多线程优化版（批量下载）

　　多线程优化版（批量下载）import os import time import requests import threading import concurrent.futures as fut  # 线程池 from bs4 import BeautifulSoup headers = {     ＂user-agent＂: ＂Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36 SE 2.X MetaSr 1.0＂ }   def request(url):     res = requests.get(url=url, headers=headers)     return res.content   def parse(html):     ＂＂＂     @pram: html 服务器响应的网页数据     r：返回图片标题与图片链接     ＂＂＂     bf = BeautifulSoup(html, ＂html.parser＂)     results = bf.find_all(＂img＂, {＂itemprop＂: ＂contentUrl＂})     # print(len(results))     return [[r[＂title＂], r[＂src＂]] for r in results]   def end_page(html):     ＂＂＂     @pram: html 服务器响应的网页数据     r@end_page：返回最大图片数量（值）     ＂＂＂     bf = BeautifulSoup(html, ＂html.parser＂)     end_page = bf.find(＂h1＂).text.split(＂:＂)[-1].strip()     return end_page   def make_dir(path):     ＂＂＂     @pram: path 指定路径     路径不存在，将自动创建     ＂＂＂     if not os.path.exists(path):         os.mkdir(path)   def down_img(title, img_url, path):     ＂＂＂     @pram: title 图片标题     @pram: img_url 图片链接     ＂＂＂     with open(path+title+＂.jpg＂, mode=＂wb＂)as f:         f.write(request(img_url))         print(threading.current_thread().name+＂	＂)         print(title+＂.jpg＂, ＂下载完成＂)         # time.sleep(0.1)   if __name__ == ＂__main__＂:     # 开始时间     start_time = time.time()       ＂＂＂     url地址拼接可根据end_page(html)获取最大值后除以每页数量，放入range中     ＂＂＂     urls = [         ＂https://www.hippopx.com/zh/search?q=建筑&page={0}＂.format(page) for page in range(1, 4)     ]      # 图片存放路径     path = str(os.getcwd())+＂/images/＂     make_dir(path)      # 请求、解析、下载     with fut.ThreadPoolExecutor() as pool:         htmls = pool.map(request, urls)     for html in htmls:         with fut.ThreadPoolExecutor() as pool:             results = pool.submit(parse, html).result()          with fut.ThreadPoolExecutor() as pool:             for r in results:                 pool.submit(down_img, r[0], r[1], path)     # 结束时间     end_time = time.time()      print(＂共用时:＂, end_time - start_time, ＂秒＂)