]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/presstv.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..utils
import remove_start
10 class PressTVIE(InfoExtractor
):
11 _VALID_URL
= r
'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>\d+)/(?P<m>\d+)/(?P<d>\d+)/(?P<id>\d+)/(?P<display_id>[^/]+)?'
14 'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/',
15 'md5': '5d7e3195a447cb13e9267e931d8dd5a5',
18 'display_id': 'Australian-sewerage-treatment-facility-',
20 'title': 'Organic mattresses used to clean waste water',
21 'upload_date': '20160409',
22 'thumbnail': r
're:^https?://.*\.jpg',
23 'description': 'md5:20002e654bbafb6908395a5c0cfcd125'
27 def _real_extract(self
, url
):
28 mobj
= re
.match(self
._VALID
_URL
, url
)
29 video_id
= mobj
.group('id')
30 display_id
= mobj
.group('display_id') or video_id
32 webpage
= self
._download
_webpage
(url
, display_id
)
34 # extract video URL from webpage
35 video_url
= self
._hidden
_inputs
(webpage
)['inpPlayback']
37 # build list of available formats
38 # specified in http://www.presstv.ir/Scripts/playback.js
39 base_url
= 'http://192.99.219.222:82/presstv'
48 'url': base_url
+ video_url
[:-4] + extension
,
49 'format_id': '%dp' % height
,
51 } for height
, extension
in _formats
]
53 # extract video metadata
55 self
._html
_search
_meta
('title', webpage
, fatal
=True), 'PressTV-')
57 thumbnail
= self
._og
_search
_thumbnail
(webpage
)
58 description
= self
._og
_search
_description
(webpage
)
60 upload_date
= '%04d%02d%02d' % (
68 'display_id': display_id
,
71 'thumbnail': thumbnail
,
72 'upload_date': upload_date
,
73 'description': description