BeautifulSoup demo

# coding:utf8from bs4 import BeautifulSoupimport urllib2url = "http://www.baidu.com"response = urllib2.urlopen(url)str = response.read()soup = BeautifulSoup(str,                     'html.parser',                     from_encoding='utf-8')print '获取所有链接'links = soup.find_all('a')for link in links:    print link.name, link["href"], link.get_text()