helper scripts

OCR-scripts/ocr_screenshots.py

@@ -0,0 +1,169 @@
+#!/usr/bin/env python3
+
+import glob
+import os
+import sqlite3
+import subprocess
+from datetime import datetime
+
+# Configuration
+SCREENSHOTS_DIR = os.path.expanduser("~/Screenshots")
+DATABASE_PATH = os.path.expanduser("~/screenshot_ocr.db")
+
+
+def create_database():
+    """Create SQLite database and table if they don't exist."""
+    conn = sqlite3.connect(DATABASE_PATH)
+    cursor = conn.cursor()
+
+    # Create table for OCR results
+    cursor.execute("""
+    CREATE TABLE IF NOT EXISTS ocr_results (
+        id INTEGER PRIMARY KEY AUTOINCREMENT,
+        filename TEXT UNIQUE,
+        full_path TEXT,
+        ocr_text TEXT,
+        file_size INTEGER,
+        created_date TEXT,
+        ocr_date TEXT
+    )
+    """)
+
+    conn.commit()
+    conn.close()
+    print(f"Database initialized at {DATABASE_PATH}")
+
+
+def get_processed_files():
+    """Get a set of filenames that have already been processed."""
+    conn = sqlite3.connect(DATABASE_PATH)
+    cursor = conn.cursor()
+
+    cursor.execute("SELECT filename FROM ocr_results")
+    processed_files = {row[0] for row in cursor.fetchall()}
+
+    conn.close()
+    return processed_files
+
+
+def perform_ocr(image_path):
+    """Perform OCR on an image file using tesseract."""
+    try:
+        # Create a temporary output file
+        temp_output = f"/tmp/{os.path.basename(image_path)}.txt"
+        temp_base = temp_output.replace(".txt", "")
+
+        # Run tesseract
+        subprocess.run(
+            ["tesseract", image_path, temp_base],
+            check=True,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+        )
+
+        # Read OCR text from the output file
+        with open(temp_output, "r", encoding="utf-8") as f:
+            ocr_text = f.read().strip()
+
+        # Clean up temporary file
+        os.remove(temp_output)
+
+        return ocr_text
+    except subprocess.CalledProcessError as e:
+        print(f"Error running tesseract on {image_path}: {str(e)}")
+        return ""
+    except Exception as e:
+        print(f"Error processing {image_path}: {str(e)}")
+        return ""
+
+
+def add_to_database(filename, full_path, ocr_text, file_size, created_date):
+    """Add OCR result to the database."""
+    conn = sqlite3.connect(DATABASE_PATH)
+    cursor = conn.cursor()
+
+    try:
+        cursor.execute(
+            """
+        INSERT INTO ocr_results
+        (filename, full_path, ocr_text, file_size, created_date, ocr_date)
+        VALUES (?, ?, ?, ?, ?, ?)
+        """,
+            (
+                filename,
+                full_path,
+                ocr_text,
+                file_size,
+                created_date,
+                datetime.now().isoformat(),
+            ),
+        )
+
+        conn.commit()
+        print(f"Added {filename} to database")
+    except sqlite3.IntegrityError:
+        print(f"File {filename} already exists in database")
+    except Exception as e:
+        print(f"Error adding {filename} to database: {str(e)}")
+    finally:
+        conn.close()
+
+
+def main():
+    """Main function to process screenshot images."""
+    print("Starting OCR process for screenshots...")
+
+    # Create database if it doesn't exist
+    create_database()
+
+    # Get list of already processed files
+    processed_files = get_processed_files()
+    print(f"Found {len(processed_files)} already processed files")
+
+    # Get list of PNG and JPG files
+    image_files = glob.glob(os.path.join(SCREENSHOTS_DIR, "*.png"))
+    image_files.extend(glob.glob(os.path.join(SCREENSHOTS_DIR, "*.jpg")))
+    image_files.extend(glob.glob(os.path.join(SCREENSHOTS_DIR, "*.jpeg")))
+    print(f"Found {len(image_files)} image files")
+
+    # Process each image file
+    processed_count = 0
+    skipped_count = 0
+    error_count = 0
+
+    for image_path in image_files:
+        filename = os.path.basename(image_path)
+
+        # Skip if already processed
+        if filename in processed_files:
+            print(f"Skipping {filename} (already processed)")
+            skipped_count += 1
+            continue
+
+        print(f"Processing {filename}...")
+
+        # Get file information
+        file_stats = os.stat(image_path)
+        file_size = file_stats.st_size
+        created_date = datetime.fromtimestamp(file_stats.st_mtime).isoformat()
+
+        # Perform OCR
+        ocr_text = perform_ocr(image_path)
+
+        if ocr_text:
+            # Add to database
+            add_to_database(filename, image_path, ocr_text, file_size, created_date)
+            processed_count += 1
+        else:
+            print(f"No OCR text extracted from {filename}")
+            error_count += 1
+
+    print("\nOCR process completed:")
+    print(f"- Processed: {processed_count}")
+    print(f"- Skipped (already in database): {skipped_count}")
+    print(f"- Errors: {error_count}")
+    print(f"- Total files in database: {len(processed_files) + processed_count}")
+
+
+if __name__ == "__main__":
+    main()