oliver-batey

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from textblob import TextBlob


def sentiment_polarity(string: str) -> float:
    polarity = TextBlob(string).sentiment[0]
    return polarity

oliver-batey

def serialise_file(document,format):
    
    if format =='txt':
        with open(document, 'r') as file:
            string = file.read().replace('\n', ' ')
        return string 
        
    elif format == 'docx'
        #docx parsing code here
        

oliver-batey

import os
from docx import Document

class DocParser:
    def parse(self,document):
        parser = get_format(document)
        return parser(document)

def get_format(document):
    format = os.path.splitext(document)[-1]

oliver-batey

import os 
import io
from docx import Document

from pdfminer3.layout import LAParams, LTTextBox
from pdfminer3.pdfpage import PDFPage
from pdfminer3.pdfinterp import PDFResourceManager
from pdfminer3.pdfinterp import PDFPageInterpreter
from pdfminer3.converter import PDFPageAggregator
from pdfminer3.converter import TextConverter

oliver-batey

import parse_file as dp

#define paths to test files
txt_path = 'test_txt.txt'
docx_path = 'test_docx.docx'
pdf_path = 'test_pdf.pdf'
html_path = 'test_html.html'
pptx_path = 'test_pptx.pptx'

file_paths = [txt_path,docx_path,pdf_path,html_path,pptx_path]