]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/tvnet.py
3 from .common
import InfoExtractor
11 class TVNetIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:[^/]+)\.tvnet\.gov\.vn/[^/]+/(?:\d+/)?(?P<id>\d+)(?:/|$)'
15 'url': 'http://de.tvnet.gov.vn/video/109788/vtv1---bac-tuyet-tai-lao-cai-va-ha-giang/tin-nong-24h',
16 'md5': 'b4d7abe0252c9b47774760b7519c7558',
20 'title': 'VTV1 - Bắc tuyết tại Lào Cai và Hà Giang',
21 'thumbnail': r
're:(?i)https?://.*\.(?:jpg|png)',
27 'url': 'http://vn.tvnet.gov.vn/radio/27017/vov1---ban-tin-chieu-10062018/doi-song-va-xa-hoi',
28 'md5': 'b5875ce9b0a2eecde029216d0e6db2ae',
32 'title': 'VOV1 - Bản tin chiều (10/06/2018)',
33 'thumbnail': r
're:(?i)https?://.*\.(?:jpg|png)',
37 'url': 'http://us.tvnet.gov.vn/video/118023/129999/ngay-0705',
41 'title': 'VTV1 - Quốc hội với cử tri (11/06/2018)',
42 'thumbnail': r
're:(?i)https?://.*\.(?:jpg|png)',
46 'skip_download': True,
50 'url': 'http://us.tvnet.gov.vn/kenh-truyen-hinh/1011/vtv1',
54 'title': r
're:^VTV1 \| LiveTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
55 'thumbnail': r
're:(?i)https?://.*\.(?:jpg|png)',
59 'skip_download': True,
63 'url': 'http://vn.tvnet.gov.vn/kenh-truyen-hinh/1014',
67 'title': r
're:VOV1 \| LiveTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
68 'thumbnail': r
're:(?i)https?://.*\.(?:jpg|png)',
72 'skip_download': True,
75 'url': 'http://us.tvnet.gov.vn/phim/6136/25510/vtv3---ca-mot-doi-an-oan-tap-1-50/phim-truyen-hinh',
76 'only_matching': True,
79 def _real_extract(self
, url
):
80 video_id
= self
._match
_id
(url
)
82 webpage
= self
._download
_webpage
(url
, video_id
)
84 title
= self
._og
_search
_title
(
85 webpage
, default
=None) or self
._html
_search
_meta
(
86 'title', webpage
, default
=None) or self
._search
_regex
(
87 r
'<title>([^<]+)<', webpage
, 'title')
88 title
= re
.sub(r
'\s*-\s*TV Net\s*$', '', title
)
90 if '/video/' in url
or '/radio/' in url
:
92 elif '/kenh-truyen-hinh/' in url
:
97 data_file
= unescapeHTML(self
._search
_regex
(
98 r
'data-file=(["\'])(?P
<url
>(?
:https?
:)?
//.+?
)\
1', webpage,
99 'data
file', group='url
'))
103 for stream in self._download_json(data_file, video_id):
104 if not isinstance(stream, dict):
106 stream_url = url_or_none(stream.get('url
'))
107 if stream_url in stream_urls or not stream_url:
109 stream_urls.add(stream_url)
110 formats.extend(self._extract_m3u8_formats(
111 stream_url, video_id, 'mp4
', live=is_live, m3u8_id='hls
', fatal=False))
113 # better support for radio streams
114 if title.startswith('VOV
'):
121 thumbnail = self._og_search_thumbnail(
122 webpage, default=None) or unescapeHTML(
124 r'data
-image
=(["\'])(?P<url>(?:https?:)?//.+?)\1', webpage,
125 'thumbnail', default=None, group='url'))
127 view_count = int_or_none(self._search_regex(
128 r'(?s)<div[^>]+\bclass=["\'].*?view
-count
[^
>]+>.*?
(\d
+).*?
</div
>',
129 webpage, 'view count
', default=None))
134 'thumbnail
': thumbnail,
136 'view_count
': view_count,