fix flickr image large issue

foodie_utils.py

@@ -283,7 +283,18 @@ def get_image(search_query):
         logging.info(f"Skipping image with unwanted keywords: {photo.id} (tags: {tags}, title: {title}, matched: {matched_keywords})")
         return None
     
+    # Try 'Large' size first, fall back to 'Medium' if unavailable
+    img_url = None
+    try:
+        img_url = photo.getPhotoFile(size_label='Large')
+    except flickr_api.flickrerrors.FlickrError as e:
+        logging.info(f"Large size not available for photo {photo.id}: {e}, trying Medium")
+        try:
             img_url = photo.getPhotoFile(size_label='Medium')
+        except flickr_api.flickrerrors.FlickrError as e:
+            logging.warning(f"Medium size not available for photo {photo.id}: {e}")
+            return None
+    
     if not img_url or img_url in used_images:
         return None
     
@@ -307,7 +318,7 @@ def get_image(search_query):
         f.write('\n')
     logging.info(f"Saved Flickr image metadata to {flickr_file}: {img_url}")
     
-        logging.info(f"Fallback Flickr image: {img_url} by {uploader} for query '{search_query}' (tags: {tags})")
+    logging.info(f"Selected Flickr image: {img_url} by {uploader} for query '{search_query}' (tags: {tags})")
     return img_url, "Flickr", uploader, page_url
 
     def search_ddg_for_flickr(query):
@@ -1010,24 +1021,19 @@ if os.path.exists(used_images_file):
             else:
                 data = json.loads(content)
                 if not isinstance(data, list):
-                    logging.warning(f"Invalid format in {used_images_file}: expected a list, got {type(data)}. Resetting.")
+                    logging.warning(f"Invalid format in {used_images_file}: expected a list, got {type(data)}. Converting to list.")
-                    data = []
+                    if isinstance(data, dict):
-                else:
+                        # If it's a dict, try to extract URLs from values
-                    # Handle malformed format (list of lists or invalid entries)
+                        data = [v for v in data.values() if isinstance(v, str) and v.startswith('https://')]
-                    flat_data = []
-                    for item in data:
-                        if isinstance(item, str) and item.startswith('https://'):
-                            flat_data.append(item)
-                        elif isinstance(item, list):
-                            logging.warning(f"Fixing malformed entry in {used_images_file}: {item}")
-                            flat_data.extend([sub_item for sub_item in item if isinstance(sub_item, str) and sub_item.startswith('https://')])
                     else:
-                            logging.warning(f"Skipping invalid entry in {used_images_file}: {item}")
+                        logging.warning(f"Cannot convert {type(data)} to list. Resetting to empty list.")
-                    data = flat_data
+                        data = []
+                # Filter out non-string or non-URL entries
+                data = [item for item in data if isinstance(item, str) and item.startswith('https://')]
             used_images.update(data)
         logging.info(f"Loaded {len(used_images)} used image URLs from {used_images_file}")
     except Exception as e:
-        logging.warning(f"Failed to load used images from {used_images_file}: {e}. Resetting file.")
+        logging.warning(f"Failed to load used images from {used_images_file}: {e}. Resetting to empty set.")
         used_images = set()
         with open(used_images_file, 'w') as f:
             json.dump([], f)
@@ -1035,17 +1041,14 @@ if os.path.exists(used_images_file):
 # Function to save used_images to file
 def save_used_images():
     try:
+        # Ensure used_images contains only valid URLs
+        valid_urls = [url for url in used_images if isinstance(url, str) and url.startswith('https://')]
+        if len(valid_urls) != len(used_images):
+            logging.warning(f"Found {len(used_images) - len(valid_urls)} invalid URLs in used_images set")
+        
         with open(used_images_file, 'w') as f:
-            f.write('[\n')
+            json.dump(valid_urls, f, indent=2)
-            urls = list(used_images)
+        logging.info(f"Saved {len(valid_urls)} used image URLs to {used_images_file}")
-            for i, url in enumerate(urls):
-                f.write(f'"{url}"')
-                if i < len(urls) - 1:
-                    f.write(',\n')
-                else:
-                    f.write('\n')
-            f.write(']')
-        logging.info(f"Saved {len(used_images)} used image URLs to {used_images_file}")
     except Exception as e:
         logging.warning(f"Failed to save used images to {used_images_file}: {e}")