From e2d5b4ab53496214b09a7d258112b1960ce1035a Mon Sep 17 00:00:00 2001
From: stoney420 <xxmartinxx1990@gmail.com>
Date: Fri, 27 Jun 2025 20:06:47 +0200
Subject: [PATCH] Update scripts/generate_playlist.py

---
 scripts/generate_playlist.py | 80 ++++++++++++++++++++++++++++++++++--
 1 file changed, 76 insertions(+), 4 deletions(-)

diff --git a/scripts/generate_playlist.py b/scripts/generate_playlist.py
index 6ae25ba..ca10d7f 100644
--- a/scripts/generate_playlist.py
+++ b/scripts/generate_playlist.py
@@ -312,7 +312,69 @@ def remove_duplicates(channels, settings):
     
     return unique_channels
 
-def update_existing_channels_with_country_detection():
+def clean_corrupted_channels():
+    """Clean up any corrupted entries in existing channels.txt"""
+    if not os.path.exists(CHANNELS_FILE):
+        return
+    
+    log_message("Cleaning up any corrupted entries in channels.txt...", "INFO")
+    
+    with open(CHANNELS_FILE, 'r', encoding='utf-8') as f:
+        content = f.read()
+    
+    channel_blocks = re.split(r'\n\s*\n+', content.strip())
+    cleaned_channels = []
+    fixed_count = 0
+    
+    for block in channel_blocks:
+        if block.strip():
+            channel = parse_channel_block(block)
+            if channel:
+                # Clean corrupted Stream URL
+                stream_url = channel.get('Stream URL', '')
+                if '#EXTINF' in stream_url or 'group-title=' in stream_url:
+                    # Extract just the URL part
+                    if '#EXTINF' in stream_url:
+                        stream_url = stream_url.split('#EXTINF')[0].strip()
+                    if 'group-title=' in stream_url:
+                        stream_url = stream_url.split('group-title=')[0].strip()
+                    channel['Stream URL'] = stream_url
+                    fixed_count += 1
+                    log_message(f"Fixed corrupted URL for: {channel.get('Stream name')}", "INFO")
+                
+                # Clean corrupted Logo URL
+                logo_url = channel.get('Logo', '')
+                if logo_url and ('group-title=' in logo_url or '#EXTINF' in logo_url):
+                    if 'group-title=' in logo_url:
+                        logo_url = logo_url.split('group-title=')[0].strip()
+                    if '#EXTINF' in logo_url:
+                        logo_url = logo_url.split('#EXTINF')[0].strip()
+                    channel['Logo'] = logo_url
+                    fixed_count += 1
+                    log_message(f"Fixed corrupted logo for: {channel.get('Stream name')}", "INFO")
+                
+                cleaned_channels.append(channel)
+    
+    if fixed_count > 0:
+        log_message(f"Fixed {fixed_count} corrupted entries, rewriting file...", "INFO")
+        
+        # Backup and rewrite
+        backup_name = f"{CHANNELS_FILE}.backup.{datetime.now().strftime('%Y%m%d_%H%M%S')}"
+        try:
+            import shutil
+            shutil.copy2(CHANNELS_FILE, backup_name)
+        except:
+            pass
+        
+        with open(CHANNELS_FILE, 'w', encoding='utf-8') as f:
+            for i, channel in enumerate(cleaned_channels):
+                if i > 0:
+                    f.write("\n\n")
+                f.write(convert_to_channels_txt_block(channel))
+        
+        log_message(f"Successfully cleaned and rewrote channels.txt", "INFO")
+    else:
+        log_message("No corrupted entries found to fix", "INFO")
     """Re-detect countries for existing channels - FORCE UPDATE ALL."""
     if not os.path.exists(CHANNELS_FILE):
         return
@@ -390,12 +452,19 @@ def process_import():
             content = f.read()
         
         # Pre-process the content to fix common issues
-        log_message("Pre-processing M3U content to fix common issues...", "INFO")
+        log_message("Pre-processing M3U content with AGGRESSIVE fixing...", "INFO")
         
-        # Fix missing newlines between entries
-        content = re.sub(r'(https?://[^\s]+)(#EXTINF)', r'\1\n\2', content)
+        # Fix the most common issue: missing newlines between URL and next EXTINF
+        content = re.sub(r'(https?://[^\s#]+)(#EXTINF)', r'\1\n\2', content)
         content = re.sub(r'(\.m3u8?)(#EXTINF)', r'\1\n\2', content)
         content = re.sub(r'(\.ts)(#EXTINF)', r'\1\n\2', content)
+        content = re.sub(r'(\d+)(#EXTINF)', r'\1\n\2', content)
+        
+        # Fix missing newlines between different sections
+        content = re.sub(r'(group-title="[^"]*")([A-Z][a-z]+:)', r'\1\n#EXTINF:-1 \2', content)
+        
+        # Ensure EXTINF always starts on new line
+        content = re.sub(r'([^#\n])#EXTINF', r'\1\n#EXTINF', content)
         
         # Split into lines after fixing
         lines = content.split('\n')
@@ -563,6 +632,9 @@ def generate_playlist():
     settings = load_settings()
     group_overrides = load_group_overrides()
     
+    # First clean any existing corrupted entries
+    clean_corrupted_channels()
+    
     update_existing_channels_with_country_detection()
     
     imported_channels = process_import()