【Pyton】【小甲鱼】爬虫4-XXOO

 import urllib.request
 import os def open_url(url):
     req=urllib.request.Request(url)
     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36')
     response=urllib.request.urlopen(url)
     html=response.read()     print(url)
     return html def get_page(url):
     html=open_url(url).decode('utf-8')     a=html.find('current-comment-page')+23 #23代表偏移
     b=html.find(']',a) #a代表起始位置
     return html[a:b] def find_imgs(url):
     html=open_url(url).decode('utf-8')
     img_addrs=[]
    #图片的左右边界
     a=html.find('img src=')
     while a!=-1:
         b=html.find('.jpg',a,a+255)
         if b!=-1:
             img_addrs.append(html[a+9:b+4])
         else:
             b=a+9
         a=html.find('img src=',b)     for each in img_addrs:
         print(each)
     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=open_url(each)
             f.write(img) def download_mm(folder='OOXX',pages=10):
     os.mkdir(folder)
     os.chdir(folder)     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=str('http')+find_imgs(page_url)
         save_imgs(folder,img_addrs) if __name__=='__main__':
     download_mm()