]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/imdb.py
1 from __future__
import unicode_literals
7 from .common
import InfoExtractor
19 class ImdbIE(InfoExtractor
):
21 IE_DESC
= 'Internet Movie Database trailers'
22 _VALID_URL
= r
'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P<id>\d+)'
25 'url': 'http://www.imdb.com/video/imdb/vi2524815897',
30 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
32 'thumbnail': r
're:^https?://.+\.jpg',
35 'url': 'https://www.imdb.com/video/vi3516832537',
39 'title': 'Paul: U.S. Trailer #1',
40 'description': 'md5:17fcc4fe11ec29b4399be9d4c5ef126c',
42 'thumbnail': r
're:^https?://.+\.jpg',
45 'url': 'http://www.imdb.com/video/_/vi2524815897',
46 'only_matching': True,
48 'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
49 'only_matching': True,
51 'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
52 'only_matching': True,
54 'url': 'http://www.imdb.com/videoplayer/vi1562949145',
55 'only_matching': True,
57 'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
58 'only_matching': True,
60 'url': 'https://www.imdb.com/list/ls009921623/videoplayer/vi260482329',
61 'only_matching': True,
64 def _real_extract(self
, url
):
65 video_id
= self
._match
_id
(url
)
66 webpage
= self
._download
_webpage
(f
'https://www.imdb.com/video/vi{video_id}', video_id
)
67 info
= self
._search
_nextjs
_data
(webpage
, video_id
)
68 video_info
= traverse_obj(info
, ('props', 'pageProps', 'videoPlaybackData', 'video'), default
={})
69 title
= (traverse_obj(video_info
, ('name', 'value'), ('primaryTitle', 'titleText', 'text'))
70 or self
._html
_search
_meta
(('og:title', 'twitter:title'), webpage
, default
=None)
71 or self
._html
_extract
_title
(webpage
))
72 data
= video_info
.get('playbackURLs') or try_get(self
._download
_json
(
73 'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id
,
75 'key': base64
.b64encode(json
.dumps({
76 'type': 'VIDEO_PLAYER',
77 'subType': 'FORCE_LEGACY',
78 'id': 'vi%s' % video_id
,
79 }).encode()).decode(),
80 }), lambda x
: x
[0]['videoLegacyEncodings'])
81 quality
= qualities(('SD', '480p', '720p', '1080p'))
82 formats
, subtitles
= [], {}
84 if not encoding
or not isinstance(encoding
, dict):
86 video_url
= url_or_none(encoding
.get('url'))
89 ext
= mimetype2ext(encoding
.get(
90 'mimeType')) or determine_ext(video_url
)
92 fmts
, subs
= self
._extract
_m
3u8_formats
_and
_subtitles
(
93 video_url
, video_id
, 'mp4', entry_protocol
='m3u8_native',
94 preference
=1, m3u8_id
='hls', fatal
=False)
95 subtitles
= self
._merge
_subtitles
(subtitles
, subs
)
98 format_id
= traverse_obj(encoding
, ('displayName', 'value'), 'definition')
100 'format_id': format_id
,
103 'quality': quality(format_id
),
105 self
._sort
_formats
(formats
)
110 'alt_title': info
.get('videoSubTitle'),
112 'description': try_get(video_info
, lambda x
: x
['description']['value']),
113 'thumbnail': url_or_none(try_get(video_info
, lambda x
: x
['thumbnail']['url'])),
114 'duration': int_or_none(try_get(video_info
, lambda x
: x
['runtime']['value'])),
115 'subtitles': subtitles
,
119 class ImdbListIE(InfoExtractor
):
120 IE_NAME
= 'imdb:list'
121 IE_DESC
= 'Internet Movie Database lists'
122 _VALID_URL
= r
'https?://(?:www\.)?imdb\.com/list/ls(?P<id>\d{9})(?!/videoplayer/vi\d+)'
124 'url': 'https://www.imdb.com/list/ls009921623/',
127 'title': 'The Bourne Legacy',
128 'description': 'A list of trailers, clips, and more from The Bourne Legacy, starring Jeremy Renner and Rachel Weisz.',
133 def _real_extract(self
, url
):
134 list_id
= self
._match
_id
(url
)
135 webpage
= self
._download
_webpage
(url
, list_id
)
137 self
.url_result('http://www.imdb.com' + m
, 'Imdb')
138 for m
in re
.findall(r
'href="(/list/ls%s/videoplayer/vi[^"]+)"' % list_id
, webpage
)]
140 list_title
= self
._html
_search
_regex
(
141 r
'<h1[^>]+class="[^"]*header[^"]*"[^>]*>(.*?)</h1>',
142 webpage
, 'list title')
143 list_description
= self
._html
_search
_regex
(
144 r
'<div[^>]+class="[^"]*list-description[^"]*"[^>]*><p>(.*?)</p>',
145 webpage
, 'list description')
147 return self
.playlist_result(entries
, list_id
, list_title
, list_description
)