vinovator

# pdfTextMiner.py
# Python 2.7.6
# For Python 3.x use pdfminer3k module
# This link has useful information on components of the program
# https://euske.github.io/pdfminer/programming.html
# http://denis.papathanasiou.org/posts/2010.08.04.post.html


''' Important classes to remember
PDFParser - fetches data from pdf file

vinovator

# python 2.7.6.
# portScanner.py

import socket
from datetime import datetime
import sys

# Here we are scanning your own terminal
# Replace this with gethostbyname("host") to scan a remote host 

vinovator

# Python 2.7.6
# timeZoneExplorer.py

from pytz import timezone, common_timezones # import all_timezones for more exhaustive list
from datetime import datetime
import os

# Log file will be created in the same folder as the python script
my_path = "."
log_path = os.path.join(my_path + "/" + "loc_log.txt")

vinovator

# jsonToCSV.py
# Python 2.7.6

'''
Place all the json payloads as separate text files in base folder
Program will extract each payload and generate single csv file
csv file will have key value pairs in separate columns
'''

import json

vinovator

# forbes2kMiner.py
# Python 3.4


"""
Extracts the Forbes Global 2000 list of companies and imports into a CSV file
Since Forbes is a JS rendered site, selenium is used to mimic user action
BeautifulSoup is used to scrape html content
Since selenium is used, Firefox is needed as webdiver
"""

vinovator

# persistListOfDicts.py
# Python 2.7.6


import json
import os
import pickle # To persist each dict

json_path = "./JSON"
	

vinovator

# Logger.py
# Python2.7.6
# For more details - https://docs.python.org/3/howto/logging.html#logging-basic-tutorial
# logging.error - just displays the error message
# logging.exception - displays the stack trace along with the error message

import logging # For logs
import sys # To read parameters from command line

# Define the format of the logging

vinovator

# persistListOfDicts.py
# Python 2.7.6


import json
import os

json_path = "./JSON"
	
# Write dicts into a pickle file each

vinovator

#Python 2.7.6
#DemergePDF.py
#Gets raw_inputs of 1 PDF file names from user and demerge into 2

import PyPDF2
import os

def getFileNameFromUser (file, path):
	pdf_file_name = raw_input("Enter {0} name: ".format(file))
	if pdf_file_name in os.listdir(path):

vinovator

#Python 2.7.6
#CombinePDF_Py2.py
#Gets raw_inputs of 2 PDF file names from user and combines them into 1

import PyPDF2
import os

def getFileNameFromUser (file, path):
	pdf_file_name = raw_input("Enter {0} name: ".format(file))
	if pdf_file_name in os.listdir(path):