Python，匹配

from bs4 import BeautifulSoup
from urllib import request

#定义请求
req=request.Request('http://www.baidu.com')
#定义下载器
opener=request.build_opener()
#下载页面
resp=opener.open(req)
print(resp.read().decode('utf-8'))

#定义解析器
soup= BeautifulSoup(resp,'html.parser',from_encoding='utf-8')
#第一步，找到标签
links=soup.find_all('a')
for link in links:
    if hasattr(link,"href"):
        print(link.name,link.get('hred'), link.get_text())

import re

#定义正则化规则=匹配模式
pattern=re.compile(r'hello')
#匹配文本
result1=re.match(pattern,'hello hello')
print(result1)

pattern2=re.compile(r'a.c')
result2=re.match(pattern2,'abcdefg')
print(result2)

pattern3=re.compile('a\.c')
result3=re.match(pattern3,'a.cdefg')
print(result3)

pattern4=re.compile(r'a[a-h,A-z]bc')
result4=re.match(pattern4,'agbcefg')
print(result4)

pattern5=re.compile(r'a\dbc')
result5=re.match(pattern5,'a9bcdfg')
print(result5)

pattern6=re.compile(r'ab\sc')
result6=re.match(pattern6,'ab cdefg')
print(result6)

pattern7=re.compile(r'aaa\Wbbb')
result7=re.match(pattern7,'aaa@bbb')
print(result7)

#匹配邮箱12345678@qq.com
pattern8=re.compile(r'\d+@\W+\.\w+')
result8=re.search(pattern8,'fhujhfusdasdh123456@qqq.com')
print(result8)