python-re之中文匹配

 1 #coding=utf-8
 2 import re
 3 import chardet#检测网页编码形式的模块
 4   
 5 p = re.compile(r‘\d+‘)  
 6 print p.findall(‘one1two2three3four4‘)  
 7 
 8 a="rewfd231321ewq21weqeqw"
 9 p=re.compile(r"(\d+)\D+(\d+)",re.S)
10 b=p.findall(a)
11 print b
12 
13 a=u"我爱@糗百，你呢"
14 print a
15 b=re.findall (u"(.+?)@糗百(.+)",a,re.S)
16 print b
17 for i in b:
18     for j in i:
19         print j

 1 import re
 2 import chardet#检测网页编码形式的模块
 3   
 4 a="我爱@糗百，你呢"
 5 if isinstance(a, unicode) :
 6     pass
 7 else:
 8     codesty=chardet.detect(a)
 9     a=a.decode(codesty[‘encoding‘])
10 print a
11 b=re.findall (u"(.+?)@糗百(.+)",a,re.S)
12 print b
13 for i in b:
14     for j in i:
15         print j