标签：
# coding:utf8
?
from bs4 import BeautifulSoup
import re
?
html_doc = """
<html><head><title>The Dormouse‘s story</title></head>
<body>
<p class="title"><b>The Dormouse‘s story</b></p>
?
<p class="story">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="story">...</p>
"""
soup = BeautifulSoup(html_doc,‘html.parser‘,from_encoding=‘utf-8‘)
?
print ‘链接‘
links = soup.find_all(‘a‘)
for link in links:
#print link
print link.name, link[‘href‘],link.get_text()
?
print ‘获取单独链接‘
link_code = soup.find(‘a‘,href=‘http://example.com/lacie‘)
print link_code.name, link_code[‘href‘],link_code.get_text()
?
print ‘正则表达式匹配‘
link_code = soup.find(‘a‘, href=re.compile(r"ill"))
#<ctrl+1> 根据re直接import未导入的模块
print link_code.name, link_code[‘href‘],link_code.get_text()
?
print ‘获取p段落文字‘
p_class = soup.find(‘p‘, class_=‘title‘)
print p_class.name,p_class.get_text()
?
yesterday
标签：
原文地址：http://www.cnblogs.com/icwangg/p/5573622.html
