Python Regular Example

regular_example.py

# -*- coding:utf-8 -*-

import re


def testReChinese():
    """测试匹配中文信息"""
    source  =  "狗b狗B骂你祖宗"
    temp    =   source.decode('utf8')
    print "同时匹配中文英文"
    print "--------------------------"
    xx      =   u"狗[^一-龥]*[Bb痹逼]|肛[^一-龥]*门|狗屎吃多|骂你祖宗|天天骂你"
    pattern =   re.compile(xx)
    results =   pattern.findall(temp)
    for result in results:
        print result
    print "--------------------------"


def testReplace():
    print re.search('[abc]', 'Mark cook').group()
    print re.sub('[abc]', 'o', 'Mar cook')
    print re.sub('[abc]', 'o', 'rock')
    print re.sub('[abc]', 'o', 'caps')


def testReplaceText():
    source  =   "狗b狗B骂你祖宗nidaye"
    text    =   source.decode('utf8')
    xx      =   u"狗[^一-龥]*[Bb痹逼]|肛[^一-龥]*门|狗屎吃多|骂你祖宗|天天骂你|nida"
    pattern =   re.compile(xx)

    def replaceFun( matched ):
        matchStr = matched.group( 0 )
        return '*' * len(matchStr)

    result = pattern.sub( replaceFun, text )
    print result


def testMatch():
    m = re.match(r'(\w+) (\w+)(?P<sign>.*)', 'hello world!')

    print "m.string:", m.string
    print "m.re:", m.re
    print "m.pos:", m.pos
    print "m.endpos:", m.endpos
    print "m.lastindex:", m.lastindex
    print "m.lastgroup:", m.lastgroup

    print "m.group(1,2):", m.group(1, 2)
    print "m.groups():", m.groups()
    print "m.groupdict():", m.groupdict()
    print "m.start(2):", m.start(2)
    print "m.end(2):", m.end(2)
    print "m.span(2):", m.span(2)
    print r"m.expand(r'\2 \1\3'):", m.expand(r'\2 \1\3')


def testPatern():
    p = re.compile(r'(\w+) (\w+)(?P<sign>.*)', re.DOTALL)

    print "p.pattern:", p.pattern
    print "p.flags:", p.flags
    print "p.groups:", p.groups
    print "p.groupindex:", p.groupindex


if __name__ == '__main__':
    # testReChinese()
    testReplace()
    # testReplaceText()
    # testMatch()
    # testPatern()
    pass