]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/go.py
3 from .adobepass
import AdobePassIE
18 class GoIE(AdobePassIE
):
22 'requestor_id': 'ABC',
26 'requestor_id': 'ABCFamily',
28 'watchdisneychannel': {
30 'resource_id': 'Disney',
32 'watchdisneyjunior': {
34 'resource_id': 'DisneyJunior',
38 'resource_id': 'DisneyXD',
42 'resource_id': 'Disney',
46 'requestor_id': 'dtci',
52 (?:{}\.)?go|fxnow\.fxnetworks|
53 (?:www\.)?(?:abc|freeform|disneynow)
56 (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
57 (?:[^/]+/)*(?P<display_id>[^/?\#]+)
59 '''.format(r
'\.|'.join(list(_SITE_INFO
.keys())))
61 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
65 'title': 'The Traitor in the White House',
66 'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
70 'skip_download': True,
72 'skip': 'This content is no longer available.',
74 'url': 'https://disneynow.com/shows/big-hero-6-the-series',
79 'playlist_mincount': 51,
81 'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
84 'title': 'This Guilty Blood',
85 'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
87 'episode': 'Episode 1',
88 'upload_date': '20170102',
90 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abcf/Shadowhunters/video/201/ae5f75608d86bf88aa4f9f4aa76ab1b7/579x325-Q100_ae5f75608d86bf88aa4f9f4aa76ab1b7.jpg',
93 'series': 'Shadowhunters',
95 'timestamp': 1483387200,
99 'geo_bypass_ip_block': '3.244.239.0/24',
101 'skip_download': True,
104 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-04/12-the-knock',
106 'id': 'VDKA26050359',
107 'title': 'The Knock',
108 'description': 'md5:0c2947e3ada4c31f28296db7db14aa64',
111 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abc/TheRookie/video/412/daf830d06e83b11eaf5c0a299d993ae3/1556x876-Q75_daf830d06e83b11eaf5c0a299d993ae3.jpg',
112 'episode': 'Episode 12',
114 'season': 'Season 4',
115 'timestamp': 1642975200,
116 'episode_number': 12,
117 'upload_date': '20220123',
118 'series': 'The Rookie',
122 'geo_bypass_ip_block': '3.244.239.0/24',
124 'skip_download': True,
127 'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
129 'id': 'VDKA12782841',
130 'title': 'First Look: Better Things - Season 2',
131 'description': 'md5:fa73584a95761c605d9d54904e35b407',
134 'upload_date': '20170825',
136 'series': 'Better Things',
137 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/fx/BetterThings/video/12782841/b6b05e58264121cc2c98811318e6d507/1556x876-Q75_b6b05e58264121cc2c98811318e6d507.jpg',
138 'timestamp': 1503661074,
141 'geo_bypass_ip_block': '3.244.239.0/24',
143 'skip_download': True,
146 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
147 'only_matching': True,
149 'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
150 'only_matching': True,
153 'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
154 'only_matching': True,
157 'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
158 'only_matching': True,
160 'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
161 'only_matching': True,
163 'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
164 'only_matching': True,
167 def _extract_videos(self
, brand
, video_id
='-1', show_id
='-1'):
168 display_id
= video_id
if video_id
!= '-1' else show_id
169 return self
._download
_json
(
170 f
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/{brand}/001/-1/{show_id}/-1/{video_id}/-1/-1.json',
173 def _real_extract(self
, url
):
174 mobj
= self
._match
_valid
_url
(url
)
175 sub_domain
= remove_start(remove_end(mobj
.group('sub_domain') or '', '.go'), 'www.')
176 video_id
, display_id
= mobj
.group('id', 'display_id')
177 site_info
= self
._SITE
_INFO
.get(sub_domain
, {})
178 brand
= site_info
.get('brand')
179 if not video_id
or not site_info
:
180 webpage
= self
._download
_webpage
(url
, display_id
or video_id
)
181 data
= self
._parse
_json
(
183 r
'["\']__abc_com__
["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
184 'data', default='{}'),
185 display_id or video_id, fatal=False)
186 # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
187 layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
192 (lambda x: x['videoid'], lambda x: x['video']['id']),
195 video_id = self._search_regex(
197 # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
198 # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
199 r'data-video-id=["\']*(VDKA\w
+)',
200 # page.analytics.videoIdCode
201 r'\bvideoIdCode
["\']\s*:\s*["\']((?
:vdka|VDKA
)\w
+)',
202 # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
203 r'\b(?
:video
)?
id["\']\s*:\s*["\'](VDKA\w
+)',
204 ), webpage, 'video
id', default=video_id)
206 brand = self._search_regex(
207 (r'data
-brand
=\s
*["\']\s*(\d+)',
208 r'data-page-brand=\s*["\']\s
*(\d
+)'), webpage, 'brand
',
211 si for _, si in self._SITE_INFO.items()
212 if si.get('brand
') == brand)
214 # show extraction works for Disney, DisneyJunior and DisneyXD
215 # ABC and Freeform has different layout
216 show_id = self._search_regex(r'data
-show
-id=["\']*(SH\d+)', webpage, 'show id')
217 videos = self._extract_videos(brand, show_id=show_id)
218 show_title = self._search_regex(r'data-show-title="([^
"]+)"', webpage, 'show title
', fatal=False)
221 entries.append(self.url_result(
222 video['url
'], 'Go
', video.get('id'), video.get('title
')))
224 return self.playlist_result(entries, show_id, show_title)
225 video_data = self._extract_videos(brand, video_id)[0]
226 video_id = video_data['id']
227 title = video_data['title
']
231 for asset in video_data.get('assets
', {}).get('asset
', []):
232 asset_url = asset.get('value
')
235 format_id = asset.get('format
')
236 ext = determine_ext(asset_url)
238 video_type = video_data.get('type')
240 'video_id
': video_data['id'],
241 'video_type
': video_type,
245 if video_data.get('accesslevel
') == '1':
246 requestor_id = site_info.get('requestor_id
', 'DisneyChannels
')
247 resource = site_info.get('resource_id
') or self._get_mvpd_resource(
248 requestor_id, title, video_id, None)
249 auth = self._extract_mvpd_auth(
250 url, video_id, requestor_id, resource)
254 'adobe_requestor_id
': requestor_id,
257 self._initialize_geo_bypass({'countries': ['US']})
258 entitlement = self._download_json(
259 'https
://api
.entitlement
.watchabc
.go
.com
/vp2
/ws
-secure
/entitlement
/2020/authorize
.json
',
260 video_id, data=urlencode_postdata(data))
261 errors = entitlement.get('errors
', {}).get('errors
', [])
264 if error.get('code
') == 1002:
265 self.raise_geo_restricted(
266 error['message
'], countries=['US
'])
267 error_message = ', '.join([error['message
'] for error in errors])
268 raise ExtractorError(f'{self.IE_NAME} said
: {error_message}
', expected=True)
269 asset_url += '?
' + entitlement['uplynkData
']['sessionKey
']
270 fmts, subs = self._extract_m3u8_formats_and_subtitles(
271 asset_url, video_id, 'mp4
', m3u8_id=format_id or 'hls
', fatal=False)
273 self._merge_subtitles(subs, target=subtitles)
276 'format_id
': format_id,
280 if re.search(r'(?
:/mp4
/source
/|_source\
.mp4
)', asset_url):
282 'format_id
': (f'{format_id}
-' if format_id else '') + 'SOURCE
',
286 mobj = re.search(r'/(\d
+)x(\d
+)/', asset_url)
288 height = int(mobj.group(2))
290 'format_id
': (f'{format_id}
-' if format_id else '') + f'{height}P
',
291 'width
': int(mobj.group(1)),
296 for cc in video_data.get('closedcaption
', {}).get('src
', []):
297 cc_url = cc.get('value
')
300 ext = determine_ext(cc_url)
303 subtitles.setdefault(cc.get('lang
'), []).append({
309 for thumbnail in video_data.get('thumbnails
', {}).get('thumbnail
', []):
310 thumbnail_url = thumbnail.get('value
')
311 if not thumbnail_url:
314 'url
': thumbnail_url,
315 'width
': int_or_none(thumbnail.get('width
')),
316 'height
': int_or_none(thumbnail.get('height
')),
322 'description
': video_data.get('longdescription
') or video_data.get('description
'),
323 'duration
': int_or_none(video_data.get('duration
', {}).get('value
'), 1000),
324 'age_limit
': parse_age_limit(video_data.get('tvrating
', {}).get('rating
')),
325 'episode_number
': int_or_none(video_data.get('episodenumber
')),
326 'series
': video_data.get('show
', {}).get('title
'),
327 'season_number
': int_or_none(video_data.get('season
', {}).get('num
')),
328 'thumbnails
': thumbnails,
330 'subtitles
': subtitles,
331 'timestamp
': unified_timestamp(traverse_obj(video_data, ('airdates
', 'airdate
', 0))),