多线程糗百爬虫

import requests
from lxml import etree

class Qiubai:
    def __init__(self):
        self.temp_url = "https://www.qiushibaike.com/text/page/{}"
        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):
        return [self.temp_url.format(i) for i in range(1,3)]
    
    def parse_url(self,url):
        response = requests.get(url,headers=self.headers)
        return response.content.decode()
        
    def get_content_list(self, html_str):       #提取数据
        html = etree.HTML(html_str)  #通过此方法得到elements对象，为了后续使用xpath方法
        div_list = html.xpath("//div[@id='content-left']/div")
        content_list = []
        for div in div_list:
            item = {}
            item["user_name"] = div.xpath(".//h2/text()")[0].strip()  #xpath得到的是一个列表，有一个内容就[0]
            item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
            content_list.append(item)
        return content_list
            
    def save_content_list(self, content_list):  #保存
        for content in content_list:
            print(content)
        
    def run(self): #实现的主要逻辑
        # 1.准备url列表（知道url地址的总共页数和规律，可以准备url列表，不知道规律，准备start_url地址）
        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.提取数据
            content_list = self.get_content_list(html_str)
        
            # 4.保存
            self.save_content_list(content_list)
if __name__ == "__main__":
    qiubai = Qiubai()
    qiubai.run()