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

🙇🏻‍♂️

get image rect list from pdf

extract all image rect list from pdf using pymupdf
look at the sample code

..

#pip install PyMuPDF

#document : https://pymupdf.readthedocs.io/en/latest/

#pip install opencv-python

#github : https://github.com/skvark/opencv-python

import fitz

img_bbox = []

doc1 =fitz.open('test.pdf')

page1 = doc1[0] #first page

d = page1.getText("dict")

blocks = d["blocks"]

imgblocks = [b for b in blocks if b["type"] == 1]

for v in imgblocks:

[x1, y1, x2, y2] = v['bbox']

#print(x1, y1, x2, y2)

img_bbox.append({'left':int(x1), 'top':int(y1), 'right':int(x2), 'bottom':int(y2)})

..

remove all image from pdf file, python source code

input

output

PyMuPDF is needed

pip install PyMuPDF

..

def remove_img_on_pdf(idoc, page):

#image list

img_list = idoc.getPageImageList(page)

con_list = idoc[page]._getContents()

# xref 274 is the only /Contents object of the page (could be

for i in con_list:

c = idoc._getXrefStream(i) # read the stream source

#print(c)

if c != None:

for v in img_list:

arr = bytes(v[7], 'utf-8')

r = c.find(arr) # try find the image display command

if r != -1:

cnew = c.replace(arr, b"")

idoc._updateStream(i, cnew)

c = idoc._getXrefStream(i)

return idoc

doc=fitz.open('example.PDF')

rdoc = remove_img_on_pdf(doc, 0) #first page

rdoc.save('no_img_example.PDF')

..

reference : https://github.com/pymupdf/PyMuPDF/issues/338

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)

..

PDF split page and save each page to pdf, python

#manual https://pymupdf.readthedocs.io/en/latest/

#pip3 install PyMuPDF

import fitz

doc = fitz.open('./test2.pdf') 

#page_number = doc.pageCount

#print(page_number)

#split pages

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

    print(i)

    doc2 = fitz.open()               

    doc2.insertPDF(doc, to_page = i) 

    doc2.save("{}.pdf".format(i))