python爬虫——爬老友记贴吧帖子-CSDN博客

本文链接：https://blog.csdn.net/woiangaoiowe/article/details/105827122

import requests

class TiebaSpider:
    """创建贴吧爬虫类"""
    def __init__(self, tieba_name):
        """初始化方法，传入需要爬取的贴吧的名称：六人行(老友记)"""
        self.tieba_name = tieba_name
        # 通过观察贴吧的url地址
        # https://tieba.baidu.com/f?kw=六人行&ie=utf-8&pn=50
        # ，我们可以发现url地址中通过kw来控制贴吧名称   通过pn来控制页数，所以我们代码可以将这两处做参数化
        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/81.0.4044.122 Safari/537.36"}

    def get_url_list(self):
        """获取请求列表"""
        url_list = list()
        for i in range(1000):
            # 遍历页数，将获取到的页数传入类属性  url_temp中完成参数 pn的值填充
            url_list.append(self.url_temp.format(i*50))
        return url_list

    def run_url(self, url):
        """执行请求"""
        print(url)
        response = requests.get(url, headers=self.headers)
        return response.content.decode()

    def save_html(self, html_str, page_num):
        """保存爬取到的网页"""
        file_path = "{}-第{}页.html".format(self.tieba_name, page_num)
        with open(file_path, "w", encoding="utf-8") as f:
            f.write(html_str)

    def run(self):
        # 构造url列表
        url_list = self.get_url_list()
        # 遍历请求列表，发送请求，获取响应内容
        for i in url_list:
            html_str = self.run_url(i)
            # 3、保存
            page_num = url_list.index(i)        # 因为我们是按照页码来构建的url地址，所以i所在url_list列表的下标就是页码数
            self.save_html(html_str, page_num)

if __name__ == '__main__':
    tieba_spider = TiebaSpider("六人行")
    tieba_spider.run()

结果：