爬虫‘斗图吧’表情包

代码在运行的时候，可能会进行403报错，主要是在爬取当个图片时，403，求求大佬帮助

（已解决）

import os.path
import threading
import requests
from lxml import  etree
from urllib import  request
import os
import re
from queue import Queue
#法一
def parse_page(url):
    headers={'User-Agent':'',
             'Referer':'https://m.doutub.com/',
             'Cookie':''}##改成自己的
    response=requests.get(url,headers=headers)
    text=response.text
    html=etree.HTML(text)
    imgs=html.xpath("//div[@class='cell']//img")
    for img in imgs:
        img_url=img.get('data-src')
        print(img_url)
        img_name=img.get('alt')
        img_name=re.sub(r'[\?？\.。，！!]','',img_name)
        suffix=os.path.splitext(img_url)[1]#分割后缀名
        filename=img_name+suffix
        ##报错位置下
        #request.urlretrieve(img_url,'images/'+filename)#保存地址

        pic = requests.get(url=img_url,headers=headers).content
        with open('images/'+ filename, 'wb') as f:
            f.write(pic)
        # break

def main():
    for x in range(1,3):
        url='https://www.doutub.com/img_lists/wang/%d'%x
        parse_page(url)
        break

if __name__ == '__main__':
    main()



#%%
#法二
class Consumer(threading.Thread):
    def __int__(self,page_queue,img_queue,*args,**kwargs):#任何参数
        super(Consumer,self).__init__(*args,**kwargs)
        self.page_queue=page_queue
        self.img_queue=img_queue
    def run(self):
        while True:
            if self.img_queue.empty() and self.page_queue.empty():
                break
            img_url,filename=self.img_queue.get()
            request.urlretrieve(img_url,'images/'+filename)#保存地址

class Producer(threading.Thread):
    def __int__(self,page_queue,img_queue,*args,**kwargs):#任何参数
        super(Producer,self).__init__(*args,**kwargs)
        self.page_queue=page_queue
        self.img_queue=img_queue
    def run(self):
        while True:
            if self.page_queue.empty():
                break
            url=self.page_queue.get()
            self.parse_page(url)
    def parse_page(self,url):
        headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36',
                 'Referer':'https://m.doutub.com/',
                 'Cookie':'Hm_lvt_0e35b200a6045f9dd8f8887cd4626da2=1695690284; Hm_lpvt_0e35b200a6045f9dd8f8887cd4626da2=1695690392'}
        response=requests.get(url,headers=headers)
        text=response.text
        html=etree.HTML(text)
        imgs=html.xpath("//div[@class='expression-list clearfix']//img")
        for img in imgs:
            img_url=img.get('data-src')
            img_name=img.get('alt')
            img_name=re.sub(r'[\?？\.。，！!]','',img_name)
            suffix=os.path.splitext(img_url)[1]#分割后缀名
            filename=img_name+suffix
            request.urlretrieve(img_url,'images/'+filename)#保存地址
            self.img_queue.put((img_url,filename))

def main():
    page_queue=Queue(2)
    img_queue=Queue(20)
    for x in range(1,3):
        url='https://www.doutub.com/img_lists/wang/%d'%x
        page_queue.put(url)
    for x in range(5):
        t=Producer(page_queue,img_queue)
        t.start()

    for x in range(5):
        t=Consumer(page_queue,img_queue)
        t.start()

if __name__ == '__main__':
    main()