5 from .common
import InfoExtractor
, SearchInfoExtractor
21 from .brightcove
import BrightcoveNewIE
22 from .youtube
import YoutubeIE
25 class YahooIE(InfoExtractor
):
26 IE_DESC
= 'Yahoo screen and movies'
27 _VALID_URL
= r
'(?P<url>https?://(?:(?P<country>[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P<id>[^?&#]*-[0-9]+(?:-[a-z]+)?)\.html)'
29 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
31 'id': '2d25e626-2378-391f-ada0-ddaf1417e588',
33 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
34 'description': 'Julian and Travis watch Julian Smith',
36 'timestamp': 1369812016,
37 'upload_date': '20130529',
39 'skip': 'No longer exists',
41 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed',
42 'md5': '7993e572fac98e044588d0b5260f4352',
44 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb',
46 'title': "Yahoo Saves 'Community'",
47 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053',
49 'timestamp': 1406838636,
50 'upload_date': '20140731',
52 'skip': 'Unfortunately, this video is not available in your region',
54 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html',
55 'md5': '71298482f7c64cbb7fa064e4553ff1c1',
57 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58',
59 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder',
60 'description': 'md5:f66c890e1490f4910a9953c941dee944',
62 'timestamp': 1414489862,
63 'upload_date': '20141028',
65 'skip': 'No longer exists',
67 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
68 'md5': '88e209b417f173d86186bef6e4d1f160',
70 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521',
72 'title': 'China Moses Is Crazy About the Blues',
73 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
75 'timestamp': 1385722202,
76 'upload_date': '20131129',
79 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html',
80 'md5': '2a9752f74cb898af5d1083ea9f661b58',
82 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
84 'title': '\'True Story\' Trailer',
85 'description': 'True Story',
87 'timestamp': 1418919206,
88 'upload_date': '20141218',
91 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
92 'only_matching': True,
94 'note': 'NBC Sports embeds',
95 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313',
99 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
100 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
101 'upload_date': '20150313',
102 'uploader': 'NBCU-SPORTS',
103 'timestamp': 1426270238,
106 'url': 'https://tw.news.yahoo.com/-100120367.html',
107 'only_matching': True,
109 # Query result is embedded in webpage, but explicit request to video API fails with geo restriction
110 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html',
111 'md5': '4fbafb9c9b6f07aa8f870629f6671b35',
113 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504',
115 'title': 'Communitary - Community Episode 1: Ladders',
116 'description': 'md5:8fc39608213295748e1e289807838c97',
118 'timestamp': 1440436550,
119 'upload_date': '20150824',
120 'series': 'Communitary',
124 'skip': 'No longer exists',
127 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html',
129 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff',
131 'title': '單車天使 - 中文版預',
132 'description': '中文版預',
133 'timestamp': 1476696196,
134 'upload_date': '20161017',
137 'skip_download': True,
140 # Contains both a Yahoo hosted video and multiple Youtube embeds
141 'url': 'https://www.yahoo.com/entertainment/gwen-stefani-reveals-the-pop-hit-she-passed-on-assigns-it-to-her-voice-contestant-instead-033045672.html',
143 'id': '46c5d95a-528f-3d03-b732-732fcadd51de',
144 'title': 'Gwen Stefani reveals the pop hit she passed on, assigns it to her \'Voice\' contestant instead',
145 'description': 'Gwen decided not to record this hit herself, but she decided it was the perfect fit for Kyndall Inskeep.',
149 'id': '966d4262-4fd1-3aaa-b45b-049ca6e38ba6',
151 'title': 'Gwen Stefani reveals she turned down one of Sia\'s best songs',
152 'description': 'On "The Voice" Tuesday, Gwen Stefani told Taylor Swift which Sia hit was almost hers.',
153 'timestamp': 1572406500,
154 'upload_date': '20191030',
160 'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019',
161 'description': 'md5:7fe8e3d5806f96002e55f190d1d94479',
162 'uploader': 'The Voice',
163 'uploader_id': 'NBCTheVoice',
164 'upload_date': '20191029',
170 'expected_warnings': ['HTTP Error 404', 'Ignoring subtitle tracks'],
172 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html',
173 'only_matching': True,
175 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html',
176 'only_matching': True,
178 'url': 'https://www.yahoo.com/entertainment/v/longtime-cbs-news-60-minutes-032036500-cbs.html',
179 'only_matching': True,
182 def _extract_yahoo_video(self
, video_id
, country
):
183 video
= self
._download
_json
(
184 'https://%s.yahoo.com/_td/api/resource/VideoService.videos;view=full;video_ids=["%s"]' % (country
, video_id
),
185 video_id
, 'Downloading video JSON metadata')[0]
186 title
= video
['title']
188 if country
== 'malaysia':
191 is_live
= video
.get('live_state') == 'live'
192 fmts
= ('m3u8',) if is_live
else ('webm', 'mp4')
198 media_obj
= self
._download
_json
(
199 'https://video-api.yql.yahoo.com/v1/video/sapi/streams/' + video_id
,
200 video_id
, 'Downloading %s JSON metadata' % fmt
,
201 headers
=self
.geo_verification_headers(), query
={
203 'region': country
.upper(),
204 })['query']['results']['mediaObj'][0]
205 msg
= media_obj
.get('status', {}).get('msg')
207 for s
in media_obj
.get('streams', []):
210 if not host
or not path
:
213 if s
.get('format') == 'm3u8':
214 formats
.extend(self
._extract
_m
3u8_formats
(
215 s_url
, video_id
, 'mp4', m3u8_id
='hls', fatal
=False))
217 tbr
= int_or_none(s
.get('bitrate'))
220 'format_id': fmt
+ ('-%d' % tbr
if tbr
else ''),
221 'width': int_or_none(s
.get('width')),
222 'height': int_or_none(s
.get('height')),
224 'fps': int_or_none(s
.get('framerate')),
227 for cc
in media_obj
.get('closedcaptions', []):
228 cc_url
= cc
.get('url')
229 if not cc_url
or cc_url
in urls
:
232 subtitles
.setdefault(cc
.get('lang') or 'en-US', []).append({
234 'ext': mimetype2ext(cc
.get('content_type')),
237 streaming_url
= video
.get('streaming_url')
238 if streaming_url
and not is_live
:
239 formats
.extend(self
._extract
_m
3u8_formats
(
240 streaming_url
, video_id
, 'mp4',
241 'm3u8_native', m3u8_id
='hls', fatal
=False))
243 if not formats
and msg
== 'geo restricted':
244 self
.raise_geo_restricted(metadata_available
=True)
246 self
._sort
_formats
(formats
)
249 for thumb
in video
.get('thumbnails', []):
250 thumb_url
= thumb
.get('url')
254 'id': thumb
.get('tag'),
255 'url': thumb
.get('url'),
256 'width': int_or_none(thumb
.get('width')),
257 'height': int_or_none(thumb
.get('height')),
260 series_info
= video
.get('series_info') or {}
266 'thumbnails': thumbnails
,
267 'description': clean_html(video
.get('description')),
268 'timestamp': parse_iso8601(video
.get('publish_time')),
269 'subtitles': subtitles
,
270 'duration': int_or_none(video
.get('duration')),
271 'view_count': int_or_none(video
.get('view_count')),
273 'series': video
.get('show_name'),
274 'season_number': int_or_none(series_info
.get('season_number')),
275 'episode_number': int_or_none(series_info
.get('episode_number')),
278 def _real_extract(self
, url
):
279 url
, country
, display_id
= self
._match
_valid
_url
(url
).groups()
283 country
= country
.split('-')[0]
285 items
= self
._download
_json
(
286 'https://%s.yahoo.com/caas/content/article' % country
, display_id
,
287 'Downloading content JSON metadata', query
={
291 item
= items
['data']['partnerData']
292 if item
.get('type') != 'video':
295 cover
= item
.get('cover') or {}
296 if cover
.get('type') == 'yvideo':
297 cover_url
= cover
.get('url')
299 entries
.append(self
.url_result(
300 cover_url
, 'Yahoo', cover
.get('uuid')))
302 for e
in (item
.get('body') or []):
303 if e
.get('type') == 'videoIframe':
304 iframe_url
= e
.get('url')
306 entries
.append(self
.url_result(iframe_url
))
308 if item
.get('type') == 'storywithleadvideo':
309 iframe_url
= try_get(item
, lambda x
: x
['meta']['player']['url'])
311 entries
.append(self
.url_result(iframe_url
))
313 self
.report_warning("Yahoo didn't provide an iframe url for this storywithleadvideo")
315 if items
.get('markup'):
317 self
.url_result(yt_url
) for yt_url
in YoutubeIE
._extract
_urls
(items
['markup']))
319 return self
.playlist_result(
320 entries
, item
.get('uuid'),
321 item
.get('title'), item
.get('summary'))
323 info
= self
._extract
_yahoo
_video
(item
['uuid'], country
)
324 info
['display_id'] = display_id
328 class YahooSearchIE(SearchInfoExtractor
):
329 IE_DESC
= 'Yahoo screen search'
331 IE_NAME
= 'screen.yahoo:search'
332 _SEARCH_KEY
= 'yvsearch'
334 def _search_results(self
, query
):
335 for pagenum
in itertools
.count(0):
336 result_url
= 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse
.quote_plus(query
), pagenum
* 30)
337 info
= self
._download
_json
(result_url
, query
,
338 note
='Downloading results page ' + str(pagenum
+ 1))
339 yield from (self
.url_result(result
['rurl']) for result
in info
['results'])
340 if info
['m']['last'] >= info
['m']['total'] - 1:
344 class YahooGyaOPlayerIE(InfoExtractor
):
345 IE_NAME
= 'yahoo:gyao:player'
346 _VALID_URL
= r
'https?://(?:gyao\.yahoo\.co\.jp/(?:player|episode(?:/[^/]+)?)|streaming\.yahoo\.co\.jp/c/y)/(?P<id>\d+/v\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
348 'url': 'https://gyao.yahoo.co.jp/player/00998/v00818/v0000000000000008564/',
350 'id': '5993125228001',
352 'title': 'フューリー 【字幕版】',
353 'description': 'md5:21e691c798a15330eda4db17a8fe45a5',
354 'uploader_id': '4235717419001',
355 'upload_date': '20190124',
356 'timestamp': 1548294365,
360 'skip_download': True,
363 'url': 'https://streaming.yahoo.co.jp/c/y/01034/v00133/v0000000000000000706/',
364 'only_matching': True,
366 'url': 'https://gyao.yahoo.co.jp/episode/%E3%81%8D%E3%81%AE%E3%81%86%E4%BD%95%E9%A3%9F%E3%81%B9%E3%81%9F%EF%BC%9F%20%E7%AC%AC2%E8%A9%B1%202019%2F4%2F12%E6%94%BE%E9%80%81%E5%88%86/5cb02352-b725-409e-9f8d-88f947a9f682',
367 'only_matching': True,
369 'url': 'https://gyao.yahoo.co.jp/episode/5fa1226c-ef8d-4e93-af7a-fd92f4e30597',
370 'only_matching': True,
374 def _real_extract(self
, url
):
375 video_id
= self
._match
_id
(url
).replace('/', ':')
376 headers
= self
.geo_verification_headers()
377 headers
['Accept'] = 'application/json'
378 resp
= self
._download
_json
(
379 'https://gyao.yahoo.co.jp/apis/playback/graphql', video_id
, query
={
380 'appId': 'dj00aiZpPUNJeDh2cU1RazU3UCZzPWNvbnN1bWVyc2VjcmV0Jng9NTk-',
382 content(parameter: {contentId: "%s", logicaAgent: PC_WEB}) {
392 content
= resp
['data']['content']
394 msg
= resp
['errors'][0]['message']
395 if msg
== 'not in japan':
396 self
.raise_geo_restricted(countries
=['JP'])
397 raise ExtractorError(msg
)
398 video
= content
['video']
400 '_type': 'url_transparent',
402 'title': video
['title'],
404 'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video
['delivery']['id'],
405 {'geo_countries': ['JP']}
),
406 'ie_key': BrightcoveNewIE
.ie_key(),
410 class YahooGyaOIE(InfoExtractor
):
411 IE_NAME
= 'yahoo:gyao'
412 _VALID_URL
= r
'https?://(?:gyao\.yahoo\.co\.jp/(?:p|title(?:/[^/]+)?)|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
414 'url': 'https://gyao.yahoo.co.jp/title/%E3%82%BF%E3%82%A4%E3%83%A0%E3%83%9C%E3%82%AB%E3%83%B3%E3%82%B7%E3%83%AA%E3%83%BC%E3%82%BA%20%E3%83%A4%E3%83%83%E3%82%BF%E3%83%BC%E3%83%9E%E3%83%B3/5f60ceb3-6e5e-40ef-ba40-d68b598d067f',
416 'id': '5f60ceb3-6e5e-40ef-ba40-d68b598d067f',
418 'playlist_mincount': 80,
420 'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/',
421 'only_matching': True,
423 'url': 'https://streaming.yahoo.co.jp/p/y/01034/v00133/',
424 'only_matching': True,
426 'url': 'https://gyao.yahoo.co.jp/title/%E3%81%97%E3%82%83%E3%81%B9%E3%81%8F%E3%82%8A007/5b025a49-b2e5-4dc7-945c-09c6634afacf',
427 'only_matching': True,
429 'url': 'https://gyao.yahoo.co.jp/title/5b025a49-b2e5-4dc7-945c-09c6634afacf',
430 'only_matching': True,
433 def _entries(self
, program_id
):
436 playlist
= self
._download
_json
(
437 f
'https://gyao.yahoo.co.jp/api/programs/{program_id}/videos?page={page}&serviceId=gy', program_id
,
438 note
=f
'Downloading JSON metadata page {page}')
441 for video
in playlist
['videos']:
442 video_id
= video
.get('id')
445 if video
.get('streamingAvailability') == 'notYet':
447 yield self
.url_result(
448 'https://gyao.yahoo.co.jp/player/%s/' % video_id
.replace(':', '/'),
449 YahooGyaOPlayerIE
.ie_key(), video_id
)
450 if playlist
.get('ended'):
454 def _real_extract(self
, url
):
455 program_id
= self
._match
_id
(url
).replace('/', ':')
456 return self
.playlist_result(self
._entries
(program_id
), program_id
)
459 class YahooJapanNewsIE(InfoExtractor
):
460 IE_NAME
= 'yahoo:japannews'
461 IE_DESC
= 'Yahoo! Japan News'
462 _VALID_URL
= r
'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)[^\d]*(?P<id>\d[\d-]*\d)?'
463 _GEO_COUNTRIES
= ['JP']
465 'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int',
469 'title': 'ムン大統領が対日批判を強化“現金化”効果は?(テレビ朝日系(ANN)) - Yahoo!ニュース',
470 'description': '韓国の元徴用工らを巡る裁判の原告が弁護士が差し押さえた三菱重工業の資産を売却して - Yahoo!ニュース(テレビ朝日系(ANN))',
471 'thumbnail': r
're:^https?://.*\.[a-zA-Z\d]{3,4}$',
474 'skip_download': True,
478 'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04',
479 'only_matching': True,
481 'url': 'https://headlines.yahoo.co.jp/videonews/',
482 'only_matching': True,
484 'url': 'https://news.yahoo.co.jp',
485 'only_matching': True,
487 'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/',
488 'only_matching': True,
490 'url': 'https://news.yahoo.co.jp/feature/1356',
491 'only_matching': True
494 def _extract_formats(self
, json_data
, content_id
):
497 video_data
= try_get(
499 lambda x
: x
['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
501 for vid
in video_data
or []:
502 delivery
= vid
.get('delivery')
503 url
= url_or_none(vid
.get('Url'))
504 if not delivery
or not url
:
506 elif delivery
== 'hls':
508 self
._extract
_m
3u8_formats
(
509 url
, content_id
, 'mp4', 'm3u8_native',
510 m3u8_id
='hls', fatal
=False))
514 'format_id': 'http-%s' % compat_str(vid
.get('bitrate', '')),
515 'height': int_or_none(vid
.get('height')),
516 'width': int_or_none(vid
.get('width')),
517 'tbr': int_or_none(vid
.get('bitrate')),
519 self
._remove
_duplicate
_formats
(formats
)
520 self
._sort
_formats
(formats
)
524 def _real_extract(self
, url
):
525 mobj
= self
._match
_valid
_url
(url
)
526 host
= mobj
.group('host')
527 display_id
= mobj
.group('id') or host
529 webpage
= self
._download
_webpage
(url
, display_id
)
531 title
= self
._html
_search
_meta
(
532 ['og:title', 'twitter:title'], webpage
, 'title', default
=None
533 ) or self
._html
_extract
_title
(webpage
)
535 if display_id
== host
:
536 # Headline page (w/ multiple BC playlists) ('news.yahoo.co.jp', 'headlines.yahoo.co.jp/videonews/', ...)
537 stream_plists
= re
.findall(r
'plist=(\d+)', webpage
) or re
.findall(r
'plist["\']:\s
*["\']([^"\']+)', webpage)
541 'http
://players
.brightcove
.net
/5690807595001/HyZNerRl7_default
/index
.html?playlistId
=%s' % plist_id,
542 {'geo_countries': ['JP']}),
543 ie='BrightcoveNew
', video_id=plist_id)
544 for plist_id in stream_plists]
545 return self.playlist_result(entries, playlist_title=title)
548 description = self._html_search_meta(
549 ['og
:description
', 'description
', 'twitter
:description
'],
550 webpage, 'description
', default=None)
551 thumbnail = self._og_search_thumbnail(
552 webpage, default=None) or self._html_search_meta(
553 'twitter
:image
', webpage, 'thumbnail
', default=None)
554 space_id = self._search_regex([
555 r'<script
[^
>]+class=["\']yvpub-player["\'][^
>]+spaceid
=([^
&"\']+)',
556 r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
557 r'<!--\s
+SpaceID
=(\d
+)'
558 ], webpage, 'spaceid
')
560 content_id = self._search_regex(
561 r'<script
[^
>]+class=["\']yvpub-player["\'][^
>]+contentid
=(?P
<contentid
>[^
&"\']+)',
562 webpage, 'contentid', group='contentid')
564 json_data = self._download_json(
565 'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
568 'appid': 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-',
570 'space_id': space_id,
572 'ak': hashlib.md5('_'.join((space_id, host)).encode()).hexdigest(),
573 'device_type': '1100',
575 formats = self._extract_formats(json_data, content_id)
580 'description': description,
581 'thumbnail': thumbnail,