通过爬取百度贴吧的案例来了解爬虫的基本使用

from urllib import request
import re

# 定义了一个URL
page = 100
url = "https://tieba.baidu.com/f?kw=%E6%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/99.0.4844.74 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'<a rel="noopener".*?title=(.*?)\s.*?>(.*?)</a>')
    # 匹配html
    items = re.findall(pattern,content)
    for i in items:
        print('标题：'+i[0]+" "+'内容：'+i[1])
except request.URLError as e:
    # 打印响应码
    if hasattr(e,'code'):
        print(e.code)
    # 打印异常原因
    if hasattr(e,'reason'):
        print(e.reason)

标签：re,打印,request,爬虫,content,案例,print,刘益长,headers
来源： https://www.cnblogs.com/wmlr/p/16025909.html