Python正则表达式 Python正则表达式的应用详解

import re

username = input('请输入用户名：')
# 通过compile编译正则表达式创建Pattern对象
username_pattern = re.compile(r'^\w{6,20}$')
print(type(username_pattern))
# 通过给Pattern对象发消息实现匹配检查
matcher = username_pattern.match(username)
print(type(matcher))
if matcher is None:
    print('无效的用户名')
else:
    print(matcher.group())

username = input('请输入用户名：')
matcher = re.fullmatch(r'\w{6,20}', username)
#^是开始符，$是结束符
# matcher = re.match(r'^\w{6,20}$', username)
if matcher is None:
    print('用户名不合法！！！')
else:
    print(matcher)
    print(matcher.group())

import re

content = """报警电话：110，我们班是Python-2105班，
我的QQ是9597658，我的手机号是13811223344，谢谢！"""

searcher = re.search(r'1[3-9]\d{9}', content)
if not searcher:
    print('没有找到手机号')
else:
    print(searcher.group())

import re

content = """报警电话：110，我们班是Python-2105班，
我的QQ是9597658，我的手机号是13811223344，谢谢！"""

pattern = re.compile(r'\d+')
matcher = pattern.search(content)
while matcher:
    print(matcher.group())
    # 从上一次匹配成功的结束位置开始搜索
    matcher = pattern.search(content, matcher.end())

import re

content = """报警电话：110，我们班是Python-2105班，
我的QQ是9597658，我的手机号是13811223344，谢谢！"""

pattern = re.compile(r'\d+')
results = pattern.findall(content)
# 没有创建正则表达式对象时，也可以用这种方法
# results = re.findall(r'\d+', content)
for result in results:
    print(result)

import re

import requests

resp = requests.get('https://www.sohu.com/')
# .表示任意字符，+表示匹配一个或任意多个，？表示惰性匹配，尽可能短的匹配
pattern = re.compile(r'href="http.+?"')
# 拿到搜狐首页
content = resp.text
matcher = pattern.search(content)
while matcher:
    print(matcher.group()[6:-1])
    matcher = pattern.search(content, matcher.end())

pattern2 = re.compile(r'title=".+?"')
title_list = pattern2.findall(content)
for title in title_list:
    print(title[7:-1])

import re

import requests

resp = requests.get('https://www.sohu.com/')
# 匹配整个a标签，但是只捕获()中的内容 ---> 正则表达式的捕获组
# .*连在一起就意味着任意数量的不包含换行的字符
pattern = re.compile(r'<a\s.*?href="(.+?)".*?title="(.+?)".*?>')
content = resp.text
results = pattern.findall(content)
for href, title in results:
    print(title)
    if not href.startswith('https://www.sohu.com'):
        href = 'https://www.sohu.com' + href
    print(href)

import re

content = '你真是一个沙雕煞笔，Fuck you!'
# pattern = re.compile(r'[傻沙煞][逼笔雕鄙]|马化腾|fuck|shit', flags=re.IGNORECASE)
# modified_content = pattern.sub('*', content)
# print(modified_content)
# |表示分支
modified_content = re.sub(r'[傻沙煞][逼笔雕鄙]|fuck|shit', '*', content, flags=re.I)
print(modified_content)

import re

poem = '床前明月光，疑是地上霜，举头望明月，低头思故乡。'
# sentences_list = re.split(r'[，。]', poem)
# sentences_list = re.split(r'，|。', poem)
pattern = re.compile(r'[，。]')
sentences_list = pattern.split(poem)
# sentences_list = [sentence for sentence in sentences_list if sentence]
# print(sentences_list)
for sentence in sentences_list:
    print(sentence)