From d335e0beecfbff7a55ba3a35ef3688104821525a Mon Sep 17 00:00:00 2001
From: deepspy <pavel.deepspy@gmail.com>
Date: Mon, 24 Jun 2024 14:22:56 +0300
Subject: [PATCH] Extracted episode list.

---
 youtube_dl/extractor/kankids.py | 34 ++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/youtube_dl/extractor/kankids.py b/youtube_dl/extractor/kankids.py
index f6f5ae38c..38866dc6f 100644
--- a/youtube_dl/extractor/kankids.py
+++ b/youtube_dl/extractor/kankids.py
@@ -2,9 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+import re
 
 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+/)?$'
+    _VALID_URL = r'https?://(?:www\.)?kankids\.org\.il/content/kids/(?P<category>[a-z]+)-main/p-(?P<id>[0-9]+)/(?P<season>\w+)?/?$'
     _TEST = {
         '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)',
@@ -22,17 +23,32 @@ class KanKidsIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        a = super()._match_valid_url(url)
-        print(a.groupdict())
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        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)
 
-        # TODO more code goes here, for example ...
-        # title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
-        title = 'hi'
+        series_title = self._html_search_regex(r'<title>(?P<title>.+) \|', webpage, 'title')
+
+        season = playlist_season if playlist_season else '(?P<season>\w+)'
+        playlist = set(re.findall(
+            r'href="/content/kids/' +   # Content dir
+            category + r'-main/' +      # Category
+            'p-' + series_id + '/' +    # Series
+            season + '/' +              # Season
+            '(?P<id>[0-9]+)/"' +        # Episode
+            '.+title="(?P<title>.+)"'   # Title
+            , webpage))
+            # , 'Episode list')
+        print('playlist:', playlist)
+
+        for season, video_id, title in playlist if not playlist_season else map(lambda episode: (playlist_season,) + episode, playlist):
+            pass
 
         return {
-            'id': video_id,
+            'id': series_id,
             'title': title,
             'description': self._og_search_description(webpage),
             'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/s1/89707/',