python如何爬取图片到指定文件夹_爬取网站图片，并下载保存到指定文件夹

源码如下：

# -*- coding: utf-8 -*-

# @Time : 2017/5/18 17:38

# @Author : xiaojingjing

# @Site :

# @File : finde_mmimg.py

# @Software: PyCharm

import urllib.request

import os,shutil

def url_open(url):

req=urllib.request.Request(url)

req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36')

response=urllib.request.urlopen(url)

html=response.read()

return html

def get_page(url):

html=url_open(url).decode('utf-8')

a=html.find('current-comment-page')+23

b=html.find(']',a)

return html[a:b]

def find_imgs(url):

html=url_open(url).decode('utf-8')

img_addrs=[]

a=html.find('img src=')

while a!= -1:

b=html.find('.jpg',a,a+255)

if b!=-1:

img_addrs.append('http:'+html[a+9:b+4])

else:

b=a+9

a=html.find('img src=',b)

print(img_addrs)

return img_addrs

def save_imgs(folder,img_addrs):

for each in img_addrs:

filename=each.split('/')[-1]

with open(filename,'wb') as f:

img=url_open(each)

f.write(img)

def download_mm(folder='ooxx'):

pages=int(input("请输入需要下载多少页："))

print("判断文件夹是否存在..........")

if os.path.exists('ooxx'):

print("存在,删除中··········")

shutil.rmtree('ooxx')

print("删除完毕！")

else:

print("新建文件夹",folder,"中...........")

os.mkdir(folder)

os.chdir(folder)

print("新建完成..............")

url="http://jandan.net/ooxx/"

page_num=int(get_page(url))

for i in range(pages):

page_num -=i

page_url=url+'page-'+str(page_num)+'#comments'

img_addrs=find_imgs(page_url)

save_imgs(folder,img_addrs)

if __name__=='__main__':

download_mm()