如下所示:
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
|
#coding=utf-8 import sys, re, os def getDictList( dict ): regx = '''[\w\~`\!\@\#\$\%\^\&\*\(\)\_\-\+\=\[\]\{\}\:\;\,\.\/\<\>\?]+''' with open ( dict ) as f: data = f.read() return re.findall(regx, data) def rmdp(dictList): return list ( set (dictList)) def fileSave(dictRmdp, out): with open (out, 'a' ) as f: for line in dictRmdp: f.write(line + '\n' ) def main(): try : dict = sys.argv[ 1 ].strip() out = sys.argv[ 2 ].strip() except Exception, e: print 'error:' , e me = os.path.basename(__file__) print 'usage: %s <input> <output>' % me print 'example: %s dict.txt dict_rmdp.txt' % me exit() dictList = getDictList( dict ) dictRmdp = rmdp(dictList) fileSave(dictRmdp, out) if __name__ = = '__main__' : main() |
以上这篇python 高效去重复 支持GB级别大文件的示例代码就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持服务器之家。
原文链接:https://blog.csdn.net/meinaozi/article/details/79326512