这个小程序的目的是将二级目录下的文件全部合并成一个文件（其实几级目录都可以，只要做少许改动）
1 #coding:utf8 2 import sys, os 3 4 def process(path): 5 new_file = open("file_1", "a+") 6 for secDir in os.listdir(path): 7 for f in os.listdir(path + "/" + secDir): 8 fin = open(path + "/" + secDir + "/" + f, "r") 9 content = fin.readline() 10 while len(content) > 0: 11 new_file.write(content) 12 content = fin.readline() 13 fin.close() 14 new_file.close() 15 16 if __name__ == "__main__": 17 process(sys.argv[1])
将这个程序稍作修改，可以实现只留下文件中的字母，去除其他字符的功能：
1 #coding:utf8 2 import sys, os 3 import re 4 5 def process(path): 6 new_file = open("file_2", "a+") 7 for secDir in os.listdir(path): 8 for f in os.listdir(path + "/" + secDir): 9 fin = open(path + "/" + secDir + "/" + f, "r") 10 content = fin.readline() 11 while len(content) > 0: 12 new_content = re.sub("[^a-zA-Z ]+",' ', content) 13 new_file.write(new_content) 14 content = fin.readline() 15 fin.close() 16 new_file.close() 17 18 if __name__ == "__main__": 19 process(sys.argv[1])