爬取百度贴吧某吧内容

import requests

class TiebaSpider:
    def __init__(self,tieba_name):
        self.tieba = tieba_name
        self.url = "https://tieba.baidu.com/f?kw="+tieba_name+"&ie=utf-8&pn={}"
        self.headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36"}

    def get_url_list(self):
        url_list = []
        for i in range(1000):
            url_list.append(self.url.format(i*50))
        return url_list
        #return [self.url.format(i*50) for i in range(1000)]

    def crawl(self,url):

        data = requests.get(url, headers=self.headers)
        return data.content.decode()

    def save(self,html_str,index):

        file_path = "{}吧第{}页.html".format(self.tieba,index)
        with open(file_path,"w",encoding="utf-8") as f:
            f.write(html_str)

    def run(self):

        url_list = self.get_url_list()
        for url in url_list:
            html_str = self.crawl(url)
            index = url_list.index(url)+1
            self.save(html_str, index)
            print("ok")

if __name__ == "__main__":

    tieba = TiebaSpider("lol")
    tieba.run()