mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-10-31 14:45:14 +00:00
Code Issues Projects Releases Wiki Activity

[extractor/moview] Add extractor (#4607)

Browse Source 
Authored by: HobbyistDev
This commit is contained in:
HobbyistDev
2022-08-15 05:09:05 +09:00
committed by GitHub
parent cb7cc448c0
commit 7695f5a0a7
4 changed files with 99 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
yt_dlp/extractor/kompas.py
View File

@@ -1,17 +1,9 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
float_or_none,
traverse_obj,
try_call,
)
from .jixie import JixieBaseIE
# Video from www.kompas.tv and video.kompas.com seems use jixie player
# see [1] https://jixie.atlassian.net/servicedesk/customer/portal/2/article/1339654214?src=-1456335525,
# [2] https://scripts.jixie.media/jxvideo.3.1.min.js for more info
# Video from video.kompas.com seems use jixie player
class KompasVideoIE(InfoExtractor):
class KompasVideoIE(JixieBaseIE):
_VALID_URL = r'https?://video\.kompas\.com/\w+/(?P<id>\d+)/(?P<slug>[\w-]+)'
_TESTS = [{
'url': 'https://video.kompas.com/watch/164474/kim-jong-un-siap-kirim-nuklir-lawan-as-dan-korsel',
@@ -33,36 +25,4 @@ class KompasVideoIE(InfoExtractor):
video_id, display_id = self._match_valid_url(url).group('id', 'slug')
webpage = self._download_webpage(url, display_id)
json_data = self._download_json(
'https://apidam.jixie.io/api/public/stream', display_id,
query={'metadata': 'full', 'video_id': video_id})['data']
formats, subtitles = [], {}
for stream in json_data['streams']:
if stream.get('type') == 'HLS':
fmt, sub = self._extract_m3u8_formats_and_subtitles(stream.get('url'), display_id, ext='mp4')
formats.extend(fmt)
self._merge_subtitles(sub, target=subtitles)
else:
formats.append({
'url': stream.get('url'),
'width': stream.get('width'),
'height': stream.get('height'),
'ext': 'mp4',
})
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'title': json_data.get('title') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
'description': (clean_html(traverse_obj(json_data, ('metadata', 'description')))
or self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage)),
'thumbnails': traverse_obj(json_data, ('metadata', 'thumbnails')),
'duration': float_or_none(traverse_obj(json_data, ('metadata', 'duration'))),
'tags': try_call(lambda: json_data['metadata']['keywords'].split(',')),
'categories': try_call(lambda: json_data['metadata']['categories'].split(',')),
'uploader_id': json_data.get('owner_id'),
}
return self._extract_data_from_jixie_id(display_id, video_id, webpage)