1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 00:16:48 +00:00

Compare commits

...

9 Commits

Author SHA1 Message Date
Pavel
86bd8f6938
Merge 5b088ccdd9 into c5098961b0 2024-08-09 17:31:19 -06:00
deepspy
5b088ccdd9 Fixed linter warnings. 2024-07-03 14:31:36 +03:00
deepspy
a4737bb755 Fixed flake8 errors. 2024-06-24 23:12:03 +03:00
deepspy
d3e980eaa5 Some cleanup of the kan kids extractor. 2024-06-24 22:11:06 +03:00
deepspy
162eb5632b Added unittests for kankids extractor.
Fixed a non p- playlist id matching bug.
2024-06-24 17:40:43 +03:00
deepspy
c9265f6d60 Fixed a series title location bug. 2024-06-24 16:46:29 +03:00
deepspy
3fb423c0bf First working version of the kan kids extractor. 2024-06-24 16:25:34 +03:00
deepspy
d335e0beec Extracted episode list. 2024-06-24 14:22:56 +03:00
deepspy
833fe8c9af Added a basic shell for a kankids extractor. 2024-06-24 00:10:22 +03:00
2 changed files with 77 additions and 0 deletions

View File

@ -560,6 +560,7 @@ from .jwplatform import JWPlatformIE
from .kakao import KakaoIE
from .kaltura import KalturaIE
from .kankan import KankanIE
from .kankids import KanKidsIE
from .karaoketv import KaraoketvIE
from .karrierevideos import KarriereVideosIE
from .keezmovies import KeezMoviesIE

View File

@ -0,0 +1,76 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import re
CONTENT_DIR = r'/content/kids/'
DOMAIN = r'kankids.org.il'
class KanKidsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?' +\
DOMAIN.replace('.', '\\.') + CONTENT_DIR +\
r'(?P<category>[a-z]+)-main/(?P<id>[\w\-0-9]+)/(?P<season>\w+)?/?$'
_TESTS = [
{
'url': 'https://www.kankids.org.il/content/kids/ktantanim-main/p-11732/',
'info_dict': {
'_type': 'playlist',
'id': 'p-11732',
'title': 'בית ספר לקוסמים',
},
'playlist_count': 60,
},
{
'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/cramel_main/s1/',
'info_dict': {
'_type': 'playlist',
'id': 'cramel_main',
'title': 'כראמל - עונה 1',
},
'playlist_count': 21,
},
]
def _real_extract(self, url):
m = super()._match_valid_url(url)
series_id = m.group('id')
category = m.group('category')
playlist_season = m.group('season')
webpage = self._download_webpage(url, series_id)
title_pattern = r'<title>(?P<title>.+) \|'
series_title = re.search(title_pattern, webpage)
if not series_title:
series_title = re.search(title_pattern[:-1] + r'-', webpage)
if series_title:
series_title = series_title.group('title')
season = playlist_season if playlist_season else r'(?P<season>\w+)'
content_dir = CONTENT_DIR + category + r'-main/'
playlist = set(re.findall(
r'href="' + content_dir # Content dir
+ series_id + r'/' # Series
+ season + r'/' # Season
+ r'(?P<id>[0-9]+)/"' # Episode
+ r'.+title="(?P<title>.+)"', # Title
webpage))
entries = []
content_dir = r'https://www.' + DOMAIN + content_dir
for season, video_id, title in playlist if not playlist_season else map(lambda episode: (playlist_season,) + episode, playlist):
entries.append(self.url_result(
content_dir + season + r'/' + video_id + r'/',
ie='Generic',
video_id=video_id,
video_title=title,
))
return {
'_type': 'playlist',
'id': series_id,
'title': series_title,
'entries': entries,
}