python爬图-优快云博客

本文链接：https://blog.youkuaiyun.com/qq_22076631/article/details/85847521

本文介绍了一个使用Python实现的多线程爬虫程序，该程序能够从指定网站抓取图片资源并进行本地存储。通过解析网页源码，爬虫能够获取到图片的URL和名称，然后利用多线程并发下载，提高了爬取效率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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

class Producer(threading.Thread):
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}

    def __init__(self,page_queue,img_queue,*args,**kwargs):
        # 引用队列
        self.page_queue = page_queue
        self.img_queue = img_queue
        super(Producer,self).__init__(*args,**kwargs)

    def parse_page(self,url):
        # 获取所有img标签
        response = requests.get(url,headers = Producer.headers)
        response.encoding = response.apparent_encoding
        text = response.text
        html = etree.HTML(text)
        imgs = html.xpath("//div[@class = 'page-content text-center']//img[@class != 'gif']")

        for img in imgs:
            #获取图片url
            img_url = img.get('data-original')
            #设置图片保保存的名字
            alt = img.get('alt')
            alt = re.sub(r'[./,!*？。，！]','',alt)
            suffix = os.path.splitext(img_url)[1]
            filename = alt + suffix
            #把图片的url传进队列
            self.img_queue.put((img_url,filename))

    def run(self):
        while True:
            if self.page_queue.empty():
                break
            #把页面的url传出队列
            url = self.page_queue.get()
            self.parse_page(url)

class Consummer(threading.Thread):
    def __init__(self, page_queue, img_queue, *args, **kwargs):
        # 引用队列
        self.page_queue = page_queue
        self.img_queue = img_queue
        super(Consummer, self).__init__(*args, **kwargs)

    def run(self):
        while True:
            if self.page_queue.empty() and self.img_queue.empty():
                break
            #把图片的url传出队列
            img_url,filename = self.img_queue.get()
            #下载图片
            request.urlretrieve(img_url,'images/' + filename)
            print(filename + '下载完成！')

def main():
    #设置队列
    page_queue = Queue(100)
    img_queue = Queue(1000)
    for i in range(1,101):
        url = 'https://www.doutula.com/photo/list/?page=%d' % i
        #把页面的url传进队列
        page_queue.put(url)
    for i in range(10):
        t = Producer(page_queue,img_queue)
        t.start()
    for i in range(20):
        t = Consummer(page_queue,img_queue)
        t.start()

if __name__ == '__main__':
    main()