import requests

tieba_name = input("输入贴吧名：")


class spider:

    def tieba_spider(self, tieba_name):  # 传入参数（贴吧名），定义临时URL和headers
        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 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36"}

    def url_list(self):  # 遍历需要爬的page地址列表，生成url_list列表，然后将数据返回出去
        page = int(input("输入爬取页数："))
        # url_list = []
        # for i in range(page):
        #     url_list.append(self.url_temp.format(i * 50))  # append添加临时url地址，foramt往后面预留大括号添加页码
        # return url_list
        return [self.url_temp.format(i*50) for i in range(page)]

    def get(self, url):  # 发送请求，获取响应
        print(f"抓取网页{url}")
        response = requests.get(url, headers=self.headers)
        return response.content.decode()  # 返回请求,将返回的数据字符串转换

    def save(self, html_str, page_num):  # 保存网页文件
        file_page = "{}吧第{}页.html".format(self.tieba_name, page_num)
        with open(file_page, "w", encoding="utf-8") as f:
            f.write(html_str)

    def run(self):  # 运行逻辑
        # 构造url列表
        page_list = self.url_list()
        # 遍历 发送请求，获取响应
        for url in page_list:
            html_str = self.get(url)
            # 保存
            page_num = page_list.index(url) + 1
            self.save(html_str, page_num)


run = spider()
run.tieba_spider(tieba_name)
run.run()