Python爬取百度贴吧

可以爬取任意贴吧，自定义任意页数并且保存页面。主要用到了request模块和quote。 

​
from urllib.request import Request,urlopen
from urllib.parse import quote

def get_html(url):
    headers = {
        "User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.69"
    }
    requests = Request(url,headers=headers)
    response = urlopen(requests)
    return response.read().decode()

def save_html(html,filename):
    with open(filename,'w',encoding='utf-8') as f:
        f.write(html)

def main():

    content = input("请输入要获取哪个贴吧：")
    n = int(input("请输入要爬取多少页："))
    for i in range(n):
        url = "https://tieba.baidu.com/f?kw=" + quote(content) + "&ie=utf-8&pn={}".format(i*50)
        print(url)
        html = get_html(url)
        filename = "第" + str(i+1) + "页.html"
        save_html(html,filename)

if __name__ == '__main__':
    main()

​