Python正则表达式的小练习分享

import re


url_ture = "https://www.csdn.net/"
url_false = "ftp://110.110.110.110:8080"

def check_url(url):
    result = re.findall('[a-zA-z]{4,5}://\w*\.*\w+\.\w+', url)

    if not len(result) == 0:
        return 'url 是一个合法的网站地址'
    else:
        return 'url 是一个不合法的网站地址'


def get_url(url):
    result = re.findall('Https://(\w*\.*\w+\.\w+)', url)

    if not len(result) == 0:
        return result[0]
    else:
        return []



if __name__ == '__main__':
    result_true = check_url(url_ture)
    print(result_true)
    result_false = check_url(url_false)
    print(result_false)

    result_url_01 = check_url("http://csdn.com")
    print(result_url_01)
    result_url_02 = check_url("https://www.csdn.com")
    print(result_url_02)

    get_url_true = get_url(url_ture)
    print(get_url_true)
    get_url_false = get_url(url_false)
    print(get_url_false)

import re


email = "Neo@protonmail.com"


def get_email(email):
    # result = re.findall('[0-9a-zA-Z]+@[0-9a-zA-Z]+\.[a-zA-Z]+', email)      # 这样写比较复杂，可以使用通配符
    result = re.findall('.+@.+\.[a-zA-Z]', email)
    return result


if __name__ == '__main__':
    get_email = get_email(email)
    print(get_email)
    
# >>> 执行结果如下：
# >>> ['Neo@protonmail.com']

import re


html = ('<div class="s-top-nav" style="display:none;">'
        '</div><div class="s-center-box"></div>')		# 这是前端代码，暂时不用理解是什么意思


def get_html_data(html):
    re_g = re.compile('style="(.*?)"')      # 非贪婪模式获取 style 标签的内容
    result = re_g.findall(html)
    return result


def get_all_data_html(html):
    re_g = re.compile('="(.+?)"')
    result = re_g.findall(html)
    return result


if __name__ == '__main__':
    get_html_data = get_html_data(html)
    print(get_html_data)

    get_all_data_html = get_all_data_html(html)
    print(get_all_data_html)
    
# >>> 执行结果如下：
# >>> ['display:none;']
# >>> ['s-top-nav', 'display:none;', 's-center-box']