pdf to txt , pyton code 17th sep 24

 2 pyton codes.

1pyton

# Install google-cloud-vision and pdf2image

!pip install google-cloud-vision pdf2image PdfReader

# Install poppler-utils

!apt-get update

!apt-get install -y poppler-utils

2nd pyton

!pip show google-cloud-vision pdf2image

!apt-cache policy poppler-utils

# this is for doc to text ; ocr.

import io

import os

from google.cloud import vision

from google.cloud.vision_v1 import types

from pdf2image import convert_from_path

from google.oauth2 import service_account

# Paths to the files

credentials_path = '/content/credentials_doc.json'

pdf_file_path = '/content/Aditya.pdf'

output_text_file_path = '/content/Aditya_text.txt'

# Verify the file existence

if os.path.exists(credentials_path):

    print("Credentials file found.")

else:

    print("Credentials file not found. Please check the path.")

if os.path.exists(pdf_file_path):

    print("PDF file found.")

else:

    print("PDF file not found. Please check the path.")

# Authenticate using service account

credentials = service_account.Credentials.from_service_account_file(credentials_path)

client = vision.ImageAnnotatorClient(credentials=credentials)

# Convert PDF to images

images = convert_from_path(pdf_file_path, dpi=300)

# Function to perform OCR on an image

def perform_ocr(image):

    content = io.BytesIO()

    image.save(content, format='PNG')

    content = content.getvalue()

    image = types.Image(content=content)

    response = client.document_text_detection(image=image)

    return response.full_text_annotation.text

# Process each image and save the text

with open(output_text_file_path, 'w', encoding='utf-8') as output_file:

    for i, image in enumerate(images):

        text = perform_ocr(image)

        output_file.write(f"Page {i + 1}\n")

        output_file.write(text)

        output_file.write("\n\n")

print(f'OCR text written to file "{output_text_file_path}"')