messyscript/processTxt.py

#出现问题conda activate base
#将文本的前19万字符留下
import sys

def main():
    input_file = sys.argv[1]  # 输入文件名
    output_file = sys.argv[1] + "out.txt" # 输出文件名
    chars_to_keep = 190000  # 需要保留的字符数

    with open(input_file, 'r', encoding='utf-8') as f_in, open(output_file, 'w', encoding='utf-8') as f_out:
       count = 0
       for line in f_in:
           count += len(line)
           if count > chars_to_keep:
               break
           f_out.write(line)

if __name__ == "__main__":
   main()