1+ from skimage import io
2+ from PyPDF2 import PdfFileReader
3+ from pdf2image import convert_from_path
4+ import numpy as np
5+ import os
6+ from PIL import Image
7+ from fpdf import FPDF
8+ import shutil
9+ 10+ pdfFile = input ('PDF file location: ' )
11+ dirname = os .path .dirname (os .path .normpath (pdfFile ))
12+ outputFile = os .path .basename (pdfFile )
13+ outputFile = os .path .splitext (outputFile )[0 ]
14+ pdf_reader = PdfFileReader (pdfFile )
15+ pages = pdf_reader .getNumPages ()
16+ rang = int (pages ) + 1
17+ 18+ # Select the pixel from the extracted images of pdf pages
19+ def select_pixel (r ,g ,b ):
20+ if r > 120 and r < 254 and g > 120 and g < 254 and b > 120 and b < 254 :
21+ return True
22+ else :
23+ return False
24+ 25+ # Handling of images for removing the watermark
26+ def handle (imgs ):
27+ for i in range (imgs .shape [0 ]):
28+ for j in range (imgs .shape [1 ]):
29+ if select_pixel (imgs [i ][j ][0 ],imgs [i ][j ][1 ],imgs [i ][j ][2 ]):
30+ imgs [i ][j ][0 ] = imgs [i ][j ][1 ] = imgs [i ][j ][2 ] = 255
31+ return imgs
32+ 33+ images = convert_from_path (pdfFile )
34+ 35+ try :
36+ os .mkdir (dirname + '\img' )
37+ except FileExistsError :
38+ print ('Folder exist' )
39+ index = 0
40+ for img in images :
41+ index += 1
42+ img = np .array (img )
43+ print (img .shape )
44+ img = handle (img )
45+ io .imsave (dirname + '\img\img' + str (index ) + '.jpg' , img )
46+ print (index )
47+ 48+ # Merging images to a sigle PDF
49+ pdf = FPDF ()
50+ sdir = dirname + "img/"
51+ w ,h = 0 ,0
52+ 53+ for i in range (1 , rang ):
54+ fname = sdir + "img%.0d.jpg" % i
55+ if os .path .exists (fname ):
56+ if i == 1 :
57+ cover = Image .open (fname )
58+ w ,h = cover .size
59+ pdf = FPDF (unit = "pt" , format = [w ,h ])
60+ image = fname
61+ pdf .add_page ()
62+ pdf .image (image , 0 , 0 , w , h )
63+ else :
64+ print ("File not found:" , fname )
65+ # print("processed %d" % i)
66+ pdf .output (dirname + outputFile + '_rw.pdf' , "F" )
67+ print ("done" )
0 commit comments