html页面爬虫

from bs4 import BeautifulSoup
import re
soup=BeautifulSoup('''<!DOCTYPE html>
                   <html1>
                   <head>
                   <meta charset="utf-8">
                   <title>菜鸟教程(runoob.com)</title>
                   </head>
                   <body>
                       <hl>我的第一标题</hl>
                       <p id="first">我的第一个段落。</p>
                   </body>
                           <table border="1">
                       <tr>
                           <td>row 1, cell 1</td>
                           <td>row 1, cell 2</td>
                       </tr>
                       <tr>
                           <td>row 2, cell 1</td>
                           <td>row 2, cell 2</td>
                       <tr>
                   </table>
                   </html>''')
print("打印head标签和我的学号")
print(soup.head,"我的学号:03") 
print("获取body标签内容",soup.body) 
print("获取id为first的标签对象",soup.find_all(id="first")) 
st=soup.text
pp = re.findall(u'[u1100-uFFFDh]+?',st)
print("获取并打印html页面中的中文字符")
print(pp)

  

原文地址:https://www.cnblogs.com/hewa123-/p/14135100.html