print("[-+-] starting pdf_csv.py...")

print("[-+-] import a pdf and convert it to a csv")

print("[-+-] importing required packages for pdf_csv.py...")

import os

import tabula # simple wrapper for tabula-java, read tables from PDF into csv

print("[-+-] pdf_csv.py packages imported! \n")

def pdf_csv(): # convert pdf to csv

print("[-+-] default filenames:")

filename = "sample1"

pdf = filename + ".pdf"

csv = filename + ".csv"

print (pdf)

print (csv + "\n")

print("[-+-] default directory:")

print("[-+-] (based on current working directory of python file)")

defaultdir = os.getcwd()

print (defaultdir + "\n")

print("[-+-] default file paths:")

pdf_path = os.path.join(defaultdir, pdf)

csv_path = os.path.join(defaultdir, csv)

print (pdf_path)

print (csv_path + "\n")

print("[-+-] looking for default pdf...")

if os.path.exists(pdf_path) == True: # check if the default pdf exists

print("[-+-] pdf found: " + pdf + "\n")

pdf_flag = True

else:

print("[-+-] looking for another pdf...")

arr_pdf = [defaultdir for defaultdir in os.listdir() if defaultdir.endswith(".pdf")]

if len(arr_pdf) == 1: # there has to be only 1 pdf in the directory

print("[-+-] pdf found: " + arr_pdf[0] + "\n")

pdf_path = os.path.join(defaultdir, arr_pdf[0])

pdf_flag = True

elif len(arr_pdf) > 1: # there are more than 1 pdf in the directory

print("[-+-] more than 1 pdf found, exiting script!")

pdf_flag = False

# TODO add option to select from available pdfs

else:

print("[-+-] pdf cannot be found, exiting script!")

pdf_flag = False

if pdf_flag == True:

# check if csv exists at the default file path

# if csv does not exist create a blank file at the default path

try:

print("[-+-] looking for default csv...")

open(csv_path, "r")

print("[-+-] csv found: " + csv + "\n")

except IOError:

print("[-+-] did not find csv at default file path!")

print("[-+-] creating a blank csv file: " + csv + "... \n")

open(csv_path, "w")

print("[-+-] converting pdf to csv...")

# print("[-+-] pdf to csv conversion suppressed! \n")

try:

tabula.convert_into(pdf_path, csv_path, output_format="csv", pages="all")

print ("[-+-] pdf to csv conversion complete!\n")

except IOError:

print("[-+-] pdf to csv conversion failed!")

print("[-+-] converted csv file can be found here: " + csv_path + "\n")

print("[-+-] finished pdf_csv.py successfully!")

pdf_csv() # run the program

tabula-py

Date,Open,High,Low,Close / Last,Volume

01/04/2017,62.48,62.75,62.12,62.3,"21,325,140"

01/03/2017,62.79,62.84,62.125,62.58,"20,655,190"

12/30/2016,62.96,62.99,62.03,62.14,"25,575,720"

12/29/2016,62.86,63.2,62.73,62.9,"10,248,460"

12/28/2016,63.4,63.4,62.83,62.99,"14,348,340"

12/27/2016,63.21,64.07,63.21,63.28,"11,743,650"

12/23/2016,63.45,63.54,62.8,63.24,"12,399,540"

12/22/2016,63.84,64.1,63.405,63.55,"22,175,270"

12/21/2016,63.43,63.7,63.12,63.54,"17,084,370"

12/20/2016,63.69,63.8,63.025,63.54,"26,017,470"

12/19/2016,62.56,63.77,62.42,63.62,"34,318,500"

12/16/2016,62.95,62.95,62.115,62.3,"42,452,660"

Date,Open,High,Low,Close / Last,Volume

01/04/2017,117.55,119.66,117.29,118.69,"19,594,560"

01/03/2017,116.03,117.84,115.51,116.86,"20,635,600"

12/30/2016,116.595,116.83,114.7739,115.05,"18,668,290"

12/29/2016,117,117.531,116.06,116.35,"9,925,082"

12/28/2016,118.19,118.25,116.65,116.92,"11,985,740"

12/27/2016,116.96,118.68,116.864,118.01,"12,034,590"

12/23/2016,117,117.56,116.3,117.27,"10,885,030"

12/22/2016,118.86,118.99,116.93,117.4,"16,226,770"

12/21/2016,118.92,119.2,118.48,119.04,"10,747,610"

12/20/2016,119.5,119.77,118.8,119.09,"13,673,570"

12/19/2016,119.85,120.36,118.51,119.24,"15,871,360"

12/16/2016,120.9,121.5,119.27,119.87,"25,316,220"