From 6a5438af4e97ed5c4320029b7c0e5c1570d1ce67 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=B6rg=20Mechnich?= <joerg.mechnich@gmail.com>
Date: Sun, 8 Feb 2026 15:09:59 +0100
Subject: [PATCH 1/2] Fix extraction of media data from webpage

---
 lib/libwdrparser.py | 165 ++++++++++++++++++++++++--------------------
 1 file changed, 91 insertions(+), 74 deletions(-)

diff --git a/lib/libwdrparser.py b/lib/libwdrparser.py
index 250d4a1..9f87ecb 100644
--- a/lib/libwdrparser.py
+++ b/lib/libwdrparser.py
@@ -1,74 +1,91 @@
-# -*- coding: utf-8 -*-
-import requests
-import json
-import re
-#import dateutil.parser
-base = 'http://www1.wdr.de'
-	
-	
-def parseVideo(url,signLang=False):
-	response = requests.get(url).text
-	if 'mediaLink video' in response:
-		j = json.loads(re.compile('<a href="javascript:void\(0\);" class="mediaLink video" data-extension=\'(.+?)\'', re.DOTALL).findall(response)[0])
-		url = j['mediaObj']['url']
-		return parseVideoJs(url,signLang)
-	if 'mediaLink audio' in response:
-		j = json.loads(re.compile('<a href="javascript:void\(0\);" class="mediaLink audio" data-extension=\'(.+?)\'', re.DOTALL).findall(response)[0])
-		url = j['mediaObj']['url']
-		return parseAudioJs(url)
-	
-def parseAudioJs(url):
-	response = requests.get(url).text
-	j = json.loads(response[38:-2])
-	audio = j['mediaResource']['dflt']['audioURL']
-	if audio.startswith('//'):
-		audio = f'http:{audio}'
-	return {'media':[{'url':audio, 'type':'video', 'stream':'audio'}]}
-
-def parseVideoJs(url,signLang=False):
-	response = requests.get(url).text
-	j = json.loads(response[38:-2])
-	
-	videos = []
-	subUrlTtml = False
-	for type in j['mediaResource']:
-		if type == 'dflt' or type == 'alt':
-			if signLang and 'slVideoURL' in j['mediaResource'][type]:
-				videos.append(j['mediaResource'][type]['slVideoURL'])
-			else:
-				videos.append(j['mediaResource'][type]['videoURL'])
-		elif type == 'captionURL':
-			subUrlTtml = j['mediaResource']['captionURL']
-		elif type == 'captionsHash':
-			if 'xml' in j['mediaResource']['captionsHash']:
-				subUrlTtml = j['mediaResource']['captionsHash']['xml']
-			if 'vtt' in j['mediaResource']['captionsHash']:
-				subUrlVtt = j['mediaResource']['captionsHash']['vtt']
-			if 'srt' in j['mediaResource']['captionsHash']:
-				subUrlSrt = j['mediaResource']['captionsHash']['srt']
-	video = False
-	for vid in videos:
-		if vid.startswith('//'):
-			vid = 'http:' + vid
-		if vid.endswith('.m3u8'):
-			video = vid
-		elif vid.endswith('.f4m') and (not video or video.endswith('.mp4')):
-			video = vid.replace('manifest.f4m','master.m3u8').replace('adaptiv.wdr.de/z/','adaptiv.wdr.de/i/')
-		elif vid.endswith('.mp4') and not video:
-			video = vid
-	d = {}
-	d['media'] = []
-	if video.endswith('m3u8'):
-		d['media'].append({'url':video, 'type': 'video', 'stream':'HLS'})
-	else:
-		d['media'].append({'url':video, 'type': 'video', 'stream':'mp4'})
-	if subUrlTtml:
-		if subUrlTtml.startswith('//'):
-			subUrlTtml = 'http:' + subUrlTtml
-		d['subtitle'] = []
-		d['subtitle'].append({'url':subUrlTtml, 'type': 'ttml', 'lang':'de'})
-	return d
-	
-def startTimeToInt(s):
-	HH,MM,SS = s.split(":")
-	return int(HH) * 60 + int(MM)
\ No newline at end of file
+# -*- coding: utf-8 -*-
+import requests
+import json
+import re
+#import dateutil.parser
+base = 'http://www1.wdr.de'
+
+
+def parseVideo(url,signLang=False):
+        response = requests.get(url).text
+        mtype = ''
+        ref = None
+
+        # This is "old-style" matching, not sure if it not used anywhere
+        matches = re.compile(r'<a href="javascript:void\(0\);" class="mediaLink (.+?)" data-extension=\'(.+?)\'', re.DOTALL).findall(response)
+        if len(matches):
+                mtype, jsonstr = matches[0]
+                j = json.loads(jsonstr)
+                url = j['mediaObj']['url']
+        else:
+                # This is "new-style" matching that works in 2026
+                matches = re.compile(r'(?ms)class="mediaLink (.+?)".*?data-extension-ard=\'(.+?)\'').findall(response)
+                if len(matches):
+                        mtype, jsonstr = matches[0]
+                        j = json.loads(jsonstr)
+                        ref = j['mediaObj']['ref']
+        if mtype == 'video':
+                return parseVideoJs(url,signLang,ref)
+        elif mtype == 'audio':
+                return parseAudioJs(url,ref)
+
+def parseAudioJs(url,ref=None):
+        j = parseJs(url,ref)
+        audio = j['mediaResource']['dflt']['audioURL']
+        if audio.startswith('//'):
+                audio = f'http:{audio}'
+        return {'media':[{'url':audio, 'type':'video', 'stream':'audio'}]}
+
+def parseVideoJs(url,signLang=False,ref=None):
+        j = parseJs(url,ref)
+        videos = []
+        subUrlTtml = False
+        for type in j['mediaResource']:
+                if type == 'dflt' or type == 'alt':
+                        if signLang and 'slVideoURL' in j['mediaResource'][type]:
+                                videos.append(j['mediaResource'][type]['slVideoURL'])
+                        else:
+                                videos.append(j['mediaResource'][type]['videoURL'])
+                elif type == 'captionURL':
+                        subUrlTtml = j['mediaResource']['captionURL']
+                elif type == 'captionsHash':
+                        if 'xml' in j['mediaResource']['captionsHash']:
+                                subUrlTtml = j['mediaResource']['captionsHash']['xml']
+                        if 'vtt' in j['mediaResource']['captionsHash']:
+                                subUrlVtt = j['mediaResource']['captionsHash']['vtt']
+                        if 'srt' in j['mediaResource']['captionsHash']:
+                                subUrlSrt = j['mediaResource']['captionsHash']['srt']
+        video = False
+        for vid in videos:
+                if vid.startswith('//'):
+                        vid = 'http:' + vid
+                if vid.endswith('.m3u8'):
+                        video = vid
+                elif vid.endswith('.f4m') and (not video or video.endswith('.mp4')):
+                        video = vid.replace('manifest.f4m','master.m3u8').replace('adaptiv.wdr.de/z/','adaptiv.wdr.de/i/')
+                elif vid.endswith('.mp4') and not video:
+                        video = vid
+        d = {}
+        d['media'] = []
+        if video.endswith('m3u8'):
+                d['media'].append({'url':video, 'type': 'video', 'stream':'HLS'})
+        else:
+                d['media'].append({'url':video, 'type': 'video', 'stream':'mp4'})
+        if subUrlTtml:
+                if subUrlTtml.startswith('//'):
+                        subUrlTtml = 'http:' + subUrlTtml
+                d['subtitle'] = []
+                d['subtitle'].append({'url':subUrlTtml, 'type': 'ttml', 'lang':'de'})
+        return d
+
+def parseJs(url,ref):
+        response = requests.get(url).text
+        if ref is None:
+                j = json.loads(response[38:-2])
+        else:
+                j = json.loads(re.compile(rf'(?ms)globalObject.gseaInlineMediaData\["{ref}"\] =(.*?)}};').findall(response)[0].strip() + '}')
+        return j
+        
+def startTimeToInt(s):
+        HH,MM,SS = s.split(":")
+        return int(HH) * 60 + int(MM)

From 56910ec639f4fa4273cae106cbc95c9aa1c02e15 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=B6rg=20Mechnich?= <joerg.mechnich@gmail.com>
Date: Mon, 9 Feb 2026 20:10:17 +0000
Subject: [PATCH 2/2] Add missing requirement for script.module.requests

---
 addon.xml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/addon.xml b/addon.xml
index 7108760..016bdfc 100644
--- a/addon.xml
+++ b/addon.xml
@@ -6,6 +6,7 @@
   <requires>
     <import addon="xbmc.python" version="3.0.0"/>
     <import addon="script.module.libmediathek4" version="0.0.1"/>
+    <import addon="script.module.requests"/>
   </requires>
   <extension point="xbmc.python.module" library="lib" />
   <extension point="xbmc.addon.metadata">