案例教学：德天和你精聊爬虫与python基础联系

最新推荐文章于 2022-12-10 20:25:06 发布

德天老师

最新推荐文章于 2022-12-10 20:25:06 发布

阅读量224

点赞数

分类专栏：爬虫

本文链接：https://blog.csdn.net/weixin_41704077/article/details/107909269

版权

爬虫专栏收录该内容

6 篇文章 0 订阅

订阅专栏

爬虫+python基础知识

标题百度贴吧爬虫源代码：

# coding=utf-8
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_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"}


    """ 1.获取到一个url列表 
     步骤a 建立空列表url_list,
     步骤b 从1到1000开始给网址self.url_temp填入数据格式信息format(i*50)   
    
    """
    def get_url_list(self):
    # url_list = []
    # for i in range(1000):
    #     url = self.url_temp.format(i*50)
    #     url_list.append(url)
    
        url_list = [self.url_temp.format(i*50) for i in range(1000)]
        return url_list

#定义函数
    def parse_url(self,url):#发送请求，获取响应
        print("现在正在请求：",url)
        r = requests.get(url,headers=self.headers)
        #对返回变量r的字节码进行解码操作
        return r.content.decode()


    def save_html_str(self,html_str,page_number):
        file_path = "{}_第{}页.html".format(self.tieba_name,page_number)
        with open(file_path,"w",encoding="utf-8") as f:
            f.write(html_str)
        print("保存成功")


    def run(self):#实现我们的主要逻辑
        #1.url list
        url_list = self.get_url_list()
    #2.遍历url，发送请求，获取响应
        for url in url_list:
            html_str = self.parse_url(url)
            #3.保存
            page_number = url_list.index(url)+1
            self.save_html_str(html_str,page_number)

search = input("请输入贴吧中文名字:")
if __name__ == '__main__':
    #   给类TiebaSPider传入参数，贴吧名，同时调用类新实例名称：tieba_spider
    #   调用实例的方法run()
    tieba_spider = TiebaSPider(search)
    tieba_spider.run()