2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
, SearchInfoExtractor
24 from .brightcove
import BrightcoveNewIE
25 from .youtube
import YoutubeIE
28 class YahooIE(InfoExtractor
):
29 IE_DESC
= 'Yahoo screen and movies'
30 _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)'
32 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
34 'id': '2d25e626-2378-391f-ada0-ddaf1417e588',
36 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
37 'description': 'Julian and Travis watch Julian Smith',
39 'timestamp': 1369812016,
40 'upload_date': '20130529',
42 'skip': 'No longer exists',
44 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed',
45 'md5': '7993e572fac98e044588d0b5260f4352',
47 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb',
49 'title': "Yahoo Saves 'Community'",
50 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053',
52 'timestamp': 1406838636,
53 'upload_date': '20140731',
55 'skip': 'Unfortunately, this video is not available in your region',
57 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html',
58 'md5': '71298482f7c64cbb7fa064e4553ff1c1',
60 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58',
62 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder',
63 'description': 'md5:f66c890e1490f4910a9953c941dee944',
65 'timestamp': 1414489862,
66 'upload_date': '20141028',
68 'skip': 'No longer exists',
70 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
71 'md5': '88e209b417f173d86186bef6e4d1f160',
73 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521',
75 'title': 'China Moses Is Crazy About the Blues',
76 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
78 'timestamp': 1385722202,
79 'upload_date': '20131129',
82 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html',
83 'md5': '2a9752f74cb898af5d1083ea9f661b58',
85 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
87 'title': '\'True Story\' Trailer',
88 'description': 'True Story',
90 'timestamp': 1418919206,
91 'upload_date': '20141218',
94 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
95 'only_matching': True,
97 'note': 'NBC Sports embeds',
98 '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',
100 'id': '9CsDKds0kvHI',
102 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
103 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
104 'upload_date': '20150313',
105 'uploader': 'NBCU-SPORTS',
106 'timestamp': 1426270238,
109 'url': 'https://tw.news.yahoo.com/-100120367.html',
110 'only_matching': True,
112 # Query result is embedded in webpage, but explicit request to video API fails with geo restriction
113 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html',
114 'md5': '4fbafb9c9b6f07aa8f870629f6671b35',
116 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504',
118 'title': 'Communitary - Community Episode 1: Ladders',
119 'description': 'md5:8fc39608213295748e1e289807838c97',
121 'timestamp': 1440436550,
122 'upload_date': '20150824',
123 'series': 'Communitary',
127 'skip': 'No longer exists',
130 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html',
132 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff',
134 'title': '單車天使 - 中文版預',
135 'description': '中文版預',
136 'timestamp': 1476696196,
137 'upload_date': '20161017',
140 'skip_download': True,
143 # Contains both a Yahoo hosted video and multiple Youtube embeds
144 'url': 'https://www.yahoo.com/entertainment/gwen-stefani-reveals-the-pop-hit-she-passed-on-assigns-it-to-her-voice-contestant-instead-033045672.html',
146 'id': '46c5d95a-528f-3d03-b732-732fcadd51de',
147 'title': 'Gwen Stefani reveals the pop hit she passed on, assigns it to her \'Voice\' contestant instead',
148 'description': 'Gwen decided not to record this hit herself, but she decided it was the perfect fit for Kyndall Inskeep.',
152 'id': '966d4262-4fd1-3aaa-b45b-049ca6e38ba6',
154 'title': 'Gwen Stefani reveals she turned down one of Sia\'s best songs',
155 'description': 'On "The Voice" Tuesday, Gwen Stefani told Taylor Swift which Sia hit was almost hers.',
156 'timestamp': 1572406500,
157 'upload_date': '20191030',
163 'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019',
164 'description': 'md5:7fe8e3d5806f96002e55f190d1d94479',
165 'uploader': 'The Voice',
166 'uploader_id': 'NBCTheVoice',
167 'upload_date': '20191029',
173 'expected_warnings': ['HTTP Error 404', 'Ignoring subtitle tracks'],
175 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html',
176 'only_matching': True,
178 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html',
179 'only_matching': True,
181 'url': 'https://www.yahoo.com/entertainment/v/longtime-cbs-news-60-minutes-032036500-cbs.html',
182 'only_matching': True,
185 def _extract_yahoo_video(self
, video_id
, country
):
186 video
= self
._download
_json
(
187 'https://%s.yahoo.com/_td/api/resource/VideoService.videos;view=full;video_ids=["%s"]' % (country
, video_id
),
188 video_id
, 'Downloading video JSON metadata')[0]
189 title
= video
['title']
191 if country
== 'malaysia':
194 is_live
= video
.get('live_state') == 'live'
195 fmts
= ('m3u8',) if is_live
else ('webm', 'mp4')
201 media_obj
= self
._download
_json
(
202 'https://video-api.yql.yahoo.com/v1/video/sapi/streams/' + video_id
,
203 video_id
, 'Downloading %s JSON metadata' % fmt
,
204 headers
=self
.geo_verification_headers(), query
={
206 'region': country
.upper(),
207 })['query']['results']['mediaObj'][0]
208 msg
= media_obj
.get('status', {}).get('msg')
210 for s
in media_obj
.get('streams', []):
213 if not host
or not path
:
216 if s
.get('format') == 'm3u8':
217 formats
.extend(self
._extract
_m
3u8_formats
(
218 s_url
, video_id
, 'mp4', m3u8_id
='hls', fatal
=False))
220 tbr
= int_or_none(s
.get('bitrate'))
223 'format_id': fmt
+ ('-%d' % tbr
if tbr
else ''),
224 'width': int_or_none(s
.get('width')),
225 'height': int_or_none(s
.get('height')),
227 'fps': int_or_none(s
.get('framerate')),
230 for cc
in media_obj
.get('closedcaptions', []):
231 cc_url
= cc
.get('url')
232 if not cc_url
or cc_url
in urls
:
235 subtitles
.setdefault(cc
.get('lang') or 'en-US', []).append({
237 'ext': mimetype2ext(cc
.get('content_type')),
240 streaming_url
= video
.get('streaming_url')
241 if streaming_url
and not is_live
:
242 formats
.extend(self
._extract
_m
3u8_formats
(
243 streaming_url
, video_id
, 'mp4',
244 'm3u8_native', m3u8_id
='hls', fatal
=False))
246 if not formats
and msg
== 'geo restricted':
247 self
.raise_geo_restricted(metadata_available
=True)
249 self
._sort
_formats
(formats
)
252 for thumb
in video
.get('thumbnails', []):
253 thumb_url
= thumb
.get('url')
257 'id': thumb
.get('tag'),
258 'url': thumb
.get('url'),
259 'width': int_or_none(thumb
.get('width')),
260 'height': int_or_none(thumb
.get('height')),
263 series_info
= video
.get('series_info') or {}
267 'title': self
._live
_title
(title
) if is_live
else title
,
269 'thumbnails': thumbnails
,
270 'description': clean_html(video
.get('description')),
271 'timestamp': parse_iso8601(video
.get('publish_time')),
272 'subtitles': subtitles
,
273 'duration': int_or_none(video
.get('duration')),
274 'view_count': int_or_none(video
.get('view_count')),
276 'series': video
.get('show_name'),
277 'season_number': int_or_none(series_info
.get('season_number')),
278 'episode_number': int_or_none(series_info
.get('episode_number')),
281 def _real_extract(self
, url
):
282 url
, country
, display_id
= self
._match
_valid
_url
(url
).groups()
286 country
= country
.split('-')[0]
288 items
= self
._download
_json
(
289 'https://%s.yahoo.com/caas/content/article' % country
, display_id
,
290 'Downloading content JSON metadata', query
={
294 item
= items
['data']['partnerData']
295 if item
.get('type') != 'video':
298 cover
= item
.get('cover') or {}
299 if cover
.get('type') == 'yvideo':
300 cover_url
= cover
.get('url')
302 entries
.append(self
.url_result(
303 cover_url
, 'Yahoo', cover
.get('uuid')))
305 for e
in (item
.get('body') or []):
306 if e
.get('type') == 'videoIframe':
307 iframe_url
= e
.get('url')
309 entries
.append(self
.url_result(iframe_url
))
311 if item
.get('type') == 'storywithleadvideo':
312 iframe_url
= try_get(item
, lambda x
: x
['meta']['player']['url'])
314 entries
.append(self
.url_result(iframe_url
))
316 self
.report_warning("Yahoo didn't provide an iframe url for this storywithleadvideo")
318 if items
.get('markup'):
320 self
.url_result(yt_url
) for yt_url
in YoutubeIE
._extract
_urls
(items
['markup']))
322 return self
.playlist_result(
323 entries
, item
.get('uuid'),
324 item
.get('title'), item
.get('summary'))
326 info
= self
._extract
_yahoo
_video
(item
['uuid'], country
)
327 info
['display_id'] = display_id
331 class YahooSearchIE(SearchInfoExtractor
):
332 IE_DESC
= 'Yahoo screen search'
334 IE_NAME
= 'screen.yahoo:search'
335 _SEARCH_KEY
= 'yvsearch'
337 def _get_n_results(self
, query
, n
):
338 """Get a specified number of results for a query"""
340 for pagenum
in itertools
.count(0):
341 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)
342 info
= self
._download
_json
(result_url
, query
,
343 note
='Downloading results page ' + str(pagenum
+ 1))
345 results
= info
['results']
347 for (i
, r
) in enumerate(results
):
348 if (pagenum
* 30) + i
>= n
:
350 mobj
= re
.search(r
'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r
)
351 e
= self
.url_result('http://' + mobj
.group('url'), 'Yahoo')
353 if (pagenum
* 30 + i
>= n
) or (m
['last'] >= (m
['total'] - 1)):
363 class YahooGyaOPlayerIE(InfoExtractor
):
364 IE_NAME
= 'yahoo:gyao:player'
365 _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})'
367 'url': 'https://gyao.yahoo.co.jp/player/00998/v00818/v0000000000000008564/',
369 'id': '5993125228001',
371 'title': 'フューリー 【字幕版】',
372 'description': 'md5:21e691c798a15330eda4db17a8fe45a5',
373 'uploader_id': '4235717419001',
374 'upload_date': '20190124',
375 'timestamp': 1548294365,
379 'skip_download': True,
382 'url': 'https://streaming.yahoo.co.jp/c/y/01034/v00133/v0000000000000000706/',
383 'only_matching': True,
385 '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',
386 'only_matching': True,
388 'url': 'https://gyao.yahoo.co.jp/episode/5fa1226c-ef8d-4e93-af7a-fd92f4e30597',
389 'only_matching': True,
393 def _real_extract(self
, url
):
394 video_id
= self
._match
_id
(url
).replace('/', ':')
395 headers
= self
.geo_verification_headers()
396 headers
['Accept'] = 'application/json'
397 resp
= self
._download
_json
(
398 'https://gyao.yahoo.co.jp/apis/playback/graphql', video_id
, query
={
399 'appId': 'dj00aiZpPUNJeDh2cU1RazU3UCZzPWNvbnN1bWVyc2VjcmV0Jng9NTk-',
401 content(parameter: {contentId: "%s", logicaAgent: PC_WEB}) {
411 content
= resp
['data']['content']
413 msg
= resp
['errors'][0]['message']
414 if msg
== 'not in japan':
415 self
.raise_geo_restricted(countries
=['JP'])
416 raise ExtractorError(msg
)
417 video
= content
['video']
419 '_type': 'url_transparent',
421 'title': video
['title'],
423 'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video
['delivery']['id'],
424 {'geo_countries': ['JP']}
),
425 'ie_key': BrightcoveNewIE
.ie_key(),
429 class YahooGyaOIE(InfoExtractor
):
430 IE_NAME
= 'yahoo:gyao'
431 _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})'
433 'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/',
435 'id': '00449:v03102',
439 'url': 'https://streaming.yahoo.co.jp/p/y/01034/v00133/',
440 'only_matching': True,
442 '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',
443 'only_matching': True,
445 'url': 'https://gyao.yahoo.co.jp/title/5b025a49-b2e5-4dc7-945c-09c6634afacf',
446 'only_matching': True,
449 def _real_extract(self
, url
):
450 program_id
= self
._match
_id
(url
).replace('/', ':')
451 videos
= self
._download
_json
(
452 'https://gyao.yahoo.co.jp/api/programs/%s/videos' % program_id
, program_id
)['videos']
455 video_id
= video
.get('id')
458 entries
.append(self
.url_result(
459 'https://gyao.yahoo.co.jp/player/%s/' % video_id
.replace(':', '/'),
460 YahooGyaOPlayerIE
.ie_key(), video_id
))
461 return self
.playlist_result(entries
, program_id
)
464 class YahooJapanNewsIE(InfoExtractor
):
465 IE_NAME
= 'yahoo:japannews'
466 IE_DESC
= 'Yahoo! Japan News'
467 _VALID_URL
= r
'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)[^\d]*(?P<id>\d[\d-]*\d)?'
468 _GEO_COUNTRIES
= ['JP']
470 'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int',
474 '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',
475 '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))',
476 'thumbnail': r
're:^https?://.*\.[a-zA-Z\d]{3,4}$',
479 'skip_download': True,
483 'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04',
484 'only_matching': True,
486 'url': 'https://headlines.yahoo.co.jp/videonews/',
487 'only_matching': True,
489 'url': 'https://news.yahoo.co.jp',
490 'only_matching': True,
492 'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/',
493 'only_matching': True,
495 'url': 'https://news.yahoo.co.jp/feature/1356',
496 'only_matching': True
499 def _extract_formats(self
, json_data
, content_id
):
502 video_data
= try_get(
504 lambda x
: x
['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
506 for vid
in video_data
or []:
507 delivery
= vid
.get('delivery')
508 url
= url_or_none(vid
.get('Url'))
509 if not delivery
or not url
:
511 elif delivery
== 'hls':
513 self
._extract
_m
3u8_formats
(
514 url
, content_id
, 'mp4', 'm3u8_native',
515 m3u8_id
='hls', fatal
=False))
519 'format_id': 'http-%s' % compat_str(vid
.get('bitrate', '')),
520 'height': int_or_none(vid
.get('height')),
521 'width': int_or_none(vid
.get('width')),
522 'tbr': int_or_none(vid
.get('bitrate')),
524 self
._remove
_duplicate
_formats
(formats
)
525 self
._sort
_formats
(formats
)
529 def _real_extract(self
, url
):
530 mobj
= self
._match
_valid
_url
(url
)
531 host
= mobj
.group('host')
532 display_id
= mobj
.group('id') or host
534 webpage
= self
._download
_webpage
(url
, display_id
)
536 title
= self
._html
_search
_meta
(
537 ['og:title', 'twitter:title'], webpage
, 'title', default
=None
538 ) or self
._html
_search
_regex
('<title>([^<]+)</title>', webpage
, 'title')
540 if display_id
== host
:
541 # Headline page (w/ multiple BC playlists) ('news.yahoo.co.jp', 'headlines.yahoo.co.jp/videonews/', ...)
542 stream_plists
= re
.findall(r
'plist=(\d+)', webpage
) or re
.findall(r
'plist["\']:\s
*["\']([^"\']+)', webpage)
546 'http
://players
.brightcove
.net
/5690807595001/HyZNerRl7_default
/index
.html?playlistId
=%s' % plist_id,
547 {'geo_countries': ['JP']}),
548 ie='BrightcoveNew
', video_id=plist_id)
549 for plist_id in stream_plists]
550 return self.playlist_result(entries, playlist_title=title)
553 description = self._html_search_meta(
554 ['og
:description
', 'description
', 'twitter
:description
'],
555 webpage, 'description
', default=None)
556 thumbnail = self._og_search_thumbnail(
557 webpage, default=None) or self._html_search_meta(
558 'twitter
:image
', webpage, 'thumbnail
', default=None)
559 space_id = self._search_regex([
560 r'<script
[^
>]+class=["\']yvpub-player["\'][^
>]+spaceid
=([^
&"\']+)',
561 r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
562 r'<!--\s
+SpaceID
=(\d
+)'
563 ], webpage, 'spaceid
')
565 content_id = self._search_regex(
566 r'<script
[^
>]+class=["\']yvpub-player["\'][^
>]+contentid
=(?P
<contentid
>[^
&"\']+)',
567 webpage, 'contentid', group='contentid')
569 json_data = self._download_json(
570 'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
573 'appid': 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-',
575 'space_id': space_id,
577 'ak': hashlib.md5('_'.join((space_id, host)).encode()).hexdigest(),
578 'device_type': '1100',
580 formats = self._extract_formats(json_data, content_id)
585 'description': description,
586 'thumbnail': thumbnail,