Christopher Kullenberg christopherkullenberg

I hereby claim:

To claim this, I am signing this object:

	def pdfparser(fn):
	import subprocess
	'''Requires pdftotext to be installed on the system. Please change directories
	accordingly.'''
	f = "upload/" + fn # fn is the filename. upload/ is a directory, pls change.
	cmd = 'python3 upload/pdf2txt.py -o %s.txt %s' % (f.split('.')[0], f)
	run = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
	out, err = run.communicate()
	# display errors if they occur
	#if err:

	from subprocess import Popen, PIPE, STDOUT
	from nltk.tokenize import sent_tokenize #make sure to install the full corpus.
	import re

	aFile = '/home/christopher/Desktop/Introduction to Computation and Programming Using Python, Revised - Guttag, John V..pdf'

	def pdftoText(filename):
	'''
	Input: a PDF file
	Output: output of pdftotext.

	'''
	Input: file with LaTeX links, ex. "\href{http://example.com}{example}"
	Output: file with mardown links, ex. [example](http://example.com)
	'''

	import re
	outfile = open('filewithmarkdownlinks.md', 'w') #make up a new filename

	texfile = open('filewithlatexlinks.md', encoding='utf-8') # the file with latex links in it
	textext = texfile.readlines()