[本文出自天外归云的博客园]
1、递归遍历目录下所有文件并通过finder函数定位指定格式字符串
2、用来查找字符串的finder函数是自己定义的,这里定义了一个ip_port_finder通过正则表达式查找ip:port格式(粗匹配:数字.数字.数字.数字:数字)的字符串
3、用gevent来实现协程并发完成耗时任务
代码如下:
# -*- coding: utf-8 -*-
import re
from os.path import join
from os import walk
from gevent import monkey
import gevent monkey.patch_all() def ip_port_finder(str: str) -> bool:
pattern = re.compile(r".+\d+\.\d+\.\d+\.\d+:\d+")
matchObj = pattern.match(str)
if matchObj:
print("------")
print(f"发现目标:{matchObj.group(0)}")
return True
else:
return False def find_in_file(file_path, finder):
with open(file_path, "r", encoding="utf-8", errors='ignore') as f:
for (num, value) in enumerate(f):
if finder(value):
print(f"文件路径:{file_path}")
print(f"所在行数:{num}") find_in_path_recursively = lambda path, finder: gevent.joinall(
[gevent.spawn(find_in_file, join(root, file_name), finder) for root, directories, f_names in walk(path) for
file_name in f_names]) if __name__ == '__main__':
path = "E:\dev_codes\xxx"
find_in_path_recursively(path, ip_port_finder)
参考文章: