# 下面的一段HTML代码将作为例子被多次用到.这是 爱丽丝梦游仙境的 的一段内容(以后内容中简称为 爱丽丝 的文档):
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>
"""
# 使用BeautifulSoup解析这段代码,能够得到一个 BeautifulSoup 的对象,并能按照标准的缩进格式的结构输出:
from bs4 import BeautifulSoup
# soup = BeautifulSoup(html_doc)
# 如果BeautifulSoup(html_doc)就这样不做任何处理，回报一个 GuessedAtParserWarning 解析器警告
# 接着往下面看，添个解析器就好
soup = BeautifulSoup(html_doc, 'html.parser')
# print(soup.prettify())
# 几个简单的浏览结构化数据的方法:
print(soup.title)
# <title>The Dormouse's story</title>
print(soup.title.name)
# title
print(soup.title.string)
# The Dormouse's story
# 上一级标签名字
print(soup.title.parent.name)
# head
print(soup.p)
# <p class="title"><b>The Dormouse's story</b></p>
print(soup.p['class'])
# ['title']
print(soup.a)
# <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
print(soup.find_all('a'))
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
print(soup.find(id="link3"))
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
print(soup.find('<body>'))
