pdf2img, pdf to image, python library

 way #1

--

# pip install pdf2image

from pdf2image import convert_from_path

pdffile = '2081033884.pdf'

pages = convert_from_path(pdffile, 500)

#Saving pages in jpeg format

for i, page in enumerate(pages):

page.save(f'pdf2image_{i}.jpg', 'JPEG')

--

way #2

--

#pip install pymupdf

import fitz

pdffile = '2081033884.pdf'

doc = fitz.open(pdffile)

#split pages

for i, page in enumerate(doc.pages()):

pix = page.get_pixmap()

img_filename = f"fitz_{i}.jpg"

pix.pil_save(img_filename, format="jpeg", dpi=(300,300)) #, ... more PIL parameters)

--

Thank you.

www.marearts.com

🙇🏻‍♂️

PDF to OpenCV as page by page using PyMuPDF library (python example code)

Just see the below example code 😊

pip install PyMuPDF
document : https://pymupdf.readthedocs.io/en/latest/

I think this is better library than pypdf2 🤔
..

import fitz

import numpy as np

import cv2

fname = 'information-10-00248-v2'
doc = fitz.open(fname+'.pdf')

#split pages

for i, page in enumerate(doc.pages()):

print(i)

zoom = 1

mat = fitz.Matrix(zoom, zoom)

pix = page.getPixmap(matrix = mat)

imgData = pix.getImageData("png")

 
#save image from byte

f = open('./save_by_byte_{}_{}.png'.format(fname, i), 'wb')

f.write(imgData)

f.close()

 
#save image from opencv

nparr = np.frombuffer(imgData, np.uint8)

img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)

print(img.shape)

cv2.imwrite('./save_by_opencv_{}_{}.png'.format(fname, i),img)

..