zoukankan      html  css  js  c++  java
  • 爬虫18-多线程爬虫

    import requests
    from lxml import etree
    from urllib import request
    import os
    from queue import Queue
    import threading
    
    class Procuder(threading.Thread):
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36"
        }
        def __init__(self,page_queue,img_queue,*args,**kwargs):
            super(Procuder, 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:
                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)
                print(filename+'  下载完成!')
    
    
    def main():
        page_queue = Queue(100)
        img_queue = Queue(1000)
        for x in range(1,101):
            url = 'http://www.doutula.com/photo/list/?page=%d' % x
            page_queue.put(url)
    
        for x in range(5):
            t = Procuder(page_queue,img_queue)
            t.start()
    
        for x in range(5):
            t = Consumer(page_queue,img_queue)
            t.start()
    
    
    if __name__ == '__main__':
        main()
    

      

  • 相关阅读:
    查看JAVA的class二进制文件的方法
    常见算法整理(二)
    常见算法整理(一)
    JAVA的Spring注入机制事例详解
    Spring的PropertyPlaceholderConfigurer事例应用
    eclipse 使用总结
    Mysql的union
    filter中的DelegatingFilterProxy使用事例
    Spring组件扫描<context:component-scan/>详解
    JAVA 注解的几大作用及使用方法详解
  • 原文地址:https://www.cnblogs.com/wcyMiracle/p/12499997.html
Copyright © 2011-2022 走看看