Getting colors from PDF

get_soil_type_from_bgr/map_colors/parse_labels.py

+import sys  # To handle potential errors more gracefully
+from collections import Counter
+
+from PIL import Image
+
+
+def analyze_image_colors(image_path):
+    """
+    Opens an image, extracts unique RGB colors, and prints them sorted by frequency.
+
+    Args:
+        image_path (str): The path to the image file (e.g., 'diagram.png').
+    """
+    try:
+        # Open the image file
+        img = Image.open(image_path)
+
+        # Ensure the image is in RGB format to get (R, G, B) tuples
+        # This handles various modes like RGBA (discards alpha), L (grayscale), P (palette)
+        img_rgb = img.convert("RGB")
+
+        # Get all pixel data efficiently. Returns a sequence of (R, G, B) tuples.
+        pixels = img_rgb.getdata()
+
+        # Use Counter to efficiently count occurrences of each color tuple
+        color_counts = Counter(pixels)
+
+        # Sort the unique colors by their count (frequency) in descending order
+        # items() gives [(color, count), ...], sort by the second element (count)
+        sorted_colors = sorted(
+            color_counts.items(), key=lambda item: item[1], reverse=True
+        )
+
+        # Output the results
+        print(f"Unique colors found in '{image_path}', sorted by frequency:")
+        if not sorted_colors:
+            print("No pixels found or image is empty.")
+        else:
+            for color, count in sorted_colors:
+                if count < 200:
+                    continue
+                html = "#%02x%02x%02x" % color
+                print(f"RGB: {html}, Count: {count}")
+
+    except FileNotFoundError:
+        print(f"Error: The file '{image_path}' was not found.", file=sys.stderr)
+    except Exception as e:
+        print(f"An error occurred: {e}", file=sys.stderr)
+
+
+# RGB: #fffcd6, Count: 2015
+# RGB: #fffa91, Count: 2015
+# RGB: #fff500, Count: 2046
+# RGB: #d99e5e, Count: 2046
+# RGB: #b8663d, Count: 2046
+# RGB: #b68041, Count: 2046
+# RGB: #ffa67d, Count: 2015
+# RGB: #e87845, Count: 2015
+# RGB: #f299bf, Count: 2015
+# RGB: #70a800, Count: 2015
+# RGB: #d9f2ff, Count: 2016
+
+cmap = {
+    "Abbauflächen": "#222222",
+    "Normallehme (ll)": "#b8663d",
+    "Lehmsande (ls)": "#fffa91",
+    "Lehmschluffe (lu)": "#ffa67d",
+    "Moore": "#70a800",
+    "Sandlehme (sl)": "#d99e5e",
+    "Reinsande (ss)": "#fffcd6",
+    "Tonlehme (tl)": "#b68041",
+    "Tonschluffe (tu)": "#e87845",
+    "Schluffsande (us)": "#fff500",
+    "Schlufftone (ut)": "#f299bf",
+    "Watt": "#d9f2ff",
+    "Siedlung": "#222222",
+    "Gewässer": "#0000ff",
+}
+
+
+# --- Main execution ---
+if __name__ == "__main__":
+    image_file = "labels.png"  # The name of your image file
+    analyze_image_colors(image_file)