def getListFromFile(path,str):
list = []
file = open(path)
lines = file.readlines()
for line in lines:
list.append(line.strip())
return list
import re
priceList = getListFromFile('hebing/price.txt','r')
nameList = getListFromFile('hebing/nameD.txt','r')
featureList = getListFromFile('hebing/aa.txt','r')
for name in nameList:
#print name.decode('gbk')
name = name.decode('gbk')
print name
pattern = re.compile(name)
for feat in featureList:
feat = feat.decode('gbk')
print 'feat:',feat
if pattern.search(feat):
print 'true'
其中,nameD.txt文件和aa.txt文件是ANSI格式的,所以在写入打印每行数据的时候,需要添加.decode('gbk')
如果txt文件是utf-8的话,则可以直接打印出来正常的汉字,但是使用正则表达式search查找里面的字段的时候会出错,所以在用正则的时候,最好是读取ANSI格式的。