MGID_TEMPLATE = 'mgid:arc:episode:%s:%s' | |
288 | mgid = _MGID_TEMPLATE % (domain, item_id) | |
289 | ||
290 | return mgid | |
291 | ||
cf7cb942 | 292 | def _extract_mgid(self, webpage, url, data_zone=None): |
8d9453b9 | 293 | try: |
4bbf139a JMF |
294 | # the url can be http://media.mtvnservices.com/fb/{mgid}.swf |
295 | # or http://media.mtvnservices.com/{mgid} | |
296 | og_url = self._og_search_video_url(webpage) | |
297 | mgid = url_basename(og_url) | |
298 | if mgid.endswith('.swf'): | |
299 | mgid = mgid[:-4] | |
8d9453b9 | 300 | except RegexNotFoundError: |
b1298d8e AMW |
301 | mgid = None |
302 | ||
320724f9 U |
303 | title = self._match_id(url) |
304 | ||
305 | try: | |
306 | window_data = self._parse_json(self._search_regex( | |
307 | r'(?s)window.__DATA__ = (?P<json>{.+});', webpage, | |
308 | 'JSON Window Data', default=None, fatal=False, group='json'), title, fatal=False) | |
51707d9a U |
309 | main_container = None |
310 | for i in range(len(window_data['children'])): | |
311 | if window_data['children'][i]['type'] == 'MainContainer': | |
312 | main_container = window_data['children'][i] | |
313 | mgid = main_container['children'][0]['props']['media']['video']['config']['uri'] | |
320724f9 U |
314 | except (KeyError, IndexError, TypeError): |
315 | pass | |
316 | ||
b1298d8e | 317 | if mgid is None or ':' not in mgid: |
b9381e43 | 318 | mgid = self._search_regex( |
197224b7 | 319 | [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'], |
fc42bc6e S |
320 | webpage, 'mgid', default=None) |
321 | ||
322 | if not mgid: | |
323 | sm4_embed = self._html_search_meta( | |
324 | 'sm4:video:embed', webpage, 'sm4 embed', default='') | |
325 | mgid = self._search_regex( | |
adf063da S |
326 | r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None) |
327 | ||
b6e0c7d2 U |
328 | if not mgid: |
329 | mgid = self._extract_new_triforce_mgid(webpage, url) | |
330 | ||
adf063da | 331 | if not mgid: |
cf7cb942 | 332 | mgid = self._extract_triforce_mgid(webpage, data_zone) |
adf063da | 333 | |
c1e90619 | 334 | return mgid |
e525d9a3 | 335 | |
c1e90619 | 336 | def _real_extract(self, url): |
337 | title = url_basename(url) | |
338 | webpage = self._download_webpage(url, title) | |
b6e0c7d2 | 339 | mgid = self._extract_mgid(webpage, url) |
320724f9 | 340 | videos_info = self._get_videos_info(mgid, url=url) |
e525d9a3 | 341 | return videos_info |
8d9453b9 | 342 | |
84db8181 | 343 | |
8940c1c0 JMF |
344 | class MTVServicesEmbeddedIE(MTVServicesInfoExtractor): |
345 | IE_NAME = 'mtvservices:embedded' | |
346 | _VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)' | |
347 | ||
348 | _TEST = { | |
349 | # From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/ | |
350 | 'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906', | |
351 | 'md5': 'cb349b21a7897164cede95bd7bf3fbb9', | |
352 | 'info_dict': { | |
353 | 'id': '1043906', | |
354 | 'ext': 'mp4', | |
355 | 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds', | |
356 | '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 |
357 | 'timestamp': 1400126400, |
358 | 'upload_date': '20140515', | |
8940c1c0 JMF |
359 | }, |
360 | } | |
361 | ||
fe1d858e S |
362 | @staticmethod |
363 | def _extract_url(webpage): | |
364 | mobj = re.search( | |
365 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media.mtvnservices.com/embed/.+?)\1', webpage) | |
366 | if mobj: | |
367 | return mobj.group('url') | |
368 | ||
8940c1c0 JMF |
369 | def _get_feed_url(self, uri): |
370 | video_id = self._id_from_uri(uri) | |
0c75abbb YCH |
371 | config = self._download_json( |
372 | 'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id) | |
373 | return self._remove_template_parameter(config['feedWithQueryParams']) | |
8940c1c0 JMF |
374 | |
375 | def _real_extract(self, url): | |
376 | mobj = re.match(self._VALID_URL, url) | |
377 | mgid = mobj.group('mgid') | |
378 | return self._get_videos_info(mgid) | |
379 | ||
380 | ||
84db8181 | 381 | class MTVIE(MTVServicesInfoExtractor): |
a54ffb8a | 382 | IE_NAME = 'mtv' |
cf0cabbe | 383 | _VALID_URL = r'https?://(?:www\.)?mtv\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)' |
8add4bfe RA |
384 | _FEED_URL = 'http://www.mtv.com/feeds/mrss/' |
385 | ||
386 | _TESTS = [{ | |
387 | 'url': 'http://www.mtv.com/video-clips/vl8qof/unlocking-the-truth-trailer', | |
388 | 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b', | |
389 | 'info_dict': { | |
390 | 'id': '5e14040d-18a4-47c4-a582-43ff602de88e', | |
391 | 'ext': 'mp4', | |
392 | 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer', | |
393 | 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.', | |
394 | 'timestamp': 1468846800, | |
395 | 'upload_date': '20160718', | |
396 | }, | |
397 | }, { | |
398 | 'url': 'http://www.mtv.com/full-episodes/94tujl/unlocking-the-truth-gates-of-hell-season-1-ep-101', | |
399 | 'only_matching': True, | |
cf0cabbe S |
400 | }, { |
401 | 'url': 'http://www.mtv.com/episodes/g8xu7q/teen-mom-2-breaking-the-wall-season-7-ep-713', | |
402 | 'only_matching': True, | |
8add4bfe RA |
403 | }] |
404 | ||
405 | ||
3cdcebf5 RA |
406 | class MTVJapanIE(MTVServicesInfoExtractor): |
407 | IE_NAME = 'mtvjapan' | |
408 | _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)' | |
008f2470 S |
409 | |
410 | _TEST = { | |
3cdcebf5 | 411 | 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade', |
008f2470 | 412 | 'info_dict': { |
3cdcebf5 | 413 | 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5', |
008f2470 | 414 | 'ext': 'mp4', |
3cdcebf5 RA |
415 | 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition', |
416 | }, | |
417 | 'params': { | |
418 | 'skip_download': True, | |
008f2470 S |
419 | }, |
420 | } | |
3cdcebf5 RA |
421 | _GEO_COUNTRIES = ['JP'] |
422 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
008f2470 | 423 | |
3cdcebf5 RA |
424 | def _get_feed_query(self, uri): |
425 | return { | |
426 | 'arcEp': 'mtvjapan.com', | |
427 | 'mgid': uri, | |
428 | } | |
008f2470 S |
429 | |
430 | ||
8add4bfe | 431 | class MTVVideoIE(MTVServicesInfoExtractor): |
a54ffb8a | 432 | IE_NAME = 'mtv:video' |
5c541b2c JMF |
433 | _VALID_URL = r'''(?x)^https?:// |
434 | (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$| | |
435 | m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))''' | |
84db8181 JMF |
436 | |
437 | _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/' | |
438 | ||
439 | _TESTS = [ | |
440 | { | |
32dac694 | 441 | 'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml', |
32dac694 PH |
442 | 'md5': '850f3f143316b1e71fa56a4edfd6e0f8', |
443 | 'info_dict': { | |
ca0f500e PH |
444 | 'id': '853555', |
445 | 'ext': 'mp4', | |
32dac694 PH |
446 | 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"', |
447 | 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.', | |
712c7530 YCH |
448 | 'timestamp': 1352610000, |
449 | 'upload_date': '20121111', | |
84db8181 JMF |
450 | }, |
451 | }, | |
84db8181 JMF |
452 | ] |
453 | ||
454 | def _get_thumbnail_url(self, uri, itemdoc): | |
455 | return 'http://mtv.mtvnimages.com/uri/' + uri | |
456 | ||
fc287219 PH |
457 | def _real_extract(self, url): |
458 | mobj = re.match(self._VALID_URL, url) | |
fc287219 | 459 | video_id = mobj.group('videoid') |
c801b205 | 460 | uri = mobj.groupdict().get('mgid') |
5c541b2c JMF |
461 | if uri is None: |
462 | webpage = self._download_webpage(url, video_id) | |
5f6a1245 | 463 | |
5c541b2c | 464 | # Some videos come from Vevo.com |
ca0f500e PH |
465 | m_vevo = re.search( |
466 | r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage) | |
5c541b2c | 467 | if m_vevo: |
8bcc8756 | 468 | vevo_id = m_vevo.group(1) |
32dac694 | 469 | self.to_screen('Vevo video detected: %s' % vevo_id) |
5c541b2c | 470 | return self.url_result('vevo:%s' % vevo_id, ie='Vevo') |
5f6a1245 | 471 | |
32dac694 | 472 | uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, 'uri') |
f7e02595 | 473 | return self._get_videos_info(uri) |
bc4ba05f JMF |
474 | |
475 | ||
071c1013 PH |
476 | class MTVDEIE(MTVServicesInfoExtractor): |
477 | IE_NAME = 'mtv.de' | |
cfabc505 | 478 | _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)' |
79fa9db0 | 479 | _TESTS = [{ |
cfabc505 | 480 | 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum', |
79fa9db0 | 481 | 'info_dict': { |
cfabc505 RA |
482 | 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5', |
483 | 'ext': 'mp4', | |
484 | 'title': 'Traum', | |
485 | 'description': 'Traum', | |
071c1013 | 486 | }, |
79fa9db0 S |
487 | 'params': { |
488 | # rtmp download | |
489 | 'skip_download': True, | |
490 | }, | |
35f6e0ff | 491 | 'skip': 'Blocked at Travis CI', |
c3c9f879 S |
492 | }, { |
493 | # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97) | |
cfabc505 | 494 | 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1', |
c3c9f879 | 495 | 'info_dict': { |
cfabc505 RA |
496 | 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285', |
497 | 'ext': 'mp4', | |
498 | 'title': 'Teen Mom 2', | |
499 | 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7', | |
c3c9f879 S |
500 | }, |
501 | 'params': { | |
502 | # rtmp download | |
503 | 'skip_download': True, | |
504 | }, | |
35f6e0ff | 505 | 'skip': 'Blocked at Travis CI', |
65488b82 | 506 | }, { |
cfabc505 | 507 | 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3', |
65488b82 S |
508 | 'info_dict': { |
509 | 'id': 'local_playlist-4e760566473c4c8c5344', | |
510 | 'ext': 'mp4', | |
511 | 'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1', | |
512 | 'description': 'MTV Movies Supercut', | |
513 | }, | |
514 | 'params': { | |
515 | # rtmp download | |
516 | 'skip_download': True, | |
517 | }, | |
712c7530 | 518 | 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.', |
79fa9db0 | 519 | }] |
cfabc505 RA |
520 | _GEO_COUNTRIES = ['DE'] |
521 | _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' | |
071c1013 | 522 | |
cfabc505 RA |
523 | def _get_feed_query(self, uri): |
524 | return { | |
525 | 'arcEp': 'mtv.de', | |
526 | 'mgid': uri, | |
527 | } |