Improved Code.

images2pdf/imges2pdf.py

@@ -1,50 +1,27 @@
-
+import PyPDF2
-### img2pdf ####
+from os import path
-import os 
 import sys
-from fpdf import FPDF 
-from PIL import Image
-import glob
 
+def File_existance_checker(filePath):
+    if path.isfile(filePath):
+        return filePath
+    else:
+        print("[-] Provide a valid File")
+        sys.exit(1)
+pdf_stored_path=input("Enter the name of you pdf file (please use backslash when typing in directory path):")
 
+textFile_stored_path=path.join(path.dirname(pdf_stored_path),path.basename(pdf_stored_path).replace(".pdf",".txt"))
+pdf_stored_path=File_existance_checker(pdf_stored_path)
 
-images_path = raw_input("Enter the path of the folder containing images : ")
+print(textFile_stored_path)
-images =images_path+"/*.*"
 
-assert os.path.exists(images_path), "this diretory doesn't exist, "+str(images_path)
+with open(pdf_stored_path,'rb') as pdf_object:
-f = os.chdir(images_path)
+    pdf_read=PyPDF2.PdfFileReader(pdf_object)
-print("Hooray we found your directory!")
-
-image_list = []
-for filename in glob.glob(images): 
     
-    image_list.append(filename)
+    pdf_pages=pdf_read.numPages
-
+    
-pdf = FPDF( unit = 'mm')
+    for i in range(pdf_pages):
-
+        page_object=pdf_read.getPage(i)
-imnames = [i.split("\\") for i in image_list] 
+        with open(textFile_stored_path,'a+') as f:
-imnames = [i[-1] for i in imnames ]
+            f.write((page_object.extract_text()))
-imnums = [i.split('.') for i in imnames]
+    print(f"[+] Pdf Text has been extracted and written to {path.basename(textFile_stored_path)}")
-imnums = [i[0] for i in imnums]
-imnums = [int(i) for i in imnums]
-
-
-
-pos = 0 
-images_dict = dict(zip(image_list, imnums))
-sorted_images = sorted(images_dict , key = images_dict.get)
-
-for i in list(sorted_images):
-    pdf.add_page()
-    im = Image.open(i)
-    pdf.image(i,pos,pos,200,250)
-
-pdf_name = raw_input("Enter the pdf name : ")
-pdf_name = pdf_name+".pdf"
-pdf.output(pdf_name)
-
-
-
-
-
-