爬虫基础_陈胜

from urllib import request
import re

#定义url
page=100
url='http://tieba.baidu.com/f?kw=%6%AE%B5%E5%AD%90$ie=utf-8$pn='+str(page)

try:
    #定义请求头
    headers={'User-Agent':' Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36'}
    #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
    content=resp.read().decode("utf-8")
    print(content)
    #正则表达式
    #pattern=re.compile(r'<title>(.*)</title>')
    pattern=re.compile(r'<a rel="noopener".*?title=(.*?)\s.*?>(.*?)</a>')
    #匹配html
    items=re.findall(pattern,content)
    for i in items:
        print('标题:'+i[0]+' '+'content:'+i[1])
        #print(i)

except request.URLError as e:
    if hasattr(e,'code'):
        print(e.code)
    if hasattr(e,'reason'):
        print(e.reason)