Python正则表达式中的量词符号与组问题小结

In [18]: data = 'insane@loafer.com'

In [19]: print(re.findall('insane|com|loafer', data))
['insane', 'loafer', 'com']

In [20]:  print(re.findall('^insane',data))
['insane']

In [21]:  print(re.findall('^insane1',data))
[]

In [22]:  print(re.findall('com$',data))
['com']

In [23]:  print(re.findall('net$',data))
[]

In [24]:  print(re.findall('\w*',data))
['insane', '', 'loafer', '', 'com', '']

In [25]:  print(re.findall('\w+',data))
['insane', 'loafer', 'com']

In [31]: data = 'insane@loaf.com'

In [32]:  print(re.findall('\w{3}',data))
['ins', 'ane', 'loa', 'com']

In [33]:  print(re.findall('[a-z]{3}',data))
['ins', 'ane', 'loa', 'com']

In [34]: data = 'insane@loaf.com'

In [35]:  print(re.findall('\w{1,4}',data))
['insa', 'ne', 'loaf', 'com']

In [36]:  print(re.findall('\w{1, 4}',data))
[]

In [37]: data = 'insane@loaf.com'

In [38]:  print(re.findall('[^insane]',data))
['@', 'l', 'o', 'f', '.', 'c', 'o', 'm']

In [42]: test = 'hello my name is insane'

In [43]: result = re.search('hello (.*) name is (.*)', test)

In [44]: result.groups()
Out[44]: ('my', 'insane')

In [45]: result.groups(1)
Out[45]: ('my', 'insane')

In [46]: result.group(1)
Out[46]: 'my'

In [47]: result.group(2)
Out[47]: 'insane'

#!/usr/bin/python3
# -*- coding: utf-8 -*-
# @Time     : 2021/8/28 22:13
# @Author   : InsaneLoafer
# @File     : re_test2.py

import re


def check_url(url):
    """
    判断url是否合法
    :param url:
    :return:
    """
    result = re.findall('[a-zA-Z]{4,5}://\w*\.*\w+\.\w+', url)
    if len(result) != 0:
        return True
    else:
        return False

def get_url(url):
    """
    通过组获取url中的某一部分
    :param url:
    :return:
    """
    result = re.findall('[https://|http://](\w*\.*\w+\.\w+)', url)
    if len(result) != 0:
        return result[0]
    else:
        return ''

def get_email(data):
    # result = re.findall('[0-9a-zA-Z_]+@[0-9a-zA-Z]+\.[a-zA-Z]+', data)
    result = re.findall('.+@.+\.[a-zA-Z]+', data)
    return result


html = ('<div class="s-top-nav" style="display:none;">'
        '</div><div class="s-center-box"></div>')

def get_html_data(data):
    """
    获取style中的display:
    使用非贪婪模式
    """
    result = re.findall('style="(.*?)"', data)
    return result

def get_all_data_html(data):
    """
    获取html中所有等号后双引号内的字符
    :param data:
    :return:
    """
    result = re.findall('="(.+?)"', data)
    return result


if __name__ == '__main__':
    result = check_url('https://www.baidu.com')
    print(result)

    result = get_url('https://www.baidu.com')
    print(result, 'https')

    result = get_url('http://www.baidu.com')
    print(result, 'http')

    result = get_email('insane@163.net')
    print(result)

    result = get_html_data(html)
    print(result)

    result = get_all_data_html(html)
    print(result)

True
www.baidu.com https
www.baidu.com http
['insane@163.net']
['display:none;']
['s-top-nav', 'display:none;', 's-center-box']

Process finished with exit code 0