from bs4 import BeautifulSoup
import re
html_doc = """
The Dormouse's story
once upon a time there were three little sisters; and their names were
http://example.com/elsie" class="sister" id="link1">Elsie,
http://example.com/lacie" class="sister" id="link2">Lacie and
http://example.com/tillie" class="sister" id="link3">Tillie;
and they lived at the bottom of a well.
...
"""
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['href'], link.get_text())
print('获取lacie的链接')
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ill的链接')
href_link = soup.find('a', href=re.compile(r'ill'))
print (href_link.name, href_link['href'], href_link.get_text())
print('获取p标签的段落内容')
p_node = soup.find('p', 'title')
print (p_node.name, p_node.get_text())
