Zeqi Lin linzeqipku

## docx_to_html.py
import mammoth
from zipfile import BadZipFile
import os

path='E:/dc/data/docx'
html_path='E:/dc/data/html'

def gci(filepath):
	files = os.listdir(filepath)
	for fi in files:

## readme.md

      
        
          
            
              
              3 files
            
          
          
            
              
              0 forks
            
          
          
            
              
              0 comments
            
          
          
            
              
              0 stars
            
          
        
        
          
              
          
          
            
                linzeqipku
                / readme.md
            
            
              Last active
              February 16, 2018 04:56
            
              
                Extract questions and answers from StackOverflow dump files by tags
              
          
        
      
        
  
      
    Step 1: run so-splitter-Posts.py (config: srcPath, dstPath, tagsPattern)
Step 2: run so-splitter-PostLinks.py (config: srcPath, dstPath)
	import mammoth
	from zipfile import BadZipFile
	import os

	path='E:/dc/data/docx'
	html_path='E:/dc/data/html'

	def gci(filepath):
	files = os.listdir(filepath)
	for fi in files: