node2:/root/python3#cat t16.py
import requests
import time
import threading
def download_one(url):
resp = requests.get(url)
print(resp.content)
#print('Read {} from {}'.format(len(resp.content), url))
threads=[]
def download_all(sites):
for site in sites:
t=threading.Thread(target=download_one,args=(site,))
threads.append(t)
for t in threads:
t.start()
for t in threads:
t.join()
print(threads)
def main():
sites = [
'http://192.168.137.3:9000/test111/',
'http://192.168.137.3:9000/test222/',
'http://192.168.137.3:9000/test333/',
'http://192.168.137.3:9000/test444/'
]
start_time = time.perf_counter()
python 多线程爬虫
最新推荐文章于 2022-12-17 20:20:01 发布
本文详细介绍了如何使用Python的threading模块构建一个多线程爬虫,通过并发请求提高网页抓取效率。同时,讨论了多线程爬虫中可能遇到的线程同步问题,如使用Lock对象来避免资源竞争。
摘要由CSDN通过智能技术生成