python抓取网页的一个小例子

#!/usr/bin/python
#coding=utf-8
from BeautifulSoup import BeautifulSoup 
import urllib
import re
import time

def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html




def check(result_list,url):
#	html = getHtml("http://stock.cnstock.com/live");
	html = getHtml(url);
	soup = BeautifulSoup(html);
	myul=soup.find('ul',id='zb-list');

	first=myul.findAll('a')[0];


	result_list.append(first['href']);
	result_list.append(first['title']);

	html = getHtml(first['href']);
	#print html;

	soup = BeautifulSoup(html,fromEncoding="gb2312");

	mydiv=soup.find('div',id='qmt_content_div');

	#print mydiv;

	for item in mydiv.findAll('a'):
		result_list.append(item['href']);
		result_list.append(item.getText());

	#print result_list;

	#print len(result_list);

result_list=[];
old_result_list=[];

while True:
	check(result_list,"http://stock.cnstock.com/live");

	if cmp(old_result_list,result_list):
		print "changed";
		for li in result_list:
			print li;		
	else:
		print "no changed";
	
	old_result_list= result_list[:];
	del result_list [:];
	#time.strftime( ISOTIMEFORMAT, time.localtime( time.time() ) );
	print time.ctime();#time.localtime() ;
	time.sleep(5);