from bs4 import BeautifulSoup
html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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>
"""
bs = BeautifulSoup(html)
print(bs.prettify())#格式化输出
print(bs.title)
print(bs.head)
print(bs.a)
print(bs.a.attrs)
print(bs.a['class'])
print(bs.p.string)
print(bs.findAll('p'))
print(bs.select('p'))
print(bs.select('.story'))
print(bs.select('.story')[0].get_text())
BeautifulSoup中的.select()
1350
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
