]>
jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/disney.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
17 class DisneyIE(InfoExtractor
):
19 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>[^/?#]+))'''
22 'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977',
24 'id': '545ed1857afee5a0ec239977',
26 'title': 'Moana - Trailer',
27 'description': 'A fun adventure for the entire Family! Bring home Moana on Digital HD Feb 21 & Blu-ray March 7',
28 'upload_date': '20170112',
32 'skip_download': True,
36 'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette',
38 'id': '5454e9f4e9804a552e3524c8',
40 'title': '"Intro" Featurette: Rogue One: A Star Wars Story',
41 'upload_date': '20170104',
42 '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.',
46 'skip_download': True,
49 'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2',
50 'only_matching': True,
52 'url': 'http://video.en.disneyme.com/watch/future-worm/robo-carp-2001-544b66002aa7353cdd3f5114',
53 'only_matching': True,
55 'url': 'http://video.disneyturkiye.com.tr/izle/7c-7-cuceler/kimin-sesi-zaten-5456f3d015f6b36c8afdd0e2',
56 'only_matching': True,
58 'url': 'http://disneyjunior.disney.com/embed/546a4798ddba3d1612e4005d',
59 'only_matching': True,
61 'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097',
62 'only_matching': True,
64 'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677',
65 'only_matching': True,
67 'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1',
68 'only_matching': True,
70 'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo',
71 'only_matching': True,
73 'url': 'http://disneychannel.de/sehen/soy-luna-folge-118-5518518987ba27f3cc729268',
74 'only_matching': True,
76 'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue',
77 'only_matching': True,
80 def _real_extract(self
, url
):
81 domain
, video_id
, display_id
= re
.match(self
._VALID
_URL
, url
).groups()
83 webpage
= self
._download
_webpage
(url
, display_id
)
84 grill
= re
.sub(r
'"\s*\+\s*"', '', self
._search
_regex
(
85 r
'Grill\.burger\s*=\s*({.+})\s*:',
86 webpage
, 'grill data'))
87 page_data
= next(s
for s
in self
._parse
_json
(grill
, display_id
)['stack'] if s
.get('type') == 'video')
88 video_data
= page_data
['data'][0]
90 webpage
= self
._download
_webpage
(
91 'http://%s/embed/%s' % (domain
, video_id
), video_id
)
92 page_data
= self
._parse
_json
(self
._search
_regex
(
93 r
'Disney\.EmbedVideo\s*=\s*({.+});',
94 webpage
, 'embed data'), video_id
)
95 video_data
= page_data
['video']
97 for external
in video_data
.get('externals', []):
98 if external
.get('source') == 'vevo':
99 return self
.url_result('vevo:' + external
['data_id'], 'Vevo')
101 video_id
= video_data
['id']
102 title
= video_data
['title']
105 for flavor
in video_data
.get('flavors', []):
106 flavor_format
= flavor
.get('format')
107 flavor_url
= flavor
.get('url')
108 if not flavor_url
or not re
.match(r
'https?://', flavor_url
) or flavor_format
== 'mp4_access':
110 tbr
= int_or_none(flavor
.get('bitrate'))
112 # wrong ks(Kaltura Signature) causes 404 Error
113 flavor_url
= update_url_query(flavor_url
, {'ks': ''}
)
114 m3u8_formats
= self
._extract
_m
3u8_formats
(
115 flavor_url
, video_id
, 'mp4',
116 m3u8_id
=flavor_format
, fatal
=False)
117 for f
in m3u8_formats
:
119 if '/fpshls/' in f
['url']:
125 format_id
.append(flavor_format
)
127 format_id
.append(compat_str(tbr
))
128 ext
= determine_ext(flavor_url
)
129 if flavor_format
== 'applehttp' or ext
== 'm3u8':
131 width
= int_or_none(flavor
.get('width'))
132 height
= int_or_none(flavor
.get('height'))
134 'format_id': '-'.join(format_id
),
140 'vcodec': 'none' if (width
== 0 and height
== 0) else None,
142 if not formats
and video_data
.get('expired'):
143 raise ExtractorError(
144 '%s said: %s' % (self
.IE_NAME
, page_data
['translations']['video_expired']),
146 self
._sort
_formats
(formats
)
149 for caption
in video_data
.get('captions', []):
150 caption_url
= caption
.get('url')
151 caption_format
= caption
.get('format')
152 if not caption_url
or caption_format
.startswith('unknown'):
154 subtitles
.setdefault(caption
.get('language', 'en'), []).append({
158 }.get(caption_format
, caption_format
),
164 'description': video_data
.get('description') or video_data
.get('short_desc'),
165 'thumbnail': video_data
.get('thumb') or video_data
.get('thumb_secure'),
166 'duration': int_or_none(video_data
.get('duration_sec')),
167 'upload_date': unified_strdate(video_data
.get('publish_date')),
169 'subtitles': subtitles
,