]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/imdb.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
15 class ImdbIE(InfoExtractor
):
17 IE_DESC
= 'Internet Movie Database trailers'
18 _VALID_URL
= r
'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P<id>\d+)'
21 'url': 'http://www.imdb.com/video/imdb/vi2524815897',
25 'title': 'No. 2 from Ice Age: Continental Drift (2012)',
26 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
29 'url': 'http://www.imdb.com/video/_/vi2524815897',
30 'only_matching': True,
32 'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
33 'only_matching': True,
35 'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
36 'only_matching': True,
38 'url': 'http://www.imdb.com/videoplayer/vi1562949145',
39 'only_matching': True,
41 'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
42 'only_matching': True,
44 'url': 'https://www.imdb.com/list/ls009921623/videoplayer/vi260482329',
45 'only_matching': True,
48 def _real_extract(self
, url
):
49 video_id
= self
._match
_id
(url
)
50 webpage
= self
._download
_webpage
(
51 'https://www.imdb.com/videoplayer/vi' + video_id
, video_id
)
52 video_metadata
= self
._parse
_json
(self
._search
_regex
(
53 r
'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage
,
54 'video metadata'), video_id
)['videos']['videoMetadata']['vi' + video_id
]
55 title
= self
._html
_search
_meta
(
56 ['og:title', 'twitter:title'], webpage
) or self
._html
_search
_regex
(
57 r
'<title>(.+?)</title>', webpage
, 'title', fatal
=False) or video_metadata
['title']
59 quality
= qualities(('SD', '480p', '720p', '1080p'))
61 for encoding
in video_metadata
.get('encodings', []):
62 if not encoding
or not isinstance(encoding
, dict):
64 video_url
= url_or_none(encoding
.get('videoUrl'))
67 ext
= mimetype2ext(encoding
.get(
68 'mimeType')) or determine_ext(video_url
)
70 formats
.extend(self
._extract
_m
3u8_formats
(
71 video_url
, video_id
, 'mp4', entry_protocol
='m3u8_native',
72 m3u8_id
='hls', fatal
=False))
74 format_id
= encoding
.get('definition')
76 'format_id': format_id
,
79 'quality': quality(format_id
),
81 self
._sort
_formats
(formats
)
87 'description': video_metadata
.get('description'),
88 'thumbnail': video_metadata
.get('slate', {}).get('url'),
89 'duration': parse_duration(video_metadata
.get('duration')),
93 class ImdbListIE(InfoExtractor
):
95 IE_DESC
= 'Internet Movie Database lists'
96 _VALID_URL
= r
'https?://(?:www\.)?imdb\.com/list/ls(?P<id>\d{9})(?!/videoplayer/vi\d+)'
98 'url': 'https://www.imdb.com/list/ls009921623/',
101 'title': 'The Bourne Legacy',
102 'description': 'A list of trailers, clips, and more from The Bourne Legacy, starring Jeremy Renner and Rachel Weisz.',
107 def _real_extract(self
, url
):
108 list_id
= self
._match
_id
(url
)
109 webpage
= self
._download
_webpage
(url
, list_id
)
111 self
.url_result('http://www.imdb.com' + m
, 'Imdb')
112 for m
in re
.findall(r
'href="(/list/ls%s/videoplayer/vi[^"]+)"' % list_id
, webpage
)]
114 list_title
= self
._html
_search
_regex
(
115 r
'<h1[^>]+class="[^"]*header[^"]*"[^>]*>(.*?)</h1>',
116 webpage
, 'list title')
117 list_description
= self
._html
_search
_regex
(
118 r
'<div[^>]+class="[^"]*list-description[^"]*"[^>]*><p>(.*?)</p>',
119 webpage
, 'list description')
121 return self
.playlist_result(entries
, list_id
, list_title
, list_description
)