1.多线程
简单说就是在一个任务进程中，采用多个线程来分别完成子任务，从而提高运行速度及效率，需要用到的模块为threading模块。
实例：
import threading
import time
def coding():
for x in range(1,4):
print('正在写%s' %x)
time.sleep(1)
def drawing():
for x in range(1,4):
print("正在画%s" %x)
time.sleep(1)
def main():
t1 = threading.Thread(target=coding)
t2 = threading.Thread(target=drawing)
t1.start()
t2.start()
if __name__ == '__main__':
main()
常用方法
threading.enumerate() 查看线程数
threading.current_thread() 查看线程的名字
继承自threading.Thread类
实例：
import threading
import time
class coding(threading.Thread):
def run(self):
for x in range(1,4):
print('正在写%s' %x)
time.sleep(1)
class drawing(threading.Thread):
def run(self):
for x in range(1,4):
print("正在画%s" %x)
time.sleep(1)
def main():
t1 = coding()
t2 = drawing()
t1.start()
t2.start()
if __name__ == '__main__':
main()
2.多线程全局变量冲突的解决
import threading
value = 0
glock = threading.Lock()
def add_value():
global value
glock.acquire() #上锁,其余线程等待中
for x in range(1000000):
value += 1
glock.release()#释放
print(value)
def main():
for x in range(2):
t = threading.Thread(target=add_value)
t.start()
if __name__ == '__main__':
main()
lock版生产者与消费者
import threading
import time
import random
gmoney = 1000
glock = threading.Lock()
totaltimes = 10
times = 0
class producer(threading.Thread):
def run(self):
global gmoney,totaltimes,times
while True:
money = random.randint(100,1000)
glock.acquire()
if times>=totaltimes:
glock.release()
break
gmoney = gmoney+money
print('%s生产者生产了%d元，剩余%d元' %(threading.current_thread(),money,gmoney))
times = times+1
glock.release()
time.sleep(0.5)
class customer(threading.Thread):
def run(self):
global gmoney
while True:
money = random.randint(100,1000)
glock.acquire()
if gmoney>=money:
gmoney -= money
print("%s消费者消费了%d元，还剩%d元" %(threading.current_thread(),money,gmoney))
else:
if times>=totaltimes:
glock.release()
break
print("%s消费者准备消费%d元，还剩%d元，不足" %(threading.current_thread(),money,gmoney))
glock.release()
time.sleep(0.5)
def main():
for x in range(3):
t = customer(name="消费者线程%d" %x)
t.start()
for x in range(5):
t = producer(name='生产者线程%d' %x)
t.start()
if __name__ == '__main__':
main()
condition版生产者与消费者(节省CPU资源)
import threading
import time
import random
gmoney = 1000
gcondition = threading.Condition()
totaltimes = 10
times = 0
class producer(threading.Thread):
def run(self):
global gmoney,totaltimes,times
while True:
money = random.randint(100,1000)
gcondition.acquire()
if times>=totaltimes:
gcondition.release()
break
gmoney = gmoney+money
print('%s生产者生产了%d元，剩余%d元' %(threading.current_thread(),money,gmoney))
times = times+1
gcondition.notify_all() #唤醒所有等待的线程
gcondition.release()
time.sleep(0.5)
class customer(threading.Thread):
def run(self):
global gmoney
while True:
money = random.randint(100,1000)
gcondition.acquire()
while gmoney<money: #判断钱是否足够
if times>=totaltimes: #判断生产者是否生产完
gcondition.release()
return
print("%s消费者准备消费%d元，还剩%d元，不足" % (threading.current_thread(), money, gmoney))
gcondition.wait() #钱不足时将线程处于等待状态，生产后唤醒
gmoney = gmoney-money
print("%s消费者消费了%d元，还剩%d元" % (threading.current_thread(), money, gmoney))
gcondition.release()
time.sleep(0.5)
def main():
for x in range(3):
t = customer(name="消费者线程%d" %x)
t.start()
for x in range(5):
t = producer(name='生产者线程%d' %x)
t.start()
if __name__ == '__main__':
main()
3.Queue线程安全队列
先进先出队列（Queue），后进先出队列（LifoQueue）
常用操作
from queue import Queue
#创建一个先进先出队列
Queue(maxsize)
#判断队列是否为空
Queue.empty()
#判断队列是否满了
Queue.full()
#获取队列最后一个数据，即最先进入队列的数据
Queue.get()
#将一个数据放到队列中
Queue.Put()
实例：Queue多线程爬取斗图吧表情
import requests
from lxml import etree
from urllib import request
from queue import Queue
import os
import re
import threading
class Producer(threading.Thread):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'
}
def __init__(self,page_queue,img_queue,*args,**kwargs): #初始化父类属性并新建属性page_queue,img_queue
super(Producer,self).__init__(*args,**kwargs) #使producer包含父类所有属性
self.page_queue = page_queue
self.img_queue = img_queue
def run(self):
while True:
if self.page_queue.empty():
break
url = self.page_queue.get()
self.page_parse(url)
def page_parse(self,url):
proxy = {
'http':'113.195.18.53:9999',
'http':'114.99.23.137:1133',
'http':'163.204.244.247:9999',
'http':'123.207.57.145:1080'
}
resp = requests.get(url,headers=self.headers,proxies=proxy)
text = resp.text
html = etree.HTML(text)
imgs = html.xpath("//div[@class='page-content text-center']//img[@class!='gif']") #过滤GIF类型
for img in imgs:
img_url = img.get("data-original")
alt = img.get("alt") #获取图片名
alt = re.sub(r'[\?？\.,，。!！“”\*]','',alt) #去除文字中的特殊符号
houzhui = os.path.splitext(img_url)[1]#获取后缀
filename = alt + houzhui #获取完整文件名
self.img_queue.put((img_url,filename)) #添加到下载队列
class Customer(threading.Thread):
def __init__(self,page_queue,img_queue,*args,**kwargs):
super(Customer,self).__init__(*args,**kwargs)
self.page_queue = page_queue
self.img_queue = img_queue
def run(self):
while True:
if self.img_queue.empty() and self.page_queue.empty():
break
img_url,filename = self.img_queue.get()
request.urlretrieve(img_url,'imgs/'+filename) #下载图片
print(filename+"打印成功")
def main():
page_queue = Queue(100)
img_queue = Queue(100)
base_url = 'https://www.doutula.com/photo/list/?page={}'
for x in range(1,3):
url = base_url.format(x)
page_queue.put(url) #添加到解析队列
for x in range(5): #创建5个生产者，即5个线程
t = Producer(page_queue,img_queue)
t.start()
for x in range(5):
t = Customer(page_queue,img_queue)
t.start()
if __name__ == '__main__':
main()
