Python Crawl (Users provide learning)

Import Urllib2,urllib,os,re

def ZZ (URL):

PATHW=OS.GETCWD ()

#图片和标题目录

Imagetitleregion=r ' <div class= "Large-imgs" >\r\n '

Imagetitlere=re.compile (imagetitleregion)

#提取文件

Downregion=u ' <a href= ' (. +?) " target= "_blank" class= "button Btn-down" title= "free download" ><i class= "Icon-down icon-white" ></i><i class= "Icon-white Icon-down-transiton" ></i> free download </a> '

Downre=re.compile (downregion)

For I in Range (5,5365+1):

Try

Response=urllib2.urlopen (Url+str (i) + '. shtml ')

Html=response.read ()

Print u ' crawl ' +str (i) +u ' page data '

#提取图片和标题

M=imagetitlere.findall (Html+re. S

Imageurl=m[0][0].decode (' Utf-8 ')

Title=m[0][1].decode (' Utf-8 ')

path=pathw+ ' \ \ ' +title+ ' _ ' +str (i)

If not (Os.path.isdir (path)):

Os.mkdir (PATH)

If Imageurl!=u ' anon ':

Urllib.urlretrieve (' http://www.cssmoban.com ' +imageurl,path+ ' \ \ ' |str (i) + '. jpg ')

#提取文件

M=downre.findall (HTML)

Urllib.urlretrieve (m[0],path+ ' \ \ ' +str (i) + '. rar ')

Print u ' crawl ' +str (i) +u ' page data complete '

Except Exception as S:

Print S,u ' failed '

Url=raw_input (' URL: ')

ZZ (URL)

Python Crawl (Users provide learning)