laudom/haruhi-dl
2
0
Fork 0
Code Issues 13 Pull requests Packages Projects Releases Wiki Activity

[tvn24] fix fakty extraction (closes #37)

Browse source
This commit is contained in:
Laura Liberda 2021-02-12 12:59:24 +01:00
parent 8a703db751
commit 9bcb5f1b61
1 changed files with 53 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

53
haruhi_dl/extractor/tvn24.py
View file

@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
ExtractorError,
int_or_none,
NO_DEFAULT,
unescapeHTML,
@ -44,6 +45,14 @@ class TVN24IE(InfoExtractor):
'description': 'Milo nie miało myśli erotycznych. Tak boleśnie myślało o własnym ciele, że nie potrafiło myśleć o nim w towarzystwie innych ciał. Ale żeby zmienić ciało, m...',
},
'playlist_count': 2,
}, {
'url': 'https://fakty.tvn24.pl/ogladaj-online,60/akcja-media-bez-wyboru-i-misja-telewizji-publicznej,1048910.html',
'info_dict': {
'id': '1048910',
'ext': 'mp4',
'title': '11.02.2021 | Misja telewizji publicznej i reakcja na protest "Media bez wyboru"',
'description': 'md5:684d2e09f57c7ed03a277bc5ce295d63',
},
}, {
'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html',
'only_matching': True,
@ -64,6 +73,8 @@ class TVN24IE(InfoExtractor):
return self._handle_magazine_frontend(url, display_id)
elif domain in ('tvn24.pl', ):
return self._handle_nextjs_frontend(url, display_id)
elif domain in ('fakty.tvn24.pl', ):
return self._handle_fakty_frontend(url, display_id)
else:
return self._handle_old_frontend(url, display_id)
@ -195,3 +206,45 @@ class TVN24IE(InfoExtractor):
'duration': movie['info']['total_time'],
'is_live': movie['video']['is_live'],
}
def _handle_fakty_frontend(self, url, display_id):
webpage = self._download_webpage(url, display_id)
data = self._parse_json(
self._search_regex(
r"window\.VideoManager\.initVideo\('[^']+',\s*({.+?})\s*,\s*{.+?}\s*\);",
webpage, 'video metadata'), display_id)
video = data['movie']['video']
info = data['movie']['info']
if video.get('protections'):
raise ExtractorError(
'This video is protected by %s DRM protection' % '/'.join(video['protections'].keys()),
expected=True)
formats = []
for fmt_id, fmt_data in video['sources'].items():
if fmt_id == 'hls':
formats.extend(self._extract_m3u8_formats(fmt_data['url'], display_id))
elif fmt_id == 'dash':
formats.extend(self._extract_mpd_formats(fmt_data['url'], display_id))
elif fmt_id == 'mp4':
for quality, mp4_url in fmt_data.items():
formats.append({
'url': mp4_url,
'ext': 'mp4',
'height': int_or_none(quality),
})
self._sort_formats(formats)
return {
'id': display_id,
'formats': formats,
'title': unescapeHTML(info['episode_title']),
'description': unescapeHTML(info.get('description')),
'duration': int_or_none(info.get('total_time')),
'age_limit': int_or_none(data.get('options', {}).get('parental_rating', {}).get('rating')),
}