Draft script to select columns and write CSV

hsparse/select_columns_to_csv.py

@@ -0,0 +1,40 @@
+import csv
+
+def read_good_headers(filename):
+    """Reads and returns the list of 'good' headers from a given file."""
+    with open(filename, 'r') as file:
+        return [line.strip() for line in file.readlines()]
+
+def filter_csv(input_file, output_file, good_headers):
+    """Filters an input CSV based on the provided good headers and writes to output CSV."""
+    
+    # Read the original CSV
+    with open(input_file, mode='r', newline='', encoding='utf-8') as infile:
+        reader = csv.DictReader(infile)
+        
+        # Get only the required fieldnames ('good' headers)
+        filtered_fieldnames = [field for field in reader.fieldnames if field in good_headers]
+        
+        # Write to output CSV
+        with open(output_file, mode='w', newline='', encoding='utf-8') as outfile:
+            writer = csv.DictWriter(outfile, fieldnames=filtered_fieldnames)
+            
+            # Write the header line (column names) first
+            writer.writeheader()
+            
+            for row in reader:
+                filtered_row = {key: value for key, value in row.items() if key in filtered_fieldnames}
+                writer.writerow(filtered_row)
+
+if __name__ == "__main__":
+    input_file = 'tmp/mycontacts.csv'
+    good_headers_file = 'tmp/good_headers.txt'
+    output_file = 'tmp/final.csv'
+
+    # Step 1: Read the list of good headers
+    good_headers = read_good_headers(good_headers_file)
+    
+    # Step 2: Filter the CSV based on these headers and write to a new file
+    filter_csv(input_file, output_file, good_headers)
+
+print(f"Filtered CSV has been written to {output_file}")