21天打造分布式爬虫-多线程下载表情包（五）

最新推荐文章于 2021-11-09 00:20:14 发布

weixin_33709219

最新推荐文章于 2021-11-09 00:20:14 发布

阅读量101

点赞数

文章标签：爬虫

5.1.threading模块

简单使用

import threading,time

def coding():
    for x in range(3):
        print('正在写代码%s'%x)
        time.sleep(2)

def drawing():
    for x in range(3):
        print('正在画画%s'%x)
        time.sleep(2)

def main():
    t1 = threading.Thread(target=coding)
    t2 = threading.Thread(target=drawing)
    t1.start()
    t2.start()

if __name__ == '__main__':
    main()

5.2.生产者和消费者

Lock模式的生产者和消费者

import threading
import random,time

gMoney = 1000
gLock = threading.Lock()
gTotalTimes = 10
gTimes = 0


class Producer(threading.Thread):
    def run(self):
        global gMoney
        global gTimes
        while True:
            money = random.randint(100,1000)
            gLock.acquire()
            #只生产10次，超过就停止，必须把锁给释放掉，否则产生死锁
            if gTimes >= gTotalTimes:
                gLock.release()
                break
            gMoney += money
            print('%s生产了%d元钱,剩余%d元钱' % (threading.current_thread(), money, gMoney))
            #生产一次，次数加1，总共10次
            gTimes += 1
            gLock.release()
            time.sleep(0.5)


class Consumer(threading.Thread):
    def run(self):
        global gMoney
        while True:
            money = random.randint(100,1000)
            gLock.acquire()
            if gMoney >= money:
                gMoney -= money
                print('%s消费了%d元钱,剩余%d元钱' % (threading.current_thread(), money,gMoney))
            else:
                if gTimes >= gTotalTimes:
                    gLock.release()
                    break
            gLock.release()
            time.sleep(0.5)


def main():
    for x in range(5):
        t1 = Producer()
        t1.start()

    for x in range(2):
        t2 = Consumer()
        t2.start()

if __name__ == '__main__':
    main()

5.3.下载表情包

网址：http://www.doutula.com/photo/list/?page=1

解析：xpath

不用多线程，速度相对会很慢

import requests
from lxml import etree
from urllib import request
import os
import re

def parse_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
        'Referer': 'https://movie.douban.com/'
    }
    response = requests.get(url,headers=headers)
    text = response.text
    html = etree.HTML(text)
    imgs = html.xpath("//div[@class='page-content text-center']//img[@class!='gif']")
    for img in imgs:
        # print(etree.tostring(img))
        #图片地址
        img_url = img.get('data-original')
        #图片名字
        alt = img.get('alt')
        #替换掉名字里面的特殊字符
        alt = re.sub(r'[\?？\.，。！!\*]','',alt)
        #获取图片的后缀名（.gif .jpg）
        suffix = os.path.splitext(img_url)[1]
        #保存的时候完整的图片名字
        filename = alt + suffix
        request.urlretrieve(img_url,'C:/Users/Administrator/Desktop/images/'+filename)

def main():
    for x in range(1,10):
        url = 'http://www.doutula.com/photo/list/?page=%d'%x
        parse_page(url)

if __name__ == '__main__':
    main()

利用多线程

main()

定义两个队列，和创建多线程
page_queue()：存放每一页的url
img_queue()：存放每一页里面所有的表情的url

Producer()

从page_queue()队列中去每一页的url，直到队列为空则break
用xpath提取出每一页的所有图片的url
把每个图片的url和名字存放到img_queue()队列里面

Consumer()

从img_queue()队列中取出图片的url和名字
下载保存
直到page_queue()和img_queue()两个队列都为空则break

代码

import requests
from lxml import etree
from urllib import request
import os
import re
import threading
from queue import Queue

class Producer(threading.Thread):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36',
        'Referer': 'https://movie.douban.com/'
    }

    def __init__(self, page_queue, img_queue, *args, **kwargs):
        super(Producer, self).__init__(*args, **kwargs)
        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.parse_page(url)

    def parse_page(self,url):
        response = requests.get(url,headers=self.headers)
        text = response.text
        html = etree.HTML(text)
        imgs = html.xpath("//div[@class='page-content text-center']//img[@class!='gif']")
        for img in imgs:
            # print(etree.tostring(img))
            #图片地址
            img_url = img.get('data-original')
            #图片名字
            alt = img.get('alt')
            #替换掉名字里面的特殊字符
            alt = re.sub(r'[\?？\.，。！!\*]','',alt)
            #获取图片的后缀名（.gif .jpg）
            suffix = os.path.splitext(img_url)[1]
            #保存的时候完整的图片名字
            filename = alt + suffix
            self.img_queue.put((img_url,filename))


class Consumer(threading.Thread):
    def __init__(self,page_queue,img_queue,*args,**kwargs):
        super(Consumer, 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, 'C:/Users/Administrator/Desktop/images/' + filename)
            print("已下载完一张图片")


def main():
    page_queue = Queue(1000)
    img_queue = Queue(10000)

    for x in range(1,1758):
        url = 'http://www.doutula.com/photo/list/?page=%d'%x
        page_queue.put(url)

    for x in range(10):
        t = Producer(page_queue,img_queue)
        t.start()

    for x in range(10):
        t = Consumer(page_queue,img_queue)
        t.start()

if __name__ == '__main__':
    main()

结果：