import os
from PIL import Image
from matplotlib import pyplot as plt
import cv2
from pdf2image import convert_from_path
import pyocr
import pyocr.builders
import sys
import pandas as pd
import time
import numpy as np
import glob
import shutil
#OCR-Tool selbst
def OCR_read(PIL_data):
    
    tools = pyocr.get_available_tools()
    if len(tools) == 0:
        print("No OCR tool found")
        sys.exit(1)

    tool = tools[0]

    txt = tool.image_to_string( #Geben Sie hier das OCR-Ziel, die Sprache und die Optionen an.
            PIL_data,
            lang='jpn',
            builder=pyocr.builders.TextBuilder(tesseract_layout=6)
            )

    txt1 = txt.replace(' ','').replace('\n','').replace('|','')
    return txt1
#Konvertieren Sie eine PDF-Datei in ein Bild
def pdftoimage(work_directory, path1):
    images = convert_from_path(path1)
    i = 0
    for image in images:
        
        
        print("Making work{}.png ...".format(i))
        image.save(work_directory +"/Output_folder/"+ "work{}.png ".format(i))

        i += 1
    imax =i
    return imax

Recommended Posts