python分頁爬取百度貼吧

import requests


class Tieba:
    def __init__(self, tieba_name):
        self.url_temp = "http://tieba.baidu.com/f?ie=utf-8&kw=" + tieba_name + "&pn={}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
        self.tieba_name = tieba_name
        print(self.url_temp)

    def get_url_list(self):  # 生成動態URL
        url_list = []
        for i in range(1000):
            url_list.append(self.url_temp.format(i * 50))
        return url_list

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

    def save_html(self, html_str, page_num):  # 保存文件到本地
        file_path = "{} - 第{}頁.html".format(self.tieba_name, page_num)
        with open(file_path, 'a', encoding="utf-8") as f:
            f.write(html_str)

    def run(self):  # 主要邏輯實現
        url_list = self.get_url_list()
        for url in url_list:
            html_str = self.pase_url(url)
            page_num = url_list.index(url)
            self.save_html(html_str, page_num)


if __name__ == '__main__':
    tieba = Tieba('廣州領養')
    tieba.run()