21天打造分布式爬蟲-多線程下載表情包（五）

5.1.threading模塊

簡單使用

import threading,time

def coding():
    for x in range(3):
        print('正在寫代碼%s'%x)
        time.sleep(2)

def drawing():
    for x in range(3):
        print('正在畫畫%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.生產者和消費者

Lock模式的生產者和消費者

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()
            #只生產10次，超過就停止，必須把鎖給釋放掉，否則產生死鎖
            if gTimes >= gTotalTimes:
                gLock.release()
                break
            gMoney += money
            print('%s生產了%d元錢,剩余%d元錢' % (threading.current_thread(), money, gMoney))
            #生產一次，次數加1，總共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消費了%d元錢,剩余%d元錢' % (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.下載表情包

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

解析：xpath

不用多線程，速度相對會很慢

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))
        #圖片地址
        img_url = img.get('data-original')
        #圖片名字
        alt = img.get('alt')
        #替換掉名字里面的特殊字符
        alt = re.sub(r'[\?？\.，。！!\*]','',alt)
        #獲取圖片的后綴名（.gif .jpg）
        suffix = os.path.splitext(img_url)[1]
        #保存的時候完整的圖片名字
        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()

利用多線程

 main()

• 定義兩個隊列，和創建多線程
• page_queue()：存放每一頁的url
• img_queue()：存放每一頁里面所有的表情的url

Producer()

• 從page_queue()隊列中去每一頁的url，直到隊列為空則break
• 用xpath提取出每一頁的所有圖片的url
• 把每個圖片的url和名字存放到img_queue()隊列里面

Consumer()

• 從img_queue()隊列中取出圖片的url和名字
• 下載保存
• 直到page_queue()和img_queue()兩個隊列都為空則break

代碼

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))
            #圖片地址
            img_url = img.get('data-original')
            #圖片名字
            alt = img.get('alt')
            #替換掉名字里面的特殊字符
            alt = re.sub(r'[\?？\.，。！!\*]','',alt)
            #獲取圖片的后綴名（.gif .jpg）
            suffix = os.path.splitext(img_url)[1]
            #保存的時候完整的圖片名字
            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("已下載完一張圖片")


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()

結果：