import requests
url='http://localhost:63342/Python%E8%BF%90%E8%A1%8C%E9%A1%B9%E7%9B%AE/sd.html?_ijt=7odtctsgf0pdru995lumvln8me'
res=requests.get(url)
res.status_code
res.encoding='utf-8'
from bs4 import BeautifulSoup
soud=BeautifulSoup(res.text,'html.parser')
1:取出h1标签的文本
print(soud.head.title.text)
2:取出a标签的链接
print(soud.a.attrs)
3:取出所有li标签的所有内容
print(soud.li.text)
4:取出一条新闻的标题、链接、发布时间、来源
标题：
print(soud.select('.news-list-title')[0].text)
链接：
print(soud.li.a.attrs)
发布时间：
print(soud.select('.news-list-info')[0].contents[0].text)
来源：
print(soud.select('.news-list-info')[0].contents[1].text)
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>Simple DOM Demo</title>
</head>
<body>
<h1>This is the document body</h1>
<P ID = "p1Node">This is paragraph 1.</P>
<P ID = "p2Node">段落2</P>
<a href="http://www.gzcc.cn/">广州商学院</a>
<li>
<a href="http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0328/9113.html">
<div class="news-list-text">
<div class="news-list-title" style="">我校校长杨文轩教授讲授新学期“思政第一课”</div>
<div class="news-list-description">3月27日下午，我校校长杨文轩教授在第四教学楼310室为学生讲授了新学期“思政第一课”。</div>
<div class="news-list-info"><span><i class="fa fa-clock-o"></i>2018-03-28</span><span><i class="fa fa-building-o"></i>马克思主义学院</span></div>
</div>
</a>
</li>
</body>
</html>
