python futures 练习

最新推荐文章于 2024-09-12 16:27:55 发布

原创最新推荐文章于 2024-09-12 16:27:55 发布 · 置顶 · 367 阅读

CC 4.0 BY-SA版权

本文通过一个具体的示例介绍了如何使用 Python 的 concurrent.futures 模块进行多线程编程，实现图片验证码的批量下载及识别。文章展示了 ThreadPoolExecutor 的两种主要使用方式：submit 和 map 方法，并对比了它们的应用场景。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

闲来无事,看看python futures 多线程这块,确实方便牛皮

from concurrent.futures import ThreadPoolExecutor
import requests
import random
import pytesseract
from PIL import Image

url = ["http://www.epicc.com.cn/wap/CreateImage?randName=verifypicForCar&next=%d"%x for x in range(10)]

h = {
    "Referer":"http://www.epicc.com.cn/wap/views/policyClaim/index.jsp",
    "User-Agent":"Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Mobile Safari/537.36",
}

def aaa(url):
    filename = str(random.random()).split('.')[-1]
    info = requests.get(url,headers=h).content
    f=open(filename+".png","wb")
    f.write(info)
    f.close()
    return filename

def shibie(res):
    res = res.result()

    image = Image.open(res+".png")
    code = pytesseract.image_to_string(image)
    f = open('1.txt',"a+")
    f.write(code+"\n")
    f.close()

ex = ThreadPoolExecutor(max_workers=10)
for i in url:
    ex.submit(aaa,i).add_done_callback(shibie)

随手写的很low

url = ["http://www.epicc.com.cn/wap/CreateImage?randName=verifypicForCar&next=%d"%x for x in range(1)]

h = {
    "Referer":"http://www.epicc.com.cn/wap/views/policyClaim/index.jsp",
    "User-Agent":"Mozilla/5.0 (Linux; Android 5.0; SM-G900P Build/LRX21T) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Mobile Safari/537.36",
}
filename = str(random.random()).split('.')[-1]
def aaa(url):
    info = requests.get(url,headers=h).content
    f=open("ttt/"+filename+".png","wb")
    f.write(info)
    f.close()
    return "OK"

s = time.time()
ex = ThreadPoolExecutor(max_workers=10)
res = ex.map(aaa,url)
print list(res)
e = time.time()
print "多线程用时",e-s