image detection not working

redmine2gitea-wiki/redmine_to_gitea_wiki.py

@@ -3,7 +3,6 @@ import requests
 import re
 from bs4 import BeautifulSoup
 import subprocess
-import time
 import logging
 
 # Configure logging
@@ -204,31 +203,21 @@ def push_to_gitea_wiki(local_dir, pages):
         if found_images:
             logger.info(f"Found images on page '{title}': {found_images}")
 
-        # Download images referenced in the content
-        # First, we need to find all image URLs and download them
-        # Look for Redmine-style image tags like !image.png!
-        def replace_image(match):
-            image_name = match.group(1)
+        # Process all !image! patterns in the content
+        original_content = markdown_content
 
-            # Try to find the actual image URL by searching for it in the page content
-            # This is a simplified approach - we'll assume the image name matches 
-            # what's found in Redmine's image system
-            if image_name:
-                # In Redmine, images are usually at /attachments/... path
-                image_url = f"/attachments/download/{image_name}"
-                logger.info(f"Attempting to download image: {image_name}")
+        # Find all image tags in the format !image_name!
+        image_tags = re.findall(r'!(.*?)!', original_content)
 
-                downloaded_path = download_image(image_url, local_dir)
-                if downloaded_path:
-                    return f"![]({downloaded_path})"
-                else:
-                    # If download fails, keep the original format
-                    return f"!{image_name}!"
-            return match.group(0)
-        
-        # We need to handle both !image.png! and ![alt](image) formats
-        # For now, we'll process !image.png! patterns specifically
-        markdown_content = re.sub(image_pattern, replace_image, markdown_content)
+        # For each image tag, attempt to download it and replace it with Markdown syntax
+        for image_tag in image_tags:
+            if image_tag and not image_tag.startswith('\\'):
+                logger.info(f"Found image tag: {image_tag}")
+                # Replace the specific tag with our download logic
+                markdown_content = markdown_content.replace(
+                    f"!{image_tag}!",
+                    handle_image_tag(image_tag, local_dir)
+                )
 
         # Write to file
         with open(filepath, 'w', encoding='utf-8') as f:
@@ -245,6 +234,30 @@ def push_to_gitea_wiki(local_dir, pages):
 
     logger.info("✅ Wiki pages pushed to Gitea!")
 
+def handle_image_tag(image_name, local_dir):
+    """Handle replacement of image tags with downloaded images"""
+    # Check if the image has a valid extension (.png, .jpg, or .jpeg)
+    valid_extensions = ('.png', '.jpg', '.jpeg')
+    if not any(image_name.lower().endswith(ext) for ext in valid_extensions):
+        logger.warning(f"Invalid image extension in tag: {image_name}")
+        return f"!{image_name}!"  # Return original format for invalid extensions
+
+    if image_name and not image_name.startswith('\\'):
+        # In Redmine, images are usually at /attachments/... path
+        image_url = f"/attachments/download/{image_name}"
+        logger.info(f"Attempting to download image: {image_name}")
+
+        # Try to download the image
+        downloaded_path = download_image(image_url, local_dir)
+        if downloaded_path:
+            return f"![]({downloaded_path})"
+        else:
+            # If download fails, keep the original format
+            return f"!{image_name}!"
+    else:
+        # This is likely a regex capture group that wasn't meant to be an image
+        return f"!{image_name}!"
+
 def main():
     # Step 1: Get wiki pages from Redmine
     logger.info("Fetching Redmine wiki pages...")