I'm using * to take all the files that start with out
:
We have : ['out0.jpg', 'out2.jpg', 'out4.jpg', 'out5.jpg', 'out1.jpg', 'out6.jpg', 'out3.jpg']
but I would like them to be sorted in ascending order. At the moment I am doing:
for file_name in file_names:
print("We have : ",file_names)
The complete code is here:
# import the necessary packages
from PIL import Image
import pytesseract
import argparse
import cv2
import os
## split
from PyPDF2 import PdfFileWriter, PdfFileReader
# remove
import sys
#
from pdf2image import convert_from_path
# import all files with a name
import glob
# functions
def pdfspliterimager(filename):
inputpdf = PdfFileReader(open(filename, "rb"))
for i in range(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
with open("document-page%s.pdf" % i, "wb") as outputStream:
output.write(outputStream)
pages = convert_from_path("document-page%s.pdf" % i, 500)
for page in pages:
page.save('out%s.jpg'%i, 'JPEG')
os.remove("document-page%s.pdf" % i)
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
help="path to input image to be OCR'd")
ap.add_argument("-p", "--preprocess", type=str, default="thresh",
help="type of preprocessing to be done")
args = vars(ap.parse_args())
# we test if it is a pdf
image_path = args["image"]
# if it is a pdf we convert it to an image
if image_path.endswith('.pdf'):
pdfspliterimager(image_path)
# for all files with out in their name
file_names = glob.glob("out*")
for file_name in file_names:
print("We have : ",file_names)
# load the image and convert it to grayscale
image = cv2.imread(file_name)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# check to see if we should apply thresholding to preprocess the
# image
if args["preprocess"] == "thresh":
gray = cv2.threshold(gray, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# make a check to see if median blurring should be done to remove
# noise
elif args["preprocess"] == "blur":
gray = cv2.medianBlur(gray, 3)
# write the grayscale image to disk as a temporary file so we can
# apply OCR to it
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
# load the image as a PIL/Pillow image, apply OCR, and then delete
# the temporary file
text = pytesseract.image_to_string(Image.open(filename))
os.remove(filename)
#print(text)
with open('resume.txt', 'a+') as f:
print('***:', text, file=f)
Maybe there are some simpler ways to do it.