]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/yahoo.py
2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
, SearchInfoExtractor
23 from .brightcove
import BrightcoveNewIE
26 class YahooIE(InfoExtractor
):
27 IE_DESC
= 'Yahoo screen and movies'
28 _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)'
30 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
32 'id': '2d25e626-2378-391f-ada0-ddaf1417e588',
34 'title': 'Julian Smith & Travis Legg Watch Julian Smith',
35 'description': 'Julian and Travis watch Julian Smith',
37 'timestamp': 1369812016,
38 'upload_date': '20130529',
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',
53 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html',
54 'md5': '71298482f7c64cbb7fa064e4553ff1c1',
56 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58',
58 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder',
59 'description': 'md5:f66c890e1490f4910a9953c941dee944',
61 'timestamp': 1414489862,
62 'upload_date': '20141028',
65 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
66 'md5': '88e209b417f173d86186bef6e4d1f160',
68 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521',
70 'title': 'China Moses Is Crazy About the Blues',
71 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
73 'timestamp': 1385722202,
74 'upload_date': '20131129',
77 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html',
78 'md5': '2a9752f74cb898af5d1083ea9f661b58',
80 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
82 'title': '\'True Story\' Trailer',
83 'description': 'True Story',
85 'timestamp': 1418919206,
86 'upload_date': '20141218',
89 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
90 'only_matching': True,
92 'note': 'NBC Sports embeds',
93 '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',
97 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
98 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
99 'upload_date': '20150313',
100 'uploader': 'NBCU-SPORTS',
101 'timestamp': 1426270238,
104 'url': 'https://tw.news.yahoo.com/-100120367.html',
105 'only_matching': True,
107 # Query result is embedded in webpage, but explicit request to video API fails with geo restriction
108 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html',
109 'md5': '4fbafb9c9b6f07aa8f870629f6671b35',
111 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504',
113 'title': 'Communitary - Community Episode 1: Ladders',
114 'description': 'md5:8fc39608213295748e1e289807838c97',
116 'timestamp': 1440436550,
117 'upload_date': '20150824',
118 'series': 'Communitary',
124 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html',
126 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff',
128 'title': '單車天使 - 中文版預',
129 'description': '中文版預',
130 'timestamp': 1476696196,
131 'upload_date': '20161017',
134 'skip_download': True,
137 # Contains both a Yahoo hosted video and multiple Youtube embeds
138 'url': 'https://www.yahoo.com/entertainment/gwen-stefani-reveals-the-pop-hit-she-passed-on-assigns-it-to-her-voice-contestant-instead-033045672.html',
140 'id': '46c5d95a-528f-3d03-b732-732fcadd51de',
141 'title': 'Gwen Stefani reveals the pop hit she passed on, assigns it to her \'Voice\' contestant instead',
142 'description': 'Gwen decided not to record this hit herself, but she decided it was the perfect fit for Kyndall Inskeep.',
146 'id': '966d4262-4fd1-3aaa-b45b-049ca6e38ba6',
148 'title': 'Gwen Stefani reveals she turned down one of Sia\'s best songs',
149 'description': 'On "The Voice" Tuesday, Gwen Stefani told Taylor Swift which Sia hit was almost hers.',
150 'timestamp': 1572406500,
151 'upload_date': '20191030',
157 'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019',
158 'description': 'md5:35b61e94c2ae214bc965ff4245f80d11',
159 'uploader': 'The Voice',
160 'uploader_id': 'NBCTheVoice',
161 'upload_date': '20191029',
167 'expected_warnings': ['HTTP Error 404'],
169 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html',
170 'only_matching': True,
172 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html',
173 'only_matching': True,
175 'url': 'https://www.yahoo.com/entertainment/v/longtime-cbs-news-60-minutes-032036500-cbs.html',
176 'only_matching': True,
179 def _real_extract(self
, url
):
180 url
, country
, display_id
= re
.match(self
._VALID
_URL
, url
).groups()
184 country
= country
.split('-')[0]
185 api_base
= 'https://%s.yahoo.com/_td/api/resource/' % country
187 for i
, uuid
in enumerate(['url=' + url
, 'ymedia-alias=' + display_id
]):
188 content
= self
._download
_json
(
189 api_base
+ 'content;getDetailView=true;uuids=["%s"]' % uuid
,
190 display_id
, 'Downloading content JSON metadata', fatal
=i
== 1)
192 item
= content
['items'][0]
195 if item
.get('type') != 'video':
198 cover
= item
.get('cover') or {}
199 if cover
.get('type') == 'yvideo':
200 cover_url
= cover
.get('url')
202 entries
.append(self
.url_result(
203 cover_url
, 'Yahoo', cover
.get('uuid')))
205 for e
in item
.get('body', []):
206 if e
.get('type') == 'videoIframe':
207 iframe_url
= e
.get('url')
210 entries
.append(self
.url_result(iframe_url
))
212 return self
.playlist_result(
213 entries
, item
.get('uuid'),
214 item
.get('title'), item
.get('summary'))
216 video_id
= item
['uuid']
217 video
= self
._download
_json
(
218 api_base
+ 'VideoService.videos;view=full;video_ids=["%s"]' % video_id
,
219 video_id
, 'Downloading video JSON metadata')[0]
220 title
= video
['title']
222 if country
== 'malaysia':
225 is_live
= video
.get('live_state') == 'live'
226 fmts
= ('m3u8',) if is_live
else ('webm', 'mp4')
232 media_obj
= self
._download
_json
(
233 'https://video-api.yql.yahoo.com/v1/video/sapi/streams/' + video_id
,
234 video_id
, 'Downloading %s JSON metadata' % fmt
,
235 headers
=self
.geo_verification_headers(), query
={
237 'region': country
.upper(),
238 })['query']['results']['mediaObj'][0]
239 msg
= media_obj
.get('status', {}).get('msg')
241 for s
in media_obj
.get('streams', []):
244 if not host
or not path
:
247 if s
.get('format') == 'm3u8':
248 formats
.extend(self
._extract
_m
3u8_formats
(
249 s_url
, video_id
, 'mp4', m3u8_id
='hls', fatal
=False))
251 tbr
= int_or_none(s
.get('bitrate'))
254 'format_id': fmt
+ ('-%d' % tbr
if tbr
else ''),
255 'width': int_or_none(s
.get('width')),
256 'height': int_or_none(s
.get('height')),
258 'fps': int_or_none(s
.get('framerate')),
261 for cc
in media_obj
.get('closedcaptions', []):
262 cc_url
= cc
.get('url')
263 if not cc_url
or cc_url
in urls
:
266 subtitles
.setdefault(cc
.get('lang') or 'en-US', []).append({
268 'ext': mimetype2ext(cc
.get('content_type')),
271 streaming_url
= video
.get('streaming_url')
272 if streaming_url
and not is_live
:
273 formats
.extend(self
._extract
_m
3u8_formats
(
274 streaming_url
, video_id
, 'mp4',
275 'm3u8_native', m3u8_id
='hls', fatal
=False))
277 if not formats
and msg
== 'geo restricted':
278 self
.raise_geo_restricted()
280 self
._sort
_formats
(formats
)
283 for thumb
in video
.get('thumbnails', []):
284 thumb_url
= thumb
.get('url')
288 'id': thumb
.get('tag'),
289 'url': thumb
.get('url'),
290 'width': int_or_none(thumb
.get('width')),
291 'height': int_or_none(thumb
.get('height')),
294 series_info
= video
.get('series_info') or {}
298 'title': self
._live
_title
(title
) if is_live
else title
,
300 'display_id': display_id
,
301 'thumbnails': thumbnails
,
302 'description': clean_html(video
.get('description')),
303 'timestamp': parse_iso8601(video
.get('publish_time')),
304 'subtitles': subtitles
,
305 'duration': int_or_none(video
.get('duration')),
306 'view_count': int_or_none(video
.get('view_count')),
308 'series': video
.get('show_name'),
309 'season_number': int_or_none(series_info
.get('season_number')),
310 'episode_number': int_or_none(series_info
.get('episode_number')),
314 class YahooSearchIE(SearchInfoExtractor
):
315 IE_DESC
= 'Yahoo screen search'
317 IE_NAME
= 'screen.yahoo:search'
318 _SEARCH_KEY
= 'yvsearch'
320 def _get_n_results(self
, query
, n
):
321 """Get a specified number of results for a query"""
323 for pagenum
in itertools
.count(0):
324 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)
325 info
= self
._download
_json
(result_url
, query
,
326 note
='Downloading results page ' + str(pagenum
+ 1))
328 results
= info
['results']
330 for (i
, r
) in enumerate(results
):
331 if (pagenum
* 30) + i
>= n
:
333 mobj
= re
.search(r
'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r
)
334 e
= self
.url_result('http://' + mobj
.group('url'), 'Yahoo')
336 if (pagenum
* 30 + i
>= n
) or (m
['last'] >= (m
['total'] - 1)):
346 class YahooGyaOPlayerIE(InfoExtractor
):
347 IE_NAME
= 'yahoo:gyao:player'
348 _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})'
350 'url': 'https://gyao.yahoo.co.jp/player/00998/v00818/v0000000000000008564/',
352 'id': '5993125228001',
354 'title': 'フューリー 【字幕版】',
355 'description': 'md5:21e691c798a15330eda4db17a8fe45a5',
356 'uploader_id': '4235717419001',
357 'upload_date': '20190124',
358 'timestamp': 1548294365,
362 'skip_download': True,
365 'url': 'https://streaming.yahoo.co.jp/c/y/01034/v00133/v0000000000000000706/',
366 'only_matching': True,
368 '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',
369 'only_matching': True,
372 def _real_extract(self
, url
):
373 video_id
= self
._match
_id
(url
).replace('/', ':')
374 video
= self
._download
_json
(
375 'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id
,
377 'fields': 'longDescription,title,videoId',
379 'X-User-Agent': 'Unknown Pc GYAO!/2.0.0 Web',
382 '_type': 'url_transparent',
384 'title': video
['title'],
386 'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video
['videoId'],
387 {'geo_countries': ['JP']}),
388 'description': video
.get('longDescription'),
389 'ie_key': BrightcoveNewIE
.ie_key(),
393 class YahooGyaOIE(InfoExtractor
):
394 IE_NAME
= 'yahoo:gyao'
395 _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})'
397 'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/',
399 'id': '00449:v03102',
403 'url': 'https://streaming.yahoo.co.jp/p/y/01034/v00133/',
404 'only_matching': True,
406 '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',
407 'only_matching': True,
410 def _real_extract(self
, url
):
411 program_id
= self
._match
_id
(url
).replace('/', ':')
412 videos
= self
._download
_json
(
413 'https://gyao.yahoo.co.jp/api/programs/%s/videos' % program_id
, program_id
)['videos']
416 video_id
= video
.get('id')
419 entries
.append(self
.url_result(
420 'https://gyao.yahoo.co.jp/player/%s/' % video_id
.replace(':', '/'),
421 YahooGyaOPlayerIE
.ie_key(), video_id
))
422 return self
.playlist_result(entries
, program_id
)
425 class YahooJapanNewsIE(InfoExtractor
):
426 IE_NAME
= 'yahoo:japannews'
427 IE_DESC
= 'Yahoo! Japan News'
428 _VALID_URL
= r
'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)[^\d]*(?P<id>\d[\d-]*\d)?'
429 _GEO_COUNTRIES
= ['JP']
431 'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int',
435 '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',
436 '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))',
437 'thumbnail': r
're:^https?://.*\.[a-zA-Z\d]{3,4}$',
440 'skip_download': True,
444 'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04',
445 'only_matching': True,
447 'url': 'https://headlines.yahoo.co.jp/videonews/',
448 'only_matching': True,
450 'url': 'https://news.yahoo.co.jp',
451 'only_matching': True,
453 'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/',
454 'only_matching': True,
456 'url': 'https://news.yahoo.co.jp/feature/1356',
457 'only_matching': True
460 def _extract_formats(self
, json_data
, content_id
):
463 video_data
= try_get(
465 lambda x
: x
['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
467 for vid
in video_data
or []:
468 delivery
= vid
.get('delivery')
469 url
= url_or_none(vid
.get('Url'))
470 if not delivery
or not url
:
472 elif delivery
== 'hls':
474 self
._extract
_m
3u8_formats
(
475 url
, content_id
, 'mp4', 'm3u8_native',
476 m3u8_id
='hls', fatal
=False))
480 'format_id': 'http-%s' % compat_str(vid
.get('bitrate', '')),
481 'height': int_or_none(vid
.get('height')),
482 'width': int_or_none(vid
.get('width')),
483 'tbr': int_or_none(vid
.get('bitrate')),
485 self
._remove
_duplicate
_formats
(formats
)
486 self
._sort
_formats
(formats
)
490 def _real_extract(self
, url
):
491 mobj
= re
.match(self
._VALID
_URL
, url
)
492 host
= mobj
.group('host')
493 display_id
= mobj
.group('id') or host
495 webpage
= self
._download
_webpage
(url
, display_id
)
497 title
= self
._html
_search
_meta
(
498 ['og:title', 'twitter:title'], webpage
, 'title', default
=None
499 ) or self
._html
_search
_regex
('<title>([^<]+)</title>', webpage
, 'title')
501 if display_id
== host
:
502 # Headline page (w/ multiple BC playlists) ('news.yahoo.co.jp', 'headlines.yahoo.co.jp/videonews/', ...)
503 stream_plists
= re
.findall(r
'plist=(\d+)', webpage
) or re
.findall(r
'plist["\']:\s
*["\']([^"\']+)', webpage)
507 'http
://players
.brightcove
.net
/5690807595001/HyZNerRl7_default
/index
.html?playlistId
=%s' % plist_id,
508 {'geo_countries
': ['JP
']}),
509 ie='BrightcoveNew
', video_id=plist_id)
510 for plist_id in stream_plists]
511 return self.playlist_result(entries, playlist_title=title)
514 description = self._html_search_meta(
515 ['og
:description
', 'description
', 'twitter
:description
'],
516 webpage, 'description
', default=None)
517 thumbnail = self._og_search_thumbnail(
518 webpage, default=None) or self._html_search_meta(
519 'twitter
:image
', webpage, 'thumbnail
', default=None)
520 space_id = self._search_regex([
521 r'<script
[^
>]+class=["\']yvpub-player["\'][^
>]+spaceid
=([^
&"\']+)',
522 r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
523 r'<!--\s
+SpaceID
=(\d
+)'
524 ], webpage, 'spaceid
')
526 content_id = self._search_regex(
527 r'<script
[^
>]+class=["\']yvpub-player["\'][^
>]+contentid
=(?P
<contentid
>[^
&"\']+)',
528 webpage, 'contentid', group='contentid')
530 json_data = self._download_json(
531 'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
534 'appid': 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-',
536 'space_id': space_id,
538 'ak': hashlib.md5('_'.join((space_id, host)).encode()).hexdigest(),
539 'device_type': '1100',
541 formats = self._extract_formats(json_data, content_id)
546 'description': description,
547 'thumbnail': thumbnail,