关于爬虫:高级爬虫实战系统掌握破解反爬技能-挑战高薪

41次阅读

共计 508 个字符，预计需要花费 2 分钟才能阅读完成。

import re
import urllib
import os

def rename(name):

name = name + '.jpg' 
return name

def getHtml(url):

page = urllib.urlopen(url)  
html = page.read()  
return html

def getImg(html):

reg = r'src="(.+?\.jpg)"pic_ext' 
imgre = re.compile(reg)  
imglist = re.findall(imgre,html)  
   
   
os.chdir("E:\\pic")    
os.getcwd()   
x=1 
for imgurl in imglist:  
    img=urllib.urlopen(imgurl)  
         
       
    name=str(x)    
    name = rename(name)    
    print(name)   
    x=x+1 
       
    f=open(name,'wb')  
    f.write(img.read())   
    f.close()

html = getHtml(“http://tieba.baidu.com/p/3553148164”)
getImg(html)
print ‘pic save!’

正文完