#coding=utf-8
# __author__ = ‘Hinfa‘
import re
import os
from urllib import request as req

url=‘https://baike.baidu.com/item/%E5%B9%BF%E5%B7%9E/72101?fr=aladdin‘
path=‘Test//百科广州图片2‘
os.mkdir(path)
fo=open(path+‘//filecatalog.txt‘,‘w+‘)
fo.write(‘爬取jpg目录：‘)
page=req.urlopen(url)
html=page.read().decode(‘utf-8‘)
jpgre=re.compile(r‘https.*?\.jpg‘)
jpglist=re.findall(jpgre,html)
i=0
for jpg in jpglist:
    jpg=re.sub(r‘\\\/‘,‘/‘,jpg)
    print(jpg)    
    filepath=path+‘//%d.jpg‘%i
    fo.write(‘\n‘+jpg)
    req.urlretrieve(jpg,filepath)
    i+=1
fo.write(‘\n‘+‘爬取共计‘+str(i)+‘个‘)
fo.flush()
fo.close()