# -*- coding: UTF-8 -*-
from bs4 import BeautifulSoup
import re
html_doc ="""
The Dormouse's storyThe Dormouse's story
Once upon a time there were three little sisters; and their names were
Elsie,
Lacie and
Tillie;
and they lived at the bottom of a well.
...
"""
soup = BeautifulSoup(html_doc,'html.parser',from_encoding='utf8')
print "获取所有链接"
links = soup.find_all('a')
for link in links:
#link.name 节点的名字
#link['href'] 节点的href属性
#link.get_text() 节点的文本
print link.name,link['href'],link.get_text()
print "只获取含有lacie链接"
link_node = soup.find('a',href='http://example.com/lacie')
print link_node.name,link_node['href'],link_node.get_text()
print "正则匹配含有tillie链接"
link_node1 = soup.find('a',href=re.compile(r'tillie'))
print link_node1.name,link_node1['href'],link_node1.get_text()
print "获取p段落文字"
p_node = soup.find('p',class_="title")
print p_node.name,p_node.get_text()
输出结果:获取所有链接
a http://example.com/elsie Elsie
a http://example.com/lacie Lacie
a http://example.com/tillie Tillie
只获取含有lacie链接
a http://example.com/lacie Lacie
正则匹配含有tillie链接
a http://example.com/tillie Tillie
获取p段落文字
p The Dormouse's story