Python3爬虫-贴吧爬虫代码

~

世上的所有事物都能被定义，除了你自己。

~

# -*- coding: gbk -*-
import requests


class TiebaSpider:
    def __init__(self, tieba_name):
        self.tieba_name = tieba_name
        # 获取贴吧的url
        self.url_temp = "http://tieba.baidu.com/f?kw=" + tieba_name + "&ie=utf-8&pn={}"
        # 模拟浏览器的请求头
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"}

    def get_url_list(self):  # 1.构造url列表
        # url_list = []
        # for i in range(5):
        #     url_list.append(self.url_temp.format(i*50))
        # return url_list
        return [self.url_temp.format(i * 50) for i in range(5)]

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

    def save_html(self, html_str, pageNum):  # 保存html字符串
        file_path = "{}-第{}页.html".format(self.tieba_name, pageNum)
        with open(file_path, "w", encoding="utf-8") as file:  # "贴吧-第一页.html"
            file.write(html_str)

    def run(self):  # 实现主要逻辑
        # 1.构造url列表
        url_list = self.get_url_list()
        # 2.遍历，发送请求，获取响应
        for url in url_list:
            html_str = self.parse_url(url)
            # 3.保存
            pageNum = url_list.index(url) + 1  # 页码数
            self.save_html(html_str, pageNum)


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