为什么80%的码农都做不了架构师?>>>
#!/usr/bin/python
#encoding:utf8
#author:cosmeimport re
import urllibdef getTop25ReginalSties():GETTOP25 = re.compile(r'^\<a\s+href\=\"/siteinfo/(?P<gettop>\S+)\"\>\S+\</a\>.*')url = 'http://www.alexa.com/topsites/countries/AM'urllist = []i = 0html= urllib.urlopen(url).read()file2 = open('file04.txt','w')file2.write(html)file2.close()file3 = open('file04.txt','r')while True:line = file3.readline()if not line:breakmo = GETTOP25.match(line)if mo:urltext1 = mo.group('gettop')print urltext1urllist.append(urltext1)print len(urllist)getTop25ReginalSties()