[python应用]python简单图片抓取

前言

emmmm

python简单图片抓取

import requests
import threading
import queue
from subprocess import Popen,PIPE
from bs4 import BeautifulSoup as bs
import urllib
import base64


queue=queue.Queue()

class Jiandan(threading.Thread):
        def __init__(self,queue):
            threading.Thread.__init__(self)
            self._queue=queue
            
        def run(self):
            while not self._queue.empty():
                url=self._queue.get_nowait()
                self.spider(url)
                
        def spider(self,url):
            headers={}
            r=requests.get(url)
            #选择lxml解析器
            soup=bs(r.content,'lxml')
            #查找html标签name为img的元素获取到它
            imgs=soup.find_all(name='img',attrs={})
            
            for img in imgs:
                if 'onload' in str(img):
                    img=img['org_src']
                else:
                    img=img['src']
                
                name=img.split('/')[-1]
                
                #获取的url没http:所以要加上http协议才能访问下载
                img="http:"+img
                
                #存储图片的路径地址
                lu="C:\Users\xhds1\Desktop\img\"+name
                print(lu)
                urlretrieve(img,lu)  #urlretrieve模块下载图片
               # print(name)
                
def main():
    sss=""
    for i in range(137,139):
        riqi="20200121-%s"%(i)
        
        #使用了base64模块进行URL编码  这里遇到的问题是编码后就成为了字节流类型 
        #查了资料才得知必须转换成字符串类型才行 纠结了好久
        strbs=base64.b64encode(riqi.encode(encoding="utf-8")).decode("utf-8") 
      
        queue.put("https://jandan.net/pic/"+strbs+"#comments")
                  
    threads=[]
    thread_count=5
    
    for i in range(thread_count):
        threads.append(Jiandan(queue))
    for t in threads:
        t.start()
    for t in threads:
        t.join()
        
if __name__=='__main__':
    main()

参考学习：

浅析Python3中的bytes和str类型:https://www.cnblogs.com/chownjy/p/6625299.html  

 https://www.cnblogs.com/OliverQin/p/8641700.html