使用python对txt文本文档进行拆分
这是一个python脚本,可以按照所需要的行数拆分txt脚本。
使用方法
在终端运行如下命令,其中10000代表每10000行拆分一次,这个可以自己设置。
python split_text_file.py 需要拆分的文本.txt 10000
import argparse
def split_file(input_file, lines_per_file):
"""Split a large text file into smaller files with a given number of lines."""
try:
with open(input_file, 'r', encoding='utf-8') as file:
count = 0
file_count = 1
current_content = []
for line in file:
count += 1
current_content.append(line)
if count % lines_per_file == 0:
output_file = f"{input_file}_part_{file_count}.txt"
with open(output_file, 'w', encoding='utf-8') as outfile:
outfile.writelines(current_content)
print(f"Created {output_file}")
file_count += 1
current_content = []
# Save the remaining lines if any
if current_content:
output_file = f"{input_file}_part_{file_count}.txt"
with open(output_file, 'w', encoding='utf-8') as outfile:
outfile.writelines(current_content)
print(f"Created {output_file}")
except Exception as e:
print(f"Error occurred: {e}")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Split a large text file into multiple smaller files.")
parser.add_argument("input_file", help="The path to the input text file.")
parser.add_argument("lines_per_file", type=int, help="Number of lines per output file.")
args = parser.parse_args()
split_file(args.input_file, args.lines_per_file)