]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/lrt.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
15 class LRTIE(InfoExtractor
):
17 _VALID_URL
= r
'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)'
20 'url': 'http://www.lrt.lt/mediateka/irasas/54391/',
21 'md5': 'fe44cf7e4ab3198055f2c598fc175cb0',
25 'title': 'Septynios Kauno dienos',
26 'description': 'md5:24d84534c7dc76581e59f5689462411a',
33 'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/',
34 'md5': '389da8ca3cad0f51d12bed0c844f6a0a',
38 'title': 'Kita tema 2016-09-05 15:05',
39 'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
46 def _real_extract(self
, url
):
47 video_id
= self
._match
_id
(url
)
48 webpage
= self
._download
_webpage
(url
, video_id
)
50 title
= remove_end(self
._og
_search
_title
(webpage
), ' - LRT')
53 for _
, file_url
in re
.findall(
54 r
'file\s*:\s*(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1', webpage):
55 ext = determine_ext(file_url)
56 if ext not in ('m3u8
', 'mp3
'):
58 # mp3 served as m3u8 produces stuttered media file
59 if ext == 'm3u8
' and '.mp3
' in file_url:
62 formats.extend(self._extract_m3u8_formats(
63 file_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
70 self._sort_formats(formats)
72 thumbnail = self._og_search_thumbnail(webpage)
73 description = self._og_search_description(webpage)
74 duration = parse_duration(self._search_regex(
75 r'var\s
+record_len\s
*=\s
*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1',
76 webpage, 'duration', default=None, group='duration'))
78 view_count = int_or_none(self._html_search_regex(
79 r'<div[^>]+class=(["\']).*?record
-desc
-seen
.*?\
1[^
>]*>(?P
<count
>.+?
)</div
>',
80 webpage, 'view count
', fatal=False, group='count
'))
81 like_count = int_or_none(self._search_regex(
82 r'<span
[^
>]+id=(["\'])flikesCount.*?\1>(?P<count>\d+)<',
83 webpage, 'like count', fatal=False, group='count'))
89 'thumbnail': thumbnail,
90 'description': description,
92 'view_count': view_count,
93 'like_count': like_count,