GBK to UTF-8 CSV Converter Script Generator for China ERP Data

import csv
import sys

INPUT_FILE = "vendor_master_export.csv"
OUTPUT_FILE = "vendor_master_utf8.csv"
SOURCE_ENC = "gb18030"
TARGET_ENC = "utf-8-sig"
DELIMITER = ","
ERRORS = "strict"


def convert():
    rows = 0
    with open(INPUT_FILE, "r", encoding=SOURCE_ENC, errors=ERRORS, newline="") as src:
        reader = csv.reader(src, delimiter=DELIMITER)
        with open(OUTPUT_FILE, "w", encoding=TARGET_ENC, errors=ERRORS, newline="") as dst:
            writer = csv.writer(dst, delimiter=DELIMITER, quoting=csv.QUOTE_MINIMAL)
            for row in reader:
                writer.writerow(row)
                rows += 1
    return rows


if __name__ == "__main__":
    try:
        count = convert()
        print("Converted", count, "rows from", SOURCE_ENC, "to", TARGET_ENC)
    except UnicodeError as exc:
        print("Encoding error:", exc)
        print("Try source encoding gb18030, which is a superset of gbk.")
        sys.exit(1)

# Print the first 3 rows of the converted file to confirm Chinese text is readable
import csv
with open("vendor_master_utf8.csv", "r", encoding="utf-8-sig", newline="") as f:
    for i, row in enumerate(csv.reader(f, delimiter=",")):
        print(row)
        if i >= 2:
            break