当前位置：首页 > news >正文

爬虫学习异步爬虫(五)

news 2025/9/11 7:53:19

多线程多进程协程

进程运行中的程序
线程被CPU调度的执行过程,操作系统运算调度的min单位
在进程之中,进程中实际运作单位

from threading import Thread#创建任务
def func(name):for i in range(100):print(name,i)if __name__ == '__main__':#创建线程t1 = Thread(target = func,args=("一一一",))#Thread() ,必须要求元组t2 = Thread(target = func,args=("二二二",))t1.start()t2.start()
print("我是主线程")
#1个主线程  2个副线程

面向对象方法

from threading import Threadclass MyThread(Thread):def __init__ (self,name):#init 传参super(MyThread,self).__init__()#初始化self.name = namedef run(self): #run方法 -->返回值可不写for i in range(100):print(self.name,i)if __name__ == '__main__':t1 = MyThread("一一一")t2 = MyThread("二二二")t1.start()t2.start()

线程池

from concurrent.futures import ThreadPoolExecutordef func(name):for i in range(10):print(name,i)if __name__ == '__main__':with ThreadPoolExecutor(10) as t:for i in range(100):t.submit (func,f"num{i}")

返回值使用

from concurrent.futures import ThreadPoolExecutordef func(name):for i in range(10):print(name,i)return namedef fn(res):print(res.result())if __name__ == '__main__':with ThreadPoolExecutor(10) as t:for i in range(100):t.submit (func,f"num{i}").add_done_callback(fn)   #返回 即执行 callback函数#顺序不确定

map映射
map返回值有顺序

from concurrent.futures import ThreadPoolExecutordef func(name):for i in range(10):print(name,i)return namedef fn(res):print(res.result())if __name__ == '__main__':with ThreadPoolExecutor(10) as t:for i in range(100):t.submit (func,f"num{i}").add_done_callback(fn)   #返回   即执行 callback函数   顺序不确定#绑定fn函数   fn 返回值-result()?

if __name__ == '__main__':with ThreadPoolExecutor(10) as t:result = t.map(func,["111","222","333"])for r in result:print(r)# map 返回值为生成器,返回顺序一致

线程池案例

#北京新发地
import  requests
from lxml import etree
from concurrent.futures import ThreadPoolExecutor#线程池f = open("线程池案例.csv","w",encoding="utf-8")def download (url):resp = requests.get(url)tree = etree.HTML(resp.text)tr_list = tree.xpath("//table[@class='hq_table']/tr")for tr in tr_list:td_texts = tr.xpath("./td/text()")s = ",".join(td_texts)f.write(s)f.write('\n')if __name__ =='__main__':with ThreadPoolExecutor(10) as t: #线程池for i in range(1,16964):url = f"http...{i}.shtml"#download(url) 线程池不能这么干t.submit(download,url)