You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

44 lines
1.6 KiB
Python

#Based in the code in https://iq.opengenus.org/pdf_to_image_in_python/
import pdf2image
from PIL import Image
import time
#DECLARE CONSTANTS
PDF_PATH = ("scans/out.pdf")
DPI = 72
FIRST_PAGE = None
LAST_PAGE = None
FORMAT = 'jpg'
THREAD_COUNT = 1
USERPWD = None
USE_CROPBOX = False
STRICT = False
def pdftopil():
#This method reads a pdf and converts it into a sequence of images
#PDF_PATH sets the path to the PDF file
#dpi parameter assists in adjusting the resolution of the image
#first_page parameter allows you to set a first page to be processed by pdftoppm
#last_page parameter allows you to set a last page to be processed by pdftoppm
#fmt parameter allows to set the format of pdftoppm conversion (PpmImageFile, TIFF)
#thread_count parameter allows you to set how many thread will be used for conversion.
#userpw parameter allows you to set a password to unlock the converted PDF
#use_cropbox parameter allows you to use the crop box instead of the media box when converting
#strict parameter allows you to catch pdftoppm syntax error with a custom type PDFSyntaxError
start_time = time.time()
pil_images = pdf2image.convert_from_path(PDF_PATH, dpi=DPI, first_page=FIRST_PAGE, last_page=LAST_PAGE, fmt=FORMAT, thread_count=THREAD_COUNT, userpw=USERPWD, use_cropbox=USE_CROPBOX, strict=STRICT)
print ("Time taken : " + str(time.time() - start_time))
return pil_images
def save_images(pil_images):
d = 0
for image in pil_images:
image.save(("split/input%d"%d) + ".jpg")
d += 1
if __name__ == "__main__":
pil_images = pdftopil()
save_images(pil_images)