]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/dhm.py
1 from __future__
import unicode_literals
3 from .common
import InfoExtractor
4 from ..utils
import parse_duration
7 class DHMIE(InfoExtractor
):
8 IE_DESC
= 'Filmarchiv - Deutsches Historisches Museum'
9 _VALID_URL
= r
'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
12 'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
13 'md5': '11c475f670209bf6acca0b2b7ef51827',
15 'id': 'the-marshallplan-at-work-in-west-germany',
17 'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
18 'description': 'md5:1fabd480c153f97b07add61c44407c82',
20 'thumbnail': r
're:^https?://.*\.jpg$',
23 'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
24 'md5': '09890226332476a3e3f6f2cb74734aa5',
29 'thumbnail': r
're:^https?://.*\.jpg$',
33 def _real_extract(self
, url
):
34 playlist_id
= self
._match
_id
(url
)
36 webpage
= self
._download
_webpage
(url
, playlist_id
)
38 playlist_url
= self
._search
_regex
(
39 r
"file\s*:\s*'([^']+)'", webpage
, 'playlist url')
41 entries
= self
._extract
_xspf
_playlist
(playlist_url
, playlist_id
)
43 title
= self
._search
_regex
(
44 [r
'dc:title="([^"]+)"', r
'<title> »([^<]+)</title>'],
45 webpage
, 'title').strip()
46 description
= self
._html
_search
_regex
(
47 r
'<p><strong>Description:</strong>(.+?)</p>',
48 webpage
, 'description', default
=None)
49 duration
= parse_duration(self
._search
_regex
(
50 r
'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
51 webpage
, 'duration', default
=None))
55 'description': description
,
59 return self
.playlist_result(entries
, playlist_id
)