多线程爬虫

有时候，比如下载图片，因为下载图片是一个耗时的操作。如果采用同步的方式下载，那么效率肯定会特别慢，这时候我们就可以考虑使用多线程的方式下载

多线程的介绍
多线程的讲解请参考：https://coding.imooc.com/class/200.html
注意：由于python中的GIL的存在，所以多线程不能使用多核CPU的优势，但是在处理I/O读写和网络请求方面，仍然能够提高处理的性能

爬取斗图啦中的最新表情：http://www.doutula.com/photo/list/

单线程爬取斗图啦里的表情包

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

def parse_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36'}
    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:
        img_url = img.get('data-original')
        alt = img.get('alt')
        alt = re.sub(r'[\?？\.，。！!]','',alt)
        suffix = os.path.splitext(img_url)[1]
        filename = alt + suffix
        print(filename)
        request.urlretrieve(img_url,'images/'+filename)

def main():
    for x in range(1,2):
        url = 'http://www.doutula.com/photo/list/?page={}'.format(x)
        parse_page(url)

if __name__ == '__main__':
    time_start = time.time()
    main()
    time_end = time.time()
    print(time_end-time_start)

多线程爬取斗图啦里的表情包

生产者：获取表情图片的url
消费者：下载表情图片

image.png

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

import time

class Producer(threading.Thread):
    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):
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36'}
        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:
            img_url = img.get('data-original')
            alt = img.get('alt')
            alt = re.sub(r'[\?？\.，。！!\*]', '', alt)
            suffix = os.path.splitext(img_url)[1]
            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, 'images/' + filename)

def main():
    page_queue = Queue(100)
    img_queue = Queue(1000)
    for i in range(1,5):
        url = 'http://www.doutula.com/photo/list/?page={}'.format(i)
        page_queue.put(url)

    for x in range(5):
        t = Producer(page_queue,img_queue)
        t.start()

    for y in range(5):
        t = Consumer(page_queue,img_queue)
        t.start()

if __name__ == '__main__':
    time_start = time.time()
    main()
    time_end = time.time()
    print(time_end - time_start)