剛剛開始學習python,在這個時代,讓指令碼代替人去做些事情還是很值得的。
下載吧,幫我去把某個網站上所有的字型下載下來…
import urllibfrom sgmllib import SGMLParserclass URLLister(SGMLParser): def reset(self): SGMLParser.reset(self) self.urls = [] def start_a(self, attrs): href = [v for k, v in attrs if k == 'href' and v.endswith('.zip')] if href: self.urls.extend(href)Exts = 'a,b,c,d,e,f,g,h,i,j,k,l,m,n,o,p,q,r,s,t,u,v,w,x,y,z,no'URLs = ['http://www.3lian.com/ziti/zt2/fonts-' + ele + '.htm' for ele in Exts.split(',')]downloadURL = []for url in URLs: http = urllib.urlopen(url) htmlSrc = http.read() http.close() parser = URLLister() parser.feed(htmlSrc) parser.close() downloadURL.extend(parser.urls)downloadURL = ['http://www.3lian.com/ziti/zt2/' + ele for ele in downloadURL]for url in downloadURL: filename = 'D:\\TDdownload\\font-en\\' + url.split('/')[-1] print filename zipfile = open(filename, 'wb') print 'download --- ' + url http = urllib.urlopen(url) zipfile.write(http.read()) http.close() zipfile.close