Zulko

## docx2md.md

      
              1 file
            
          
              25 forks
            
          
              16 comments
            
          
              126 stars
            
          
                vdavez
                / docx2md.md
            
            
              Last active
              April 21, 2024 20:05
            
              
                Convert a Word Document into MD
              
          
    Converting a Word Document to Markdown in Two Moves

The Problem

A lot of important government documents are created and saved in Microsoft Word (*.docx). But Microsoft Word is a proprietary format, and it's not really useful for presenting documents on the web. So, I wanted to find a way to convert a .docx file into markdown.
The Solution

As it turns out, there are several open-source tools that allow for conversion between file types. Pandoc is one of them, and it's powerful. In fact, pandoc's website says "If you need to convert files from one markup format into another, pandoc is your swiss-army knife." But, although pandoc can convert from markdown into .docx, it doesn't work in the other direction.

  
## nginx.conf
#
# CORS header support
#
# One way to use this is by placing it into a file called "cors_support"
# under your Nginx configuration directory and placing the following
# statement inside your **location** block(s):
#
#   include cors_support;
#
# As of Nginx 1.7.5, add_header supports an "always" parameter which

## sqlite3-example.py
import sqlite3

# open connection and get a cursor
conn = sqlite3.connect(':memory:')
c = conn.cursor()

# create schema for a new table
c.execute('CREATE TABLE IF NOT EXISTS sometable (name, age INTEGER)')
conn.commit()

## index.html
<!DOCTYPE html>
<html>
  <head>
    <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
    <script src="http://d3js.org/d3.v2.js"></script>
  </head>
  <body>
    <script type="text/javascript">
/**
 * A convenient function for taking a transformation (with rotation) on

## nwxpython.py
import networkx as nx
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
img=mpimg.imread('/home/shobhit/Desktop/shobhit.jpg')
# draw graph without images
G =nx.Graph()
G.add_edge(0,1,image=img,size=0.1)
G.add_edge(1,2,image=img,size=0.05)
G.add_edge(2,3,image=img,size=0.02)
G.add_edge(3,4,image=img,size=0.075)

## video_stabilize.py
#!/usr/bin/env python

""" Video stabilization with OpenCV (>=2.3) and Hugin

Adrien Gaidon
INRIA - 2012

TODO: add cropping, clean-up and improve doc-strings
"""

## gist:1323387
function cartesianProductOf(){
    return _.reduce(arguments, function(mtrx, vals){
        return _.reduce(vals, function(array, val){
            return array.concat(
                _.map(mtrx, function(row){ return row.concat(val); })
            );
        }, []);
    }, [[]]);
}

## gist:260331
import os
import subprocess
import multiprocessing

def q_runner(n_procs, list_item, function, *args):
    '''generic function used to start worker processes'''
    task_queue      = multiprocessing.Queue()
    results_queue   = multiprocessing.JoinableQueue()
    if args:
        arguments = (task_queue, results_queue,) + args

## frequency_estimator.py
from __future__ import division
from numpy.fft import rfft
from numpy import argmax, mean, diff, log, nonzero
from scipy.signal import blackmanharris, correlate
from time import time
import sys
try:
    import soundfile as sf
except ImportError:
    from scikits.audiolab import flacread

## .gitignore
*.acn
*.acr
*.alg
*.aux
*.bak
*.bbl
*.bcf
*.blg
*.brf
*.bst
	#
	# CORS header support
	#
	# One way to use this is by placing it into a file called "cors_support"
	# under your Nginx configuration directory and placing the following
	# statement inside your location block(s):
	#
	# include cors_support;
	#
	# As of Nginx 1.7.5, add_header supports an "always" parameter which
	import sqlite3

	# open connection and get a cursor
	conn = sqlite3.connect(':memory:')
	c = conn.cursor()

	# create schema for a new table
	c.execute('CREATE TABLE IF NOT EXISTS sometable (name, age INTEGER)')
	conn.commit()
	<!DOCTYPE html>
	<html>
	<head>
	<meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
	<script src="http://d3js.org/d3.v2.js"></script>
	</head>
	<body>
	<script type="text/javascript">
	/**
	* A convenient function for taking a transformation (with rotation) on
	import networkx as nx
	import matplotlib.pyplot as plt
	import matplotlib.image as mpimg
	img=mpimg.imread('/home/shobhit/Desktop/shobhit.jpg')
	# draw graph without images
	G =nx.Graph()
	G.add_edge(0,1,image=img,size=0.1)
	G.add_edge(1,2,image=img,size=0.05)
	G.add_edge(2,3,image=img,size=0.02)
	G.add_edge(3,4,image=img,size=0.075)
	#!/usr/bin/env python

	""" Video stabilization with OpenCV (>=2.3) and Hugin

	Adrien Gaidon
	INRIA - 2012

	TODO: add cropping, clean-up and improve doc-strings
	"""
	function cartesianProductOf(){
	return _.reduce(arguments, function(mtrx, vals){
	return _.reduce(vals, function(array, val){
	return array.concat(
	_.map(mtrx, function(row){ return row.concat(val); })
	);
	}, []);
	}, [[]]);
	}
	import os
	import subprocess
	import multiprocessing

	def q_runner(n_procs, list_item, function, *args):
	'''generic function used to start worker processes'''
	task_queue = multiprocessing.Queue()
	results_queue = multiprocessing.JoinableQueue()
	if args:
	arguments = (task_queue, results_queue,) + args
	from __future__ import division
	from numpy.fft import rfft
	from numpy import argmax, mean, diff, log, nonzero
	from scipy.signal import blackmanharris, correlate
	from time import time
	import sys
	try:
	import soundfile as sf
	except ImportError:
	from scikits.audiolab import flacread