<image src="data:image/bg.jpg"/>

# -*- coding: utf-8 -*-
import urllib, httplib, urlparse
import sys
import redef httpExists(url):host, path = urlparse.urlsplit(url)[1:3]if ':' in host:# port specified, try to use ithost, port = host.split(':', 1)try:port = int(port)except ValueError:print 'invalid port number %r' % (port,)return Falseelse:# no port specified, use default portport = Nonetry:connection = httplib.HTTPConnection(host, port=port)connection.request("HEAD", path)resp = connection.getresponse( )if resp.status == 200:       # normal 'found' statusfound = Trueelif resp.status == 302:     # recurse on temporary redirectfound = httpExists(urlparse.urljoin(url,resp.getheader('location', '')))else:                        # everything else -> not foundprint "Status %d %s : %s" % (resp.status, resp.reason, url)found = Falseexcept Exception, e:print e.__class__, e, urlfound = Falsereturn found"""根据url获取文件名"""
def gGetFileName(url):if url==None: return Noneif url=="" : return ""arr=url.split("/")return arr[len(arr)-1]"""根据url下载文件，文件名参数指定"""
def gDownloadWithFilename(url,savePath,file):#参数检查，现忽略try:urlopen=urllib.URLopener()fp = urlopen.open(url)data = fp.read()fp.close()print 'download file url :',urlfile=open(savePath + file,'w+b')file.write(data)file.close()except IOError:print "download error!"+ urldef gDownload(url,savePath):fileName = gGetFileName(url)gDownloadWithFilename(url,savePath,fileName)def getRexgList(lines,regx,searchRegx):if lines==None : return lists =[]for line in lines:ismatch = re.search(regx,line,re.IGNORECASE)if ismatch :matchs = re.search(searchRegx,line,re.IGNORECASE)if matchs != None:groups = matchs.groups()for str in groups:if str not in lists:lists.append(str)return lists
def checkLine(lines):for line in lines :matchs = re.search(r'url\((\S+)\)',re.IGNORECASE)if matchs != None :print matchs.groups()
def  getPageLines(url):if url==None : returnif not httpExists(url): return try:page = urllib.urlopen(url)   html = page.readlines()page.close()return htmlexcept:print "getPageLines() error!"return
def getCurrentPageImage(url,savePath):lines = getPageLines(url)print 'lines.length',len(lines)regxlists =  getRexgList(lines,r'src\s*="images(\S+)"',r'src\s*="(\S+)"')if regxlists==None: return print 'getCurrentPageImage() images.length',len(regxlists)for jpg in regxlists:jpg =url + jpggDownload(jpg,savePath)def getCSSImages(link,savePath,url):lines = getPageLines(link)print 'lines.length',len(lines)regxlists =  getRexgList(lines,r'url\((\S+)\)',r'url\((\S+)\)')if regxlists==None: return print 'getCurrentPageImage() images.length',len(regxlists)for jpg in regxlists:jpg =url + jpggDownload(jpg,savePath)"""根据url获取其上的相关htm、html链接，返回list"""
def gGetHtmlLink(url):#参数检查，现忽略rtnList=[]lines=getPageLines(url)regx = r"""href="?(\S+)\.htm"""for link in getRexgList(lines,regx,r'href="(\S+)"'):link =url + linkif link not in rtnList:rtnList.append(link)print linkreturn rtnList
"""根据url获取其上的相关css链接，返回list"""
def gGetCSSLink(url):#参数检查，现忽略rtnList=[]lines=getPageLines(url)regx = r"""href="?(\S+)\.css"""for link in getRexgList(lines,regx,r'href="(\S+)"'):link = url + linkif link not in rtnList:rtnList.append(link)return rtnList
def getPageImage(url,savePath):"""getCurrentPageImage(url,savePath)""""""读取其他的CSS，html文件中的图片links=gGetHtmlLink(url)for link in links:print u'get images on link-html读取'getCurrentPageImage(link,savePath)"""links=gGetCSSLink(url)for link in links:print 'get images on link:',linkgetCSSImages(link,savePath,url)
if __name__ == '__main__':url = 'http://www.templatemo.com/templates/templatemo_281_chrome/'savePath = 'd:/tmp/'print 'download pic from [' + url +']'print 'save to [' +savePath+'] ...'getPageImage(url,savePath)print "download finished"