python爬虫：BF4安装与使用 

'''
安装解析器：
pip3 install lxml
安装解析库：
pip3 install bs4
'''

html_doc = '''
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="sister"><b>$37</b></p>

<p class="story" id="p">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" >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>
'''
from bs4 import BeautifulSoup

# python自带解析库
#  soup = BeautifulSoup(html_doc,'html.parser')
# 调用bs4得到 一个soup对象
soup = BeautifulSoup(html_doc,'lxml')

# bs4对象
print(soup)

# bs4类型
print(type(soup))

# 美化功能
html = soup.prettify()
print(html)

　　

posted @ 2019-07-03 18:19  Auraro997  阅读(898)  评论(0)    收藏  举报