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