多线程表情包

import requests
import threading
from lxml import etree
from fake_useragent import UserAgent
import re
from queue import Queue
# 获取url列表
def get_urls(page):
    # 创建一个队列保存网址
    url_queue = Queue(page)
    for i in range(1,page+1):
        url = f'https://www.fabiaoqing.com/biaoqing/lists/page/{i}.html'
        url_queue.put(url)
    return url_queue
# 获取图片的地址
def get_imgurl(url_queue,imgs_queue):
    url = url_queue.get()
    if not url_queue.empty():
        headers = {
            'User-Agent': UserAgent().random
        }
        html = requests.get(url=url, headers=headers)
        xml = etree.HTML(html.text)
        img_list = xml.xpath('//img[@class="ui image lazy"]')
        for img in img_list:
            item = {}
            item['title'] = img.xpath('./@title')[0]
            item['src'] = img.xpath('./@data-original')[0]
            imgs_queue.put(item)
# 保存数据
def save_data(imgs_queue):
    while not imgs_queue.empty():
        item = imgs_queue.get()
        name = item['title'] + '.' + item['src'].split('.')[-1]
        # 把文件名中的特殊字符替换掉
        name = re.sub(r'[\\/:*?"<>!]', '', name)
        print(name)
        data = requests.get(item['src']).content
        with open('./static/' + name, 'wb') as file:
            file.write(data)
if __name__ == '__main__':
    page = int(input('请输入要爬取的页数'))
    url_queue =  get_urls(page)
    imgs_queue = Queue(45 * page)
    t_list = []
    # 启动获取图片的线程
    for i in range(5):
        t = threading.Thread(target=get_imgurl,args=(url_queue,imgs_queue))
        t.start()
        t_list.append(t)
    # 等待子线程结束
    for i in t_list:
        i.join()
    # print(imgs_queue.qsize())
    # 启动下载图片的小程序
    for i in range(5):
        t = threading.Thread(target=save_data,args=(imgs_queue,))
        t.start()