ExtractContentsFromFile.py

import io 
import PyPDF2
import docx2txt 
import numpy as np
from psycopg2.extensions import register_adapter, AsIs
register_adapter(np.int64, AsIs)
import warnings
warnings.filterwarnings('ignore')
class ExtractContentFromFile:
    def ExtractDataFromFile(FileName,file):
        text =''
        try:
            #print(text)
            if FileName.endswith("pdf"):
                reserve_pdf_on_memory = io.BytesIO(file)
                load_pdf = PyPDF2.PdfReader(reserve_pdf_on_memory)
                for page in load_pdf.pages:
                    text += page.extract_text()
            
            elif FileName.endswith("doc") or FileName.endswith("docx"):
                text = docx2txt.process(file)
                text = text.read()
            
            else:
                text = file.decode('utf-8')
        except:
            print("Error reading file")    
        finally:
            # Close the resources to free up memory
            del reserve_pdf_on_memory
            del load_pdf
        return text