textractor.py

from tika import parser
import sys
import os
import re
from docx import Document

document = Document()

def filecheck(filepath):
    return os.path.isfile(filepath)

def regexFilter(filepath):
    print("[Textractor] Checking for email-addresses...")
    raw = parser.from_file(filepath)
    match = re.findall(r'[\w\.-]+@[\w\.-]+', raw['content'], re.DOTALL)
    if len(match) == 0:
        print("No email-addresses found.")
    else:
        document.add_heading('Email-addresses', level=1)
        for e in match:
            document.add_paragraph(e, style='List Bullet')
            print(e)
    print("[Textractor] Checking for phonenumbers...")
    match = re.findall(r'\(?([0-9]{3})\)?([ .-]?)([0-9]{3})\2([0-9]{4})', raw['content'], re.DOTALL)
    if len(match) == 0:
        print("No phonenumbers found.")
    else:
        document.add_heading('Phonenumbers', level=1)
        for p in match:
            document.add_paragraph(p, style='List Bullet')
            print(p)

if len(sys.argv) < 2:
    print("[Textractor] Please append the filename you wish to extract the e-mail addresses from.")

else:
    if filecheck(sys.argv[1]) == True:
        regexFilter(sys.argv[1])

if len(sys.argv) >= 3:
        document.save(sys.argv[2])
        print("[Textractor] Wordfile written to " + sys.argv[2])