python抓取网页及网页上所有连接的演示代码，python抓取,import urlli

python抓取网页及网页上所有连接的演示代码，python抓取,import urlli

import urllib, htmllib, formatter, re, sysurl = sys.argv[1]website = urllib.urlopen("http://"+url)data = website.read()website.close()format = formatter.AbstractFormatter(formatter.NullWriter())ptext = htmllib.HTMLParser(format)ptext.feed(data)links = []links = ptext.anchorlistfor link in links:   if re.search('http', link) != None:      print(link)      website = urllib.urlopen(link)      data = website.read()      website.close()      ptext = htmllib.HTMLParser(format)      ptext.feed(data)      morelinks = ptext.anchorlist      for alink in morelinks:         if re.search('http', alink) != None:            links.append(alink)