Python爬虫获取网页信息

代码如下：

import re
from urllib import request
# 定义url
page=50
url='http://club.sanguosha.com/thread-1111069-1-1.html'

try:
    # 定义请求头
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36 Edg/99.0.1150.39'}
    # 定义请求，传入请求头
    req=request.Request(url,headers=headers)
    # 打开网页
    resp=request.urlopen(req);
    # 打印响应，解码
    #print(resp.read().decode('utf-8'))
    content=resp.read().decode('utf-8')
    # 正则表达式获取需要的网页信息
    # pattern=re.compile(r'<a.*>title=(.*?)\s{1}.?>(.*?)</a>')
    pattern=re.compile(r'<font size=(.*?)>(.*?)</font>')
    # 匹配html
    items=re.findall(pattern,content)
    # 打印解析内容
    for i in items:
        # print('标题:'+i[0]+" "+'内容'+i[1])
        print(i[1])


except request.URLError as e:
    # 打印响应码
    if hasattr(e,'code'):
        print(e.code)
    # 打印异常
    if hasattr(e,'reason'):
        print(e.reason)