常用正则表达式最强汇总（含Python代码举例讲解+爬虫实战）

#导入re模块
import re
pattern = re.compile(r'python')
# 使用re.match匹配文本，获得匹配结果，无法匹配时将返回None
result1 = re.match(pattern,'python')
result2 = re.match(pattern,'pythonn CQC!')
result3 = re.match(pattern,'pthon CQC!')
print(result1)
print(result2)
print(result3)

"""
结果:
<_sre.SRE_Match object; span=(0, 6), match='python'>
<_sre.SRE_Match object; span=(0, 6), match='python'>
None
"""

import re
pattern = re.compile(r'python')
#从“hello pythonnnnn!”中匹配“python”
result1 = re.search(pattern,'hello pythonnnnn!')
#从“hello pyhon!”中匹配“python”
result2 = re.search(pattern,'hello pyhon!')
print(result1)
print(result2)

"""
结果:
<_sre.SRE_Match object; span=(6, 12), match='python'>
None
"""

import re
#以一位或者多位数字作为分割间隔
pattern = re.compile(r'\d+')
print(re.split(pattern,'python1java2php3js'))
#只分割两次
print(re.split(pattern,'python1java2php3js',maxsplit=2))

"""
结果:
['python', 'java', 'php', 'js']
['python', 'java', 'php3js']
"""

import re
pattern = re.compile(r'\d+')
print(re.findall(pattern,'python1java2php3js2245'))

"""
结果:
['1', '2', '3', '2245']
"""

import re
#以一位或者多位数字作为搜索条件
pattern = re.compile(r'\d+')
#搜索结果得到一个集合，通过循环对集合遍历输出
for item in re.finditer(pattern,'python1java2php3js2245'):
  print(item.group())

"""
结果:
1
2
3
2245
"""

import re
pattern1 = re.compile(r'music')
#例1中“i love the music”里的music替换成python
print(re.sub(pattern1, 'python', 'i love the music'))
pattern2 = re.compile(r'(\d+)')
#例2中“数字123 和9”被python替换。
print(re.sub(pattern2, 'python', 'My number is 123 and my favorite number is 9'))

"""
结果:
i love the python
My number is python and my favorite number is python
"""

import re
#以一位或者多位数字作为替换条件
pattern1 = re.compile(r'(\d+)')
#用“python”替换数字（一位或者多位），最后返回替换结果和替换次数
print(re.subn(pattern1, 'python', 'My number is 123 and my favorite number is 9'))
pattern2 = re.compile(r'(\d+)')
print(re.subn(pattern2, 'python', 'My number is 123 and my favorite number is 9',1))

"""
结果:
('My number is python and my favorite number is python', 2)
('My number is python and my favorite number is 9', 1)
"""

import requests
import re
import json
# 设置代理服务器
headers = {
    'User_Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36'
}
#请求连接
url = "http://book.chenlove.cn/book/12242/39a44ff6dd27f.html"
response = requests.get(url, headers=headers)
if response.status_code == 200:
    # 转化为utf-8格式，不加这条语句，输出爬取的信息为乱码
    response.encoding = 'utf8'
    #获取到源码
    html = response.text
    # 正则表达式解析小说章节标题
    pattern1 = re.compile('<h3>(.+)</h3>')
    title = re.findall(pattern1, html)[0]
    #正则表达式解析小说章节正文内容
    text = re.findall(r"<p>(.*?)</p>", html,re.S)[2:-1][0].split("</div>")[0]
    # 打印输出
    print(title)
    print(text)

"""
结果:
第一章 北灵院
     烈日如炎,灼热的阳光从天空上倾洒下来，令得整片大地都是处于一片蒸腾之中，杨柳微垂，......
"""