python内置的线程安全队列模块叫queue
python的Queue模块中提供了同步的、线程安全的队列类
FIFO(先进先出)队列的Queue(常用)
LIFO(后进先出)lifoQueue
可以使用队列来实现线程间的同步。
| 函数 | 描述 |
|---|---|
| qsize() | 返回队列大小 |
| empty() | 判断队列是否为空 |
| full() | 判断队列是否满了 |
| get() | 从队列中获取先插入的数据 |
| put() | 将一个数据放到队列中 |
from queue import Queue | |
# 指定队列当中最多可存放5个数据 | |
queue = Queue(5) | |
for num in range(5): | |
# put()将一个数据放到队列中 | |
queue.put(num) # 队列中获取先插入的数据 | |
print("当前队列的大小为:", queue.qsize()) | |
------------------------- | |
当前队列的大小为: 5 |
from queue import Queue | |
# 指定队列当中最多可存放5个数据 | |
queue = Queue(5) | |
for num in range(5): | |
# put()将一个数据放到队列中 | |
queue.put(num) # 队列中获取先插入的数据 | |
# 判断队列是否为空 | |
print(queue.empty()) | |
print(queue.full()) | |
---------------------- | |
False | |
True |
get() 从队列中获取先插入的数据
from queue import Queue | |
# 指定队列当中最多可存放5个数据 | |
queue = Queue(5) | |
for num in range(5): | |
# put()将一个数据放到队列中 | |
queue.put(num) # 队列中获取先插入的数据 | |
print("当前队列的大小为:", queue.qsize()) | |
# get()从队列中获取先插入的数据 | |
for i in range(1,6): | |
print(queue.get(i)) | |
------------------------------------- | |
当前队列的大小为: 5 | |
0 | |
1 | |
2 | |
3 | |
4 |
个人博客推荐:白煮蛋的博客
Queue是线程安全的队列,在使用时无须加锁,可以再多线程当中直接使用
队列也是实现线程间同步的方式
from queue import Queue | |
import threading | |
import random | |
import time | |
def put_data(queue): | |
while True: | |
queue.put(random.randint(10,100)) | |
time.sleep(1) | |
print(queue.qsize()) | |
def get_data(queue): | |
while True: | |
print(f"已经获取到队列当中的--{queue.get()}--元素") | |
def main(): | |
queue = Queue(10) | |
t1 = threading.Thread(target=put_data,args=(queue,)) | |
t2 = threading.Thread(target=get_data,args=(queue,)) | |
t1.start() | |
t2.start() | |
if __name__ == '__main__': | |
main() |
产生数据的模块,就形象地称为生产者;而处理数据的模块,就称为消费者。
单单抽象出生产者和消费者,还够不上是生产者/消费者模式。该模式还需要有一个缓冲区处于生产者和消费者之间,作为一个中介。生产者把数据放入缓冲区,而消费者从缓冲区取出数据。
缓冲区
如果制造数据的速度时快时慢,缓冲区的好处就体现出来了。当数据制造快的时候,消费者来不及处理,未处理的数据可以暂时存在缓冲区中。等生产者的制造速度慢下来,消费者再慢慢处理掉。
import requests | |
from bs4 import BeautifulSoup | |
import os | |
from threading import Thread | |
from queue import Queue | |
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.26"} | |
# 生产者类 | |
class Page_Url(Thread): | |
# page_queue 生产者队列 | |
# img_queue 消费者队列 | |
def __init__(self,page_queue,img_queue): | |
super().__init__() | |
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.download_image(url) | |
def download_image(self,url): | |
resp = requests.get(url, headers=headers).text | |
# print(resp) | |
soup = BeautifulSoup(resp, "lxml") | |
image_list = soup.find_all("img", class_="ui image lazy") | |
for img in image_list: | |
title = img.get("title") | |
href = img.get("data-original") | |
self.img_queue.put((title,href)) | |
# 消费者类 | |
class Img_Url(Thread): | |
# page_queue 生产者队列 | |
# img_queue 消费者队列 | |
def __init__(self, page_queue, img_queue): | |
super().__init__() | |
self.page_queue = page_queue | |
self.img_queue = img_queue | |
def run(self): | |
while True: | |
data = self.img_queue.get() | |
title,href = data | |
try: | |
with open("./image/"+title+os.path.splitext(href)[-1],"wb") as f: | |
resp =requests.get(href).content | |
f.write(resp) | |
print(title,"保存成功!") | |
except OSError: | |
pass | |
# 判断两个队列是否全部清空 | |
if self.page_queue.empty() and self.img_queue.empty(): | |
break | |
def main(): | |
# 创建两个队列 | |
page_queue = Queue() | |
img_queue = Queue() | |
for num in range(1,6): | |
url = "https://www.fabiaoqing.com/biaoqing/lists/page/{}.html".format(num) | |
# 将前五页的url添加到生产者队列 | |
page_queue.put(url) | |
t1 = Page_Url(page_queue,img_queue) | |
t1.start() | |
t2 = Img_Url(page_queue,img_queue) | |
t2.start() | |
if __name__ == '__main__': | |
main() |
(1)创建生产者与消费者队列
(2)将前5页的url添加到生产者队列
def main(): | |
# 创建两个队列 | |
page_queue = Queue() | |
img_queue = Queue() | |
for num in range(1,6): | |
url = "https://www.fabiaoqing.com/biaoqing/lists/page/{}.html".format(num) | |
# 将前五页的url添加到生产者队列 | |
page_queue.put(url) | |
t1 = Page_Url(page_queue,img_queue) | |
t1.start() | |
t2 = Img_Url(page_queue,img_queue) | |
t2.start() |
(1)生产者队列while循环当中获取的前5页的链接,当队列为空,停止获取。
def run(self): | |
while True: | |
if self.page_queue.empty(): | |
break | |
url = self.page_queue.get() | |
self.download_image(url) |
(2)将获取的链接给到dowl_img
def download_image(self,url): | |
resp = requests.get(url, headers=headers).text | |
# print(resp) | |
soup = BeautifulSoup(resp, "lxml") | |
image_list = soup.find_all("img", class_="ui image lazy") | |
for img in image_list: | |
title = img.get("title") | |
href = img.get("data-original") |
(3)将获取到的名称和链接添加到消费者队列
self.img_queue.put((title,href)) |
(1)从队列当中获取图片名称和链接
def run(self): | |
while True: | |
data = self.img_queue.get() | |
title,href = data |
(2)保存图片
try: | |
with open("./image/"+title+os.path.splitext(href)[-1],"wb") as f: | |
resp =requests.get(href).content | |
f.write(resp) | |
print(title,"保存成功!") | |
except OSError: | |
pass | |
# 判断两个队列是否全部清空 | |
if self.page_queue.empty() and self.img_queue.empty(): | |
break |
好了, 以上是本文所有内容,希望对大家有所帮助,也希望大家对码农之家多多支持,你们的支持是我创作的动力!祝大家生活愉快!
上一篇:企业python面试题