#!/usr/bin/python
#-*- coding:cp936-*-#思路，将str转换成unicode，方可用正则表达式，前提是，要知道文件的编码，本例中是gbk
import cPickle as mypickle
import re
import sys
if (__name__=='__main__'):
 fid1=file('demo.txt','r');#demo.txt写入字符如：脚本之家
 p=re.compile('(^s+|s+$)');
 phanzigbk=re.compile('[\x20-\x7f]');
 phanzi=re.compile(u'[u4e00-u9fa5]');#这里要加u,注意
 commlines=fid1.readlines();
 fid1.close();
 dictfamilyname={};
 dictfirstname={};
 for line in commlines:
 line=p.sub('',line);
 print type(line);
 print line;
 uline=unicode(line,'gbk');
 print type(uline);
 candidates=phanzi.findall(uline);
 print len(candidates);
 if(len(candidates)==2):
 print candidates[0];
 familynamegbk=candidates[0].encode('gbk');#把unicode型的变量变成str型的变量
 firstnamegbk=candidates[1].encode('gbk');
 if(dictfamilyname.has_key(familynamegbk)):
 dictfamilyname[familynamegbk]=dictfamilyname[familynamegbk]+1;
 else:
 dictfamilyname[familynamegbk]=1;
 if(dictfirstname.has_key(firstnamegbk)):
 dictfirstname[firstnamegbk]=dictfirstname[firstnamegbk]+1;
 else:
 dictfirstname[firstnamegbk]=1;
 familynameitems=dictfamilyname.items();
 print familynameitems;
 firstnameitems=dictfirstname.items();
 familynameitems.sort(key=lambda d:d[1],reverse=True);
 firstnameitems.sort(key=lambda d :d[1],reverse=True);
 fid=file('familyname.txt','w');
 for m in familynameitems:
 s=m[0]+'	'+str(m[1]);
 fid.write(s);
 fid.write('
');
 fid.close();
 fid=file('firstname.txt','w');
 for m in firstnameitems:
 s=m[0]+'	'+str(m[1]);
 fid.write(s);
 fid.write('
');
 fid.close();
 print 'finish'

运行效果图如下：

更多Python正则表达式匹配中文用法示例相关文章请关注PHP中文网！