Python爬虫【实战篇】百度贴吧爬取页面存到本地

先上代码

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 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36"
        }

    def get_url_list(self):
        """构造url列表"""
        return [self.url_temp.format(i * 50) for i in range(50)]

    def parse_url(self, url):
        """发送请求 获取响应"""
        print(url)
        response = requests.get(url=url, headers=self.headers)
        return response.content

    def save_html(self, html_str, page_num):
        # 构建文件名
        file_path = "{}第{}页.html".format(self.tieba_name, page_num)
        with open(file_path, "wb") as f:
            f.write(html_str)

    def run(self):
        """实现主要逻辑"""

        url_list = self.get_url_list()

        # 遍历请求
        for url in url_list:
            html_str = self.parse_url(url=url)

            # 构建页码
            page_num = url_list.index(url) + 1

            # 创建html文件
            self.save_html(html_str, page_num)


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

转载于:https://www.cnblogs.com/tangkaishou/p/10247471.html