depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-28 13:11:49 +00:00
Code Issues Releases Wiki Activity

First working version of the kan kids extractor.

Browse source
This commit is contained in:
deepspy 2024-06-24 16:25:34 +03:00
parent d335e0beec
commit 3fb423c0bf
1 changed files with 24 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
youtube_dl/extractor/kankids.py
View file

@ -4,8 +4,13 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
import re import re
CONTENT_DIR = r'/content/kids/'
DOMAIN = r'kankids.org.il'
class KanKidsIE(InfoExtractor): class KanKidsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kankids\.org\.il/content/kids/(?P<category>[a-z]+)-main/p-(?P<id>[0-9]+)/(?P<season>\w+)?/?$' _VALID_URL = r'https?://(?:www\.)?' +\
DOMAIN.replace('.', '\.') + CONTENT_DIR +\
r'(?P<category>[a-z]+)-main/p-(?P<id>[0-9]+)/(?P<season>\w+)?/?$'
_TEST = { _TEST = {
'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/', 'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)', 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
@ -32,29 +37,32 @@ class KanKidsIE(InfoExtractor):
series_title = self._html_search_regex(r'<title>(?P<title>.+) \|', webpage, 'title') series_title = self._html_search_regex(r'<title>(?P<title>.+) \|', webpage, 'title')
season = playlist_season if playlist_season else '(?P<season>\w+)' season = playlist_season if playlist_season else r'(?P<season>\w+)'
content_dir = CONTENT_DIR + category + r'-main/'
playlist = set(re.findall( playlist = set(re.findall(
r'href="/content/kids/' + # Content dir r'href="' + content_dir + # Content dir
category + r'-main/' + # Category r'p-' + series_id + r'/' + # Series
'p-' + series_id + '/' + # Series season + r'/' + # Season
season + '/' + # Season r'(?P<id>[0-9]+)/"' + # Episode
'(?P<id>[0-9]+)/"' + # Episode r'.+title="(?P<title>.+)"' # Title
'.+title="(?P<title>.+)"' # Title
, webpage)) , webpage))
# , 'Episode list') # , 'Episode list')
print('playlist:', playlist) print('playlist:', playlist)
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): for season, video_id, title in playlist if not playlist_season else map(lambda episode: (playlist_season,) + episode, playlist):
pass entries.append(self.url_result(
content_dir + season + r'/' + video_id + r'/',
ie='Generic',
video_id=video_id,
video_title=title,
))
return { return {
'_type': 'playlist',
'id': series_id, 'id': series_id,
'title': title, 'title': series_title,
'description': self._og_search_description(webpage), 'entries': entries,
'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/s1/89707/',
'ie_key': 'Generic',
'_type': 'url',
# 'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
} }