这个代码还有许多可行的改进,比如加参数argv方便改变URL,多页图片下载等
有兴趣的朋友可以自行修改,这只是基本的功能 | | | | | | | | | | | | | | | import re,urllib,urllib2 | | | | | | savepath = 'd:\\picture\\' | | | | | | url = 'http://www.zhuoku.com/zhuomianbizhi/game-gamewall/20120503162540.htm' | | urlSource = urllib.urlopen(url).read() | | | | pattern = re.compile(r'<a href="(\d+\(\d+\)\.htm)" ', re.M | re.S) | | match = pattern.findall(urlSource) | | | | if match: | | for subUrl in match: | | subUrlSource = urllib.urlopen(url[0:url.rfind('/')+1]+subUrl).read() | | sPattern = re.compile(r'var thunder_url = "(.*)";') | | picUrl = sPattern.findall(subUrlSource)[0] | | getPic = urllib2.Request(picUrl) | | getPic.add_header('Referer','http://www.zhuoku.com') | | | | f = open(savepath+picUrl[picUrl.rfind('/')+1:],'wb') | | f.write(urllib2.urlopen(getPic).read()) | | f.close() | | | | print "All done."COPY |
|