]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/archiveorg.py
1 from __future__
import unicode_literals
3 from .common
import InfoExtractor
10 class ArchiveOrgIE(InfoExtractor
):
11 IE_NAME
= 'archive.org'
12 IE_DESC
= 'archive.org videos'
13 _VALID_URL
= r
'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
15 'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
16 'md5': '8af1d4cf447933ed3c7f4871162602db',
18 'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
20 'title': '1968 Demo - FJCC Conference Presentation Reel #1',
21 'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
22 'upload_date': '19681210',
23 'uploader': 'SRI International'
26 'url': 'https://archive.org/details/Cops1922',
27 'md5': '0869000b4ce265e8ca62738b336b268a',
31 'title': 'Buster Keaton\'s "Cops" (1922)',
32 'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
35 'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
36 'only_matching': True,
39 def _real_extract(self
, url
):
40 video_id
= self
._match
_id
(url
)
41 webpage
= self
._download
_webpage
(
42 'http://archive.org/embed/' + video_id
, video_id
)
43 jwplayer_playlist
= self
._parse
_json
(self
._search
_regex
(
44 r
"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
45 webpage
, 'jwplayer playlist'), video_id
)
46 info
= self
._parse
_jwplayer
_data
(
47 {'playlist': jwplayer_playlist
}, video_id
, base_url
=url
)
49 def get_optional(metadata
, field
):
50 return metadata
.get(field
, [None])[0]
52 metadata
= self
._download
_json
(
53 'http://archive.org/details/' + video_id
, video_id
, query
={
57 'title': get_optional(metadata
, 'title') or info
.get('title'),
58 'description': clean_html(get_optional(metadata
, 'description')),
60 if info
.get('_type') != 'playlist':
62 'uploader': get_optional(metadata
, 'creator'),
63 'upload_date': unified_strdate(get_optional(metadata
, 'date')),