]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/snotr.py
2 from __future__
import unicode_literals
5 from .common
import InfoExtractor
13 class SnotrIE(InfoExtractor
):
14 _VALID_URL
= r
'http?://(?:www\.)?snotr\.com/video/(?P<id>\d+)/([\w]+)'
16 'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
20 'title': 'Drone flying through fireworks!',
22 'filesize_approx': 40700000,
23 'description': 'A drone flying through Fourth of July Fireworks',
24 'thumbnail': r
're:^https?://.*\.jpg$',
26 'expected_warnings': ['description'],
28 'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
32 'title': 'David Letteman - George W. Bush Top 10',
34 'filesize_approx': 8500000,
35 'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
36 'thumbnail': r
're:^https?://.*\.jpg$',
40 def _real_extract(self
, url
):
41 mobj
= self
._match
_valid
_url
(url
)
42 video_id
= mobj
.group('id')
44 webpage
= self
._download
_webpage
(url
, video_id
)
45 title
= self
._og
_search
_title
(webpage
)
47 description
= self
._og
_search
_description
(webpage
)
48 info_dict
= self
._parse
_html
5_media
_entries
(
49 url
, webpage
, video_id
, m3u8_entry_protocol
='m3u8_native')[0]
51 view_count
= str_to_int(self
._html
_search
_regex
(
52 r
'<p[^>]*>\s*<strong[^>]*>Views:</strong>\s*<span[^>]*>([\d,\.]+)',
53 webpage
, 'view count', fatal
=False))
55 duration
= parse_duration(self
._html
_search
_regex
(
56 r
'<p[^>]*>\s*<strong[^>]*>Length:</strong>\s*<span[^>]*>([\d:]+)',
57 webpage
, 'duration', fatal
=False))
59 filesize_approx
= parse_filesize(self
._html
_search
_regex
(
60 r
'<p[^>]*>\s*<strong[^>]*>Filesize:</strong>\s*<span[^>]*>([^<]+)',
61 webpage
, 'filesize', fatal
=False))
65 'description': description
,
67 'view_count': view_count
,
69 'filesize_approx': filesize_approx
,