python 爬虫003-正则表达式简单介绍

正则表达式，简单的说就是用一个“字符串”来描述一个特征，然后去验证另外一个“字符串”是否符合这个特征。

正则表达式在线测试工具 http://tool.chinaz.com/regex

实例一，判断字符串全是小写字母

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re

if __name__ == '__main__':
    str1 = '2asdfsfwdsfsfwk'
    an = re.match('[a-z]+$', str1)
    print(type(an))
    if an:
        print(u'全是小写')
    else:
        print(u'不全是小写')

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re

if __name__ == '__main__':
    str1 = '2asdfsfwdsfsfwk'
    an = re.search('^[a-z]+$', str1)
    print(type(an))
    if an:
        print(u'全是小写')
    else:
        print(u'不全是小写')

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re

if __name__ == '__main__':
    str1 = 'asdfsfwdsfsfwk'
    regex = re.compile('^[a-z]+$')
    an = regex.search(str1)
    print(type(an))
    if an:
        print(u'全是小写')
    else:
        print(u'不全是小写')

实例二，从字符串中提取手机号

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re

if __name__ == '__main__':
    str1 = '从字符串中15011891096abc@qq.com提取1368678804手机13710819640号码'
    regex_phone = re.compile('(?:13[0-9]|14|15[^4,\D]|18[0,2,5-9])\d{8}')
    # regex_phone = re.compile('((?:(?:13[0-9])|(?:15[^4,\D])|(?:18[0,2,5-9]))\d{8})')
    print regex_phone.findall(str1)