]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/disney.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
16 class DisneyIE(InfoExtractor
):
18 https?://(?P<domain>(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr|channel\.de)|(?:starwars|marvelkids)\.com))/(?:(?:embed/|(?:[^/]+/)+[\w-]+-)(?P<id>[a-z0-9]{24})|(?:[^/]+/)?(?P<display_id>[^/?#]+))'''
21 'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
23 'id': '545ed1857afee5a0ec239977',
25 'title': 'Moana - Trailer',
26 'description': 'A fun adventure for the entire Family! Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
27 'upload_date': '20170112',
31 'skip_download': True,
35 'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
37 'id': '5454e9f4e9804a552e3524c8',
39 'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
40 'upload_date': '20170104',
41 'description': 'Go behind-the-scenes of Rogue One: A Star Wars Story in this featurette with Director Gareth Edwards and the cast of the film.',
45 'skip_download': True,
48 'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
49 'only_matching': True,
51 'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
52 'only_matching': True,
54 'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
55 'only_matching': True,
57 'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
58 'only_matching': True,
60 'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
61 'only_matching': True,
63 'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
64 'only_matching': True,
66 'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
67 'only_matching': True,
69 'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
70 'only_matching': True,
72 'url': 'http://disneychannel.de/sehen/soy-luna-folge-118-5518518987ba27f3cc729268',
73 'only_matching': True,
75 'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue',
76 'only_matching': True,
79 def _real_extract(self
, url
):
80 domain
, video_id
, display_id
= self
._match
_valid
_url
(url
).groups()
82 webpage
= self
._download
_webpage
(url
, display_id
)
83 grill
= re
.sub(r
'"\s*\+\s*"', '', self
._search
_regex
(
84 r
'Grill\.burger\s*=\s*({.+})\s*:',
85 webpage
, 'grill data'))
86 page_data
= next(s
for s
in self
._parse
_json
(grill
, display_id
)['stack'] if s
.get('type') == 'video')
87 video_data
= page_data
['data'][0]
89 webpage
= self
._download
_webpage
(
90 'http://%s/embed/%s' % (domain
, video_id
), video_id
)
91 page_data
= self
._parse
_json
(self
._search
_regex
(
92 r
'Disney\.EmbedVideo\s*=\s*({.+});',
93 webpage
, 'embed data'), video_id
)
94 video_data
= page_data
['video']
96 for external
in video_data
.get('externals', []):
97 if external
.get('source') == 'vevo':
98 return self
.url_result('vevo:' + external
['data_id'], 'Vevo')
100 video_id
= video_data
['id']
101 title
= video_data
['title']
104 for flavor
in video_data
.get('flavors', []):
105 flavor_format
= flavor
.get('format')
106 flavor_url
= flavor
.get('url')
107 if not flavor_url
or not re
.match(r
'https?://', flavor_url
) or flavor_format
== 'mp4_access':
109 tbr
= int_or_none(flavor
.get('bitrate'))
111 # wrong ks(Kaltura Signature) causes 404 Error
112 flavor_url
= update_url_query(flavor_url
, {'ks': ''}
)
113 m3u8_formats
= self
._extract
_m
3u8_formats
(
114 flavor_url
, video_id
, 'mp4',
115 m3u8_id
=flavor_format
, fatal
=False)
116 for f
in m3u8_formats
:
118 if '/fpshls/' in f
['url']:
124 format_id
.append(flavor_format
)
126 format_id
.append(compat_str(tbr
))
127 ext
= determine_ext(flavor_url
)
128 if flavor_format
== 'applehttp' or ext
== 'm3u8':
130 width
= int_or_none(flavor
.get('width'))
131 height
= int_or_none(flavor
.get('height'))
133 'format_id': '-'.join(format_id
),
139 'vcodec': 'none' if (width
== 0 and height
== 0) else None,
141 if not formats
and video_data
.get('expired'):
142 self
.raise_no_formats(
143 '%s said: %s' % (self
.IE_NAME
, page_data
['translations']['video_expired']),
145 self
._sort
_formats
(formats
)
148 for caption
in video_data
.get('captions', []):
149 caption_url
= caption
.get('url')
150 caption_format
= caption
.get('format')
151 if not caption_url
or caption_format
.startswith('unknown'):
153 subtitles
.setdefault(caption
.get('language', 'en'), []).append({
157 }.get(caption_format
, caption_format
),
163 'description': video_data
.get('description') or video_data
.get('short_desc'),
164 'thumbnail': video_data
.get('thumb') or video_data
.get('thumb_secure'),
165 'duration': int_or_none(video_data
.get('duration_sec')),
166 'upload_date': unified_strdate(video_data
.get('publish_date')),
168 'subtitles': subtitles
,