![在这里插入图片描述](https://i-blog.csdnimg.cn/blog_migrate/758bc868adfca2f5b6093115cb3606ad.png)
![在这里插入图片描述](https://i-blog.csdnimg.cn/blog_migrate/e48e3db3dfa95703a06da6e870e6edff.png)
from bs4 import BeautifulSoup
html_doc = """
<!DOCTYPE html>
<!--STATUS OK-->
<html>
<head>
<meta content="text/html;charset=utf-8" http-equiv="content-type"/>
<meta content="IE=Edge" http-equiv="X-UA-Compatible"/>
<meta content="always" name="referrer"/>
<link href="https://ss1.bdstatic.com/5eN1bjq8AAUYm2zgoY3K/r/www/cache/bdorz/baidu.min.css" rel="stylesheet" type="text/css"/>
<title>百度一下,你就知道 </title>
</head>
<body link="#0000cc">
<div id="wrapper">
<div id="head">
<div class="head_wrapper">
<div id="u1">
<a class="mnav" href="http://news.baidu.com" name="tj_trnews">
新闻 </a>
<a class="mnav" href="https://www.hao123.com" name="tj_trhao123">
hao123 </a>
<a class="mnav" href="http://map.baidu.com" name="tj_trmap">
地图 </a>
<a class="mnav" href="http://v.baidu.com" name="tj_trvideo">
视频 </a>
<a class="mnav" href="http://tieba.baidu.com" name="tj_trtieba">
贴吧 </a>
<a class="bri" href="//www.baidu.com/more/" name="tj_briicon" style="display: block;">
更多产品 </a>
</div>
</div>
</div>
</div>
</body>
</html>
"""
soup = BeautifulSoup(html_doc, "html.parser")
print(soup.get_text())
print(soup.prettify())
print(soup.head)
print(soup.head.find_all('meta'))
print(soup.title)
print(soup.title.string)
print(soup.head.link.get('href'))
print(soup.head.link['href'])
print(soup.body)
for link in soup.find_all('a'):
print(link.get('href'))
for text in soup.find_all('a'):
print(text.get_text)
print(soup.find(id="u1"))
print(soup.head.name)
print(soup.a.attrs)
print(soup.a.get('class'))
print(soup.a['class'])
soup.a['class'] = 'newclass'
print(soup.a)
del soup.a['class']
print(soup.a)
print(soup.title.string)
print(type(soup.title.string))
print(type(soup))
print(soup.name)
print(soup.select('a'))
print(soup.select('.mnav'))
print(soup.select('#u1'))
print(soup.select('a[class="mnav"]'))
print(soup.select('a[href="http://tieba.baidu.com"]'))
print(soup.select('div[id="u1"]'))
t_list = bs.select("title")
print(soup.select('title')[0].get_text())