Create searchable (multipage) PDF with Python

Question

I've found some guides online on how to make a PDF searchable if it was scanned. However, I'm currently struggling with figuring out how to do it for a multipage PDF.

My code takes multipaged PDFs, converts each page into a JPG, runs OCR on each page and then converts it into a PDF. However, only the last page is returned.

import pytesseract
from pdf2image import convert_from_path

pytesseract.pytesseract.tesseract_cmd = 'directory'
TESSDATA_PREFIX = 'directory'
tessdata_dir_config = '--tessdata-dir directory'

# Path of the pdf
PDF_file = r"pdf directory"
  
  
def pdf_text():
    
    # Store all the pages of the PDF in a variable
    pages = convert_from_path(PDF_file, 500)
  
    image_counter = 1

    for page in pages:

        # Declare file names
        filename = "page_"+str(image_counter)+".jpg"

        # Save the image of the page in system
        page.save(filename, 'JPEG')

        # Increment the counter to update filename
        image_counter = image_counter + 1

    # Variable to get count of total number of pages
    filelimit = image_counter-1

    outfile = "out_text.pdf"

    # Open the file in append mode so that all contents of all images are added to the same file
    
    f = open(outfile, "a")

    # Iterate from 1 to total number of pages
    for i in range(1, filelimit + 1):

        filename = "page_"+str(i)+".jpg"

        # Recognize the text as string in image using pytesseract
        result =  pytesseract.image_to_pdf_or_hocr(filename, lang="eng", config=tessdata_dir_config) 

            
        f = open(outfile, "w+b")
        f.write(bytearray(result))
        f.close()

pdf_text()

How can I run this for all pages and output one merged PDF?

Answer 1

I can't run it but I think all problem is because you use open(..., 'w+b') inside loop - and this remove previous content, and finally you write only last page.

You should use already opened file open(outfile, "a") and close it after loop.

# --- before loop ---

f = open(outfile, "ab")

# --- loop ---

for i in range(1, filelimit+1):

    filename = f"page_{i}.jpg"

    result =  pytesseract.image_to_pdf_or_hocr(filename, lang="eng", config=tessdata_dir_config) 

    f.write(bytearray(result))

# --- after loop ---
        
f.close()

---

BTW:

But there is other problem - image_to_pdf_or_hocr creates full PDF - with special headers and maybe footers - and appending two results can't create correct PDF. You would have to use special modules to merge pdfs. Like Merge PDF files

Something similar to

    # --- before loop ---
    
    from PyPDF2 import PdfFileMerger
    import io

    merger = PdfFileMerger()

    # --- loop ---
    
    for i in range(1, filelimit + 1):

        filename = "page_"+str(i)+".jpg"

        result =  pytesseract.image_to_pdf_or_hocr(filename, lang="eng", config=tessdata_dir_config)
        
        pdf_file_in_memory = io.BytesIO(result)        
        merger.append(pdf_file_in_memory)
        
    # --- after loop ---
    
    merger.write(outfile)
    merger.close()