import urllib.request
import re

#获得当前页面的页数page_name
def get_pagenum(url):
    req = urllib.request.Request(url)
    req.add_header(‘User-Agent‘,‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36‘)
    res = urllib.request.urlopen(req)
    html = res.read().decode(‘utf-8‘)
    p = r‘<span class="current-comment-page">[^"]+</span>‘
    temp = re.search(p,html)
    page_num = temp.group()[36:39]
    return page_num


#将此页面上的图片写入我们的mm文件夹中
def get_img(page_url):
    req = urllib.request.Request(page_url)
    req.add_header(‘User-Agent‘,‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36‘)
    res = urllib.request.urlopen(req)
    html = res.read().decode(‘utf-8‘)
    p = r‘<img src="http://www.mamicode.com/([^"]+\.jpg)"‘
    url_list = re.findall(p,html)
    num = 0
    for each in url_list:
        file = open(‘C:/Users/lenovo/Desktop/mm/‘+each[-8:]+‘.jpg‘,‘wb‘)
        if each[0:5] == ‘http:‘:
            res = urllib.request.urlopen(each)
        else:
            res = urllib.request.urlopen(‘http:‘+each)
        file.write(res.read())
        file.close()

    

#只能直接运行
if __name__ == ‘__main__‘:
    url = ‘http://jandan.net/ooxx/‘
    page_num = get_pagenum(url)
    for i in range(10):   #抓取了十个页面上美女图片
        page_url = url + ‘page-‘+str(page_num)+‘#comments‘
        get_img(page_url)
        page_num = int(page_num) - 1
    


#下面是写正则的时候方便看所以粘贴过来的连接
#<img src="http://ws3.sinaimg.cn/mw600/006wUWIjgy1fgxrw8goikj30hs0qodh7.jpg" style="max-width: 480px; max-height: 750px;">

#http://jandan.net/ooxx/page-143#comments

#<span class="current-comment-page">[141]</span>

#  http://wx3.sinaimg.cn/mw600/661eb95cly1fgioxk7mk3j20xc1e01f1.jpg

#<img src="http://wx1.sinaimg.cn/mw600/006wUWIjgy1fgxg2yj5f3j30g70s6dgw.jpg" style="max-width: 480px; max-height: 750px;">