···

       
1
       
1
       
+
       
import re

     

       
1
       
2
       
 
       
from html.parser import HTMLParser

     

       
3
       
3
       
+
       


     

       
4
       
4
       
+
       
WHITESPACE = re.compile(r'[\r\n\t]+')

     

       
2
       
5
       
 
       


     

       
3
       
6
       
 
       
class HTMLToMarkdownParser(HTMLParser):

     

       
4
       
7
       
 
       
    def __init__(self) -> None:

     
···

       
120
       
123
       
 
       
        

     

       
121
       
124
       
 
       
        elif tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:

     

       
122
       
125
       
 
       
            self.markdown.append('\n')

     

       
126
       
126
       
+
       
    

     

       
127
       
127
       
+
       
    def handle_data(self, data):

     

       
128
       
128
       
+
       
        self.markdown.append(data)

     

       
123
       
129
       
 
       
    

     

       
124
       
130
       
 
       
    def reset(self):

     

       
125
       
131
       
 
       
        """Reset the parser state for reuse."""