Extract text from Scanned pdf using Python

To extract text from scanned pdf first we need to download tesseract and poppler.

Code to Extract Text From scanned PDF using Python

from PIL import Image
from pytesseract import image_to_string
import pytesseract
from pdf2image import convert_from_path
def convert_pdf_to_img(pdf_file):
return convert_from_path(pdf_file,poppler_path=".../Release-23.07.0-0/poppler-23.07.0/Library/bin")
def convert_image_to_text(file):
pytesseract.pytesseract.tesseract_cmd ="/Files/Tesseract-OCR/tesseract.exe"
text=image_to_string(file)
return(text)
def get_text_from_any_pdf(pdf_file):
images=convert_pdf_to_img(pdf_file)
final_text=""
for pg,img in enumerate(images):
final_text+=convert_image_to_text(img)
return final_text
filepath='../Page_14.pdf'
get_text_from_any_pdf(filepath)
Output:Text will be extracted from pdf.