Add historical data import functionality

- Add import_historical_data() method to EnhancedWaterMonitorScraper
- Support date range imports with Buddhist calendar API format
- Add CLI arguments --import-historical and --force-overwrite
- Include API rate limiting and skip existing data option
- Enable importing years of historical water level data

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

src/main.py

@@ -163,6 +163,45 @@ def run_data_update(days_back: int):
         logger.error(f"❌ Data update failed: {e}")
         return False
 
+def run_historical_import(start_date_str: str, end_date_str: str, skip_existing: bool = True):
+    """Import historical data for a date range"""
+    try:
+        # Parse dates
+        start_date = datetime.strptime(start_date_str, "%Y-%m-%d")
+        end_date = datetime.strptime(end_date_str, "%Y-%m-%d")
+
+        if start_date > end_date:
+            logger.error("Start date must be before or equal to end date")
+            return False
+
+        logger.info(f"Importing historical data from {start_date.date()} to {end_date.date()}")
+        if skip_existing:
+            logger.info("Skipping dates that already have data")
+
+        # Validate configuration
+        Config.validate_config()
+
+        # Initialize scraper
+        db_config = Config.get_database_config()
+        scraper = EnhancedWaterMonitorScraper(db_config)
+
+        # Import historical data
+        imported_count = scraper.import_historical_data(start_date, end_date, skip_existing)
+
+        if imported_count > 0:
+            logger.info(f"✅ Imported {imported_count} historical data points")
+        else:
+            logger.info("✅ No new data imported")
+
+        return True
+
+    except ValueError as e:
+        logger.error(f"❌ Invalid date format. Use YYYY-MM-DD: {e}")
+        return False
+    except Exception as e:
+        logger.error(f"❌ Historical import failed: {e}")
+        return False
+
 def run_web_api():
     """Run the FastAPI web interface"""
     logger.info("Starting web API server...")
@@ -320,6 +359,7 @@ Examples:
   %(prog)s --web-api                # Start web API server
   %(prog)s --fill-gaps 7            # Fill missing data for last 7 days
   %(prog)s --update-data 2          # Update existing data for last 2 days
+  %(prog)s --import-historical 2024-01-01 2024-01-31  # Import historical data
   %(prog)s --status                 # Show system status
   %(prog)s --alert-check            # Check water levels and send alerts
   %(prog)s --alert-test             # Send test Matrix message
@@ -352,6 +392,19 @@ Examples:
         help="Update existing data for the specified number of days back"
     )
     
+    parser.add_argument(
+        "--import-historical",
+        nargs=2,
+        metavar=("START_DATE", "END_DATE"),
+        help="Import historical data for date range (YYYY-MM-DD format)"
+    )
+
+    parser.add_argument(
+        "--force-overwrite",
+        action="store_true",
+        help="Overwrite existing data when importing historical data"
+    )
+
     parser.add_argument(
         "--status",
         action="store_true",
@@ -408,6 +461,10 @@ Examples:
             success = run_gap_filling(args.fill_gaps)
         elif args.update_data is not None:
             success = run_data_update(args.update_data)
+        elif args.import_historical is not None:
+            start_date, end_date = args.import_historical
+            skip_existing = not args.force_overwrite
+            success = run_historical_import(start_date, end_date, skip_existing)
         elif args.status:
             success = show_status()
         elif args.alert_check:

src/water_scraper_v3.py

@@ -576,6 +576,58 @@ class EnhancedWaterMonitorScraper:
             logger.debug(f"Error checking data existence: {e}")
             return False
 
+    def import_historical_data(self, start_date: datetime.datetime, end_date: datetime.datetime,
+                             skip_existing: bool = True) -> int:
+        """
+        Import historical data for a date range
+
+        Args:
+            start_date: Start date for historical import
+            end_date: End date for historical import
+            skip_existing: Skip dates that already have data (default: True)
+
+        Returns:
+            Number of data points imported
+        """
+        logger.info(f"Starting historical data import from {start_date.date()} to {end_date.date()}")
+
+        total_imported = 0
+        current_date = start_date
+
+        while current_date <= end_date:
+            try:
+                # Check if data already exists for this date
+                if skip_existing and self._check_data_exists_for_date(current_date):
+                    logger.info(f"Data already exists for {current_date.date()}, skipping...")
+                    current_date += datetime.timedelta(days=1)
+                    continue
+
+                logger.info(f"Importing data for {current_date.date()}...")
+
+                # Fetch data for this date
+                data = self.fetch_water_data_for_date(current_date)
+
+                if data:
+                    # Save to database
+                    if self.save_to_database(data):
+                        total_imported += len(data)
+                        logger.info(f"Successfully imported {len(data)} data points for {current_date.date()}")
+                    else:
+                        logger.warning(f"Failed to save data for {current_date.date()}")
+                else:
+                    logger.warning(f"No data available for {current_date.date()}")
+
+                # Add small delay to be respectful to the API
+                time.sleep(1)
+
+            except Exception as e:
+                logger.error(f"Error importing data for {current_date.date()}: {e}")
+
+            current_date += datetime.timedelta(days=1)
+
+        logger.info(f"Historical import completed. Total data points imported: {total_imported}")
+        return total_imported
+
 # Main execution for standalone usage
 if __name__ == "__main__":
     import argparse