TiebaSpider04

import requests


class TiebaSpider:
    def __init__(self,tieba_name):
        self.tieba_name = tieba_name
        self.url_temp = "https://tieba.baidu.com/f?kw=" + tieba_name + "&ie=utf-8&pn={}"
        self.headers = {"User-Agent":"Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1"}

    def get_url_list(self): #1.構造url列表
        return [self.url_temp.format(i*50) for i in range(1000)]

    def parse_url(self,url): # 發送請求,獲取響應
        print(url)
        response = requests.get(url,headers=self.headers)
        return response.content.decode()

    def save_html_str(self,html_str,page_num): #保存
        file_path = "{}--第{}頁.html".format(self.tieba_name,page_num)
        with open(file_path,"w",encoding="utf-8") as f:
            f.write(html_str)
        print("保存成功")

    def run(self): #實現主要邏輯
        #1.構造url列表
        url_list = self.get_url_list()
        #2.發送請求,獲取響應
        for url in url_list:
            html_str = self.parse_url(url)
            #3.保存
            page_num = url_list.index(url) + 1
            self.save_html_str(html_str,page_num)

if __name__ == '__main__':
    tieba_spider = TiebaSpider("李毅")
    tieba_spider.run()