Python爬虫抓取煎蛋(jandan.net)无聊图

#!/usr/bin/python
#encoding:utf-8
'''
@python 3.6.1
@author: 1109159477@qq.com
@create date: 20170611

'''
import requests
import urllib
import re
import os

#当前最大页数
url='http://jandan.net/pic'
data=urllib.request.urlopen(url).read().decode('utf-8')
max_page_num=re.findall(r'<span class.*current-comment-page.*?>[(.*?)]</span>',data)[1]

def download_pic(start_page,stop_page,download_file):
    for num in range(start_page,stop_page):
        os.chdir(download_file)#图片保存目录
        url='http://jandan.net/pic/page-%s' % num
        data=urllib.request.urlopen(url).read().decode('utf-8')
        pics=re.findall(r'<a href="//(.*?)" target.*?</a><br />',data, re.I|re.S|re.M)
        for i in pics:
            i='http://'+i
            r=requests.get(i)
            pic_name=i[28:100]
            with open(pic_name,'wb') as f:
                f.write(r.content)
                f.close()

if __name__=='__main__':
    print('当前最大页数为:  %s' % max_page_num)
    page1,page2=input('请输入要下载页数范围，例如     500,513 :').split(',')  
    download_pic(int(page1),int(page2),r'C:UserssamsungDesktopjd_pics')