python 爬虫 睡不着觉听音频 全站爬取所有音频内容

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2020/11/27 18:33
# @Author  : huni
# @File    : 全站音频.py
# @Software: PyCharm

from threading import Thread        #多线程的包
from queue import Queue             #队列
import requests
from lxml import etree
import os


class CrawlInfo(Thread):

    #重写构造函数
    def __init__(self,url_queue,html_queue):
        Thread.__init__(self)
        #声明两个类属性
        self.url_queue = url_queue
        self.html_queue = html_queue

    #重写run方法
    def run(self):
        #爬虫代码
        headers = {
   
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.93 Safari/537.36'
        }
        while self.url_queue.empty() == False:          #当url队列中不是空的就继续爬
            url = self.url_queue.get()                  #从队列中获取一个url
            reponse = requests.get(url=url,headers=headers)