# _*_coding:utf-8 _*_
from bs4 import BeautifulSoup
import re
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="itle"><b>The Dormouse's story</b></p>
<p class="tory">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="tory">...</p>
"""
soup = BeautifulSoup(html_doc, 'html.parser', from_encoding='utf-8')
print '获取所有的链接'
links = soup.find_all('a')
for link in links:
print link.name, link.get_text(), link['href']
print '获取lacie的链接'
link_node = soup.find('a', href = 'http://example.com/lacie')
print link_node.name, link_node.get_text(), link_node['href']
print u'正则匹配'
link_node = soup.find('a', href = re.compile(r'il'))
print link_node.name, link_node.get_text(), link_node['href']
print '获取p段落文字'
p_node = soup.find('p', class_ = re.compile(r't'))
print p_node.name, p_node.get_text()
