Python实现抓取网页并且解析的实例

#!/usr/bin/python#coding=utf-8import sys import reimport urllib2from urllib import urlencodefrom urllib import quoteimport timemaxline = 2000wenda = re.compile("href=/"http://wenda.so.com/q/.+/?src=(.+?)/"")baidu = re.compile("<a href=/"http://www.baidu.com/link/?url=.+/".*?>更多知道相关问题.*?</a>")f1 = open("baidupage.txt","w")f2 = open("wendapage.txt","w")for line in sys.stdin:  if maxline == 0:    break  query = line.strip();  time.sleep(1);  recall_url = "http://www.so.com/s?&q=" + query;  response = urllib2.urlopen(recall_url);  html = response.read();                                                     f1.write(html)  m = wenda.search(html);  if m:    if m.group(1) == "110":      print query + "/twenda/t0";    else:      print query + "/twenda/t1";  else:    print query + "/twenda/t0";  recall_url = "http://www.baidu.com/s?wd=" + query +"&ie=utf-8";  response = urllib2.urlopen(recall_url);  html = response.read();  f2.write(html)  m = baidu.search(html);  if m:    print query + "/tbaidu/t1";  else:    print query + "/tbaidu/t0";  maxline = maxline - 1;f1.close()f2.close()