1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
This commit is contained in:
Subrat Lima 2025-06-20 21:48:41 +02:00 committed by GitHub
commit 1968b04957
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 135 additions and 23 deletions

View File

@ -2405,7 +2405,11 @@
VoicyChannelIE,
VoicyIE,
)
from .volejtv import VolejTVIE
from .volejtv import (
VolejTVCategoryPlaylistIE,
VolejTVClubPlaylistIE,
VolejTVIE,
)
from .voxmedia import (
VoxMediaIE,
VoxMediaVolumeIE,

View File

@ -1,40 +1,148 @@
import functools
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
int_or_none,
join_nonempty,
orderedSet,
str_or_none,
strftime_or_none,
traverse_obj,
unified_timestamp,
url_or_none,
)
class VolejTVIE(InfoExtractor):
_VALID_URL = r'https?://volej\.tv/video/(?P<id>\d+)'
class VolejTVBaseIE(InfoExtractor):
TBR_HEIGHT_MAPPING = {'6000': 1080, '2400': 720, '1500': 480, '800': 360}
def _call_api(self, endpoint, display_id, query=None):
return self._download_json(
f'https://api-volejtv-prod.apps.okd4.devopsie.cloud/api/{endpoint}', display_id, query=query)
class VolejTVIE(VolejTVBaseIE):
IE_NAME = 'volejtv:match'
_VALID_URL = r'https?://volej\.tv/match/(?P<id>\d+)'
_TESTS = [{
'url': 'https://volej.tv/video/725742/',
'url': 'https://volej.tv/match/270579',
'info_dict': {
'id': '725742',
'id': '270579',
'ext': 'mp4',
'description': 'Zápas VK Královo Pole vs VK Prostějov 10.12.2022 v 19:00 na Volej.TV',
'thumbnail': 'https://volej.tv/images/og/16/17186/og.png',
'title': 'VK Královo Pole vs VK Prostějov',
'title': 'SWE-CZE (2024-06-16)',
'categories': ['ženy'],
'series': 'ZLATÁ EVROPSKÁ VOLEJBALOVÁ LIGA',
'season': '2023-2024',
'timestamp': 1718553600,
'upload_date': '20240616',
},
}, {
'url': 'https://volej.tv/video/725605/',
'url': 'https://volej.tv/match/487520',
'info_dict': {
'id': '725605',
'id': '487520',
'ext': 'mp4',
'thumbnail': 'https://volej.tv/images/og/15/17185/og.png',
'title': 'VK Lvi Praha vs VK Euro Sitex Příbram',
'description': 'Zápas VK Lvi Praha vs VK Euro Sitex Příbram 11.12.2022 v 19:00 na Volej.TV',
'thumbnail': r're:https://.+\.(png|jpeg)',
'title': 'FRA-CZE (2024-09-06)',
'categories': ['mládež'],
'series': 'Mistrovství Evropy do 20 let',
'season': '2024-2025',
'timestamp': 1725627600,
'upload_date': '20240906',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
json_data = self._search_json(
r'<\s*!\[CDATA[^=]+=', webpage, 'CDATA', video_id)
formats, subtitle = self._extract_m3u8_formats_and_subtitles(
json_data['urls']['hls'], video_id)
return {
json_data = self._call_api(f'match/{video_id}', video_id)
formats = []
for video in traverse_obj(json_data, ('videos', 0, 'qualities', lambda _, v: v['cloud_front_path'])):
formats.append(traverse_obj(video, {
'url': ('cloud_front_path', {url_or_none}),
'tbr': ('quality', {int_or_none}),
'format_id': ('id', {str_or_none}),
'height': ('quality', {lambda v: self.TBR_HEIGHT_MAPPING[v]}),
}))
data = {
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
**traverse_obj(json_data, {
'series': ('competition_name', {str}),
'season': ('season', {str}),
'timestamp': ('match_time', {unified_timestamp}),
'categories': ('category', ('title'), {str}, filter, all, filter),
'thumbnail': ('poster', {url_or_none}),
}),
'formats': formats,
'subtitles': subtitle,
}
teams = orderedSet(traverse_obj(json_data, ('teams', ..., 'shortcut', {str})))
if len(teams) > 2 and 'FIN' in teams:
teams.remove('FIN')
data['title'] = join_nonempty(join_nonempty(*teams, delim='-'),
f"({strftime_or_none(data['timestamp'], '%Y-%m-%d')})", delim=' ')
return data
class VolejTVClubPlaylistIE(VolejTVBaseIE):
IE_NAME = 'volejtv:club'
_VALID_URL = r'https?://volej\.tv/klub/(?P<id>\d+)'
_TESTS = [{
'url': 'https://volej.tv/klub/1173',
'info_dict': {
'id': '1173',
'title': 'VK Jihostroj České Budějovice',
},
'playlist_mincount': 30,
}]
_PAGE_SIZE = 6
def _get_page(self, playlist_id, page):
return self._call_api(f'match/by-team-id-paginated/{playlist_id}', playlist_id,
query={'page': page + 1, 'take': self._PAGE_SIZE, 'order': 'DESC'})
def _entries(self, playlist_id, first_page_data, page):
entries = first_page_data if page == 0 else self._get_page(playlist_id, page)
for entry in entries.get('data', []):
yield self.url_result(f"https://volej.tv/match/{entry['id']}", VolejTVIE)
def _real_extract(self, url):
playlist_id = self._match_id(url)
title = self._call_api(f'team/show/{playlist_id}', playlist_id)['title']
first_page_data = self._get_page(playlist_id, 0)
total_pages = traverse_obj(first_page_data, ('meta', 'pageCount', {int}))
return self.playlist_result(InAdvancePagedList(
functools.partial(self._entries, playlist_id, first_page_data),
total_pages, self._PAGE_SIZE), playlist_id, title)
class VolejTVCategoryPlaylistIE(VolejTVClubPlaylistIE):
IE_NAME = 'volejtv:category'
_VALID_URL = r'https?://volej\.tv/kategorie/(?P<id>[^/$?]+)'
_TESTS = [{
'url': 'https://volej.tv/kategorie/chance-cesky-pohar',
'info_dict': {
'id': 'chance-cesky-pohar',
'title': 'Chance Český pohár',
},
'playlist_mincount': 30,
}]
_PAGE_SIZE = 10
def _get_page(self, playlist_id, page):
return self._call_api(f'match/by-category-id-paginated/{playlist_id}', playlist_id,
query={'page': page + 1, 'take': self._PAGE_SIZE, 'order': 'DESC'})
def _get_category(self, playlist_id):
categories = self._call_api('category', playlist_id)
for category in categories:
if category['slug'] == str(playlist_id):
return category['id'], category['title']
def _real_extract(self, url):
playlist_id = self._match_id(url)
category_id, title = self._get_category(playlist_id)
first_page_data = self._get_page(category_id, 0)
total_pages = traverse_obj(first_page_data, ('meta', 'pageCount', {int}))
return self.playlist_result(InAdvancePagedList(
functools.partial(self._entries, category_id, first_page_data),
total_pages, self._PAGE_SIZE), playlist_id, title)