Python实现抓取网页并且解析的实例

#!/usr/bin/python
#coding=utf-8

import sys 
import re
import urllib2
from urllib import urlencode
from urllib import quote
import time
maxline = 2000

wenda = re.compile("href=\"http://wenda.so.com/q/.+\"")
baidu = re.compile("<a href=\"http://www.baidu.com/link\".*?>更多知道相关问题.*")
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" + 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" + 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()