import re
import sys

def extract_strings(filename, min_length=4):
    with open(filename, "rb") as f:
        data = f.read()
    # 提取 UTF-8 可见字符串
    strings = re.findall(rb"[ -~]{%d,}" % min_length, data)
    return [s.decode("utf-8", errors="ignore") for s in strings]

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("用法: python3 extract_strings.py <page_file>")
        sys.exit(1)

    page_file = sys.argv[1]
    strings = extract_strings(page_file)

    print(f"=== {page_file} 中提取的可见字符串 ===")
    for s in strings:
        print(s)