>>> from bs4 import BeautifulSoup #导入
>>> soup = BeautifulSoup(url.content,"lxml")
>>> print(soup.prettify) #格式化代价
>>> print(soup.title.string)
郑州轻工业学院OJ #打印title
>>> print(soup.title)
<title>郑州轻工业学院OJ</title>
标签选择器:
>>> print(soup.a)
<a class="navbar-brand" href="./" style="font-weight:bold;">郑州轻工业学院OJ</a>
>> print(soup.title.name)
title
以zzuli的zcm网为抓取对象:
>>> print(soup.div.attrs['class'])
['container']
>>> print(soup.nav.attrs['class'])
['navbar', 'navbar-default']
>>> print(soup.nav.attrs['role'])
navigation
(可使用此方法获取标签后对应的内容)
其余的写法:
>>> print(soup.nav['role'])
navigation