PDF Manipulation using Python — fitz Library

pip install PyMuPDF

1. Extract Text from a PDF

import fitz

def extract_text(pdf_path):
    doc = fitz.open(pdf_path)
    text = ""
    for page in doc:
        text += page.get_text()
    return text

pdf_path = "clcoding.pdf"
text = extract_text(pdf_path)
print(text)

Hello World!

2. Extract Images from a PDF

import fitz
import os

def extract_images(pdf_path, output_dir):
    doc = fitz.open(pdf_path)
    for page_num in range(len(doc)):
        page = doc.load_page(page_num)
        for img in page.get_images(full=True):
            xref = img[0]
            base_image = doc.extract_image(xref)
            image_bytes = base_image["image"]
            image_ext = base_image["ext"]
            image_filename = os.path.join(output_dir, 
                                          f"image_{page_num+1}_{xref}.{image_ext}")
            with open(image_filename, "wb") as image_file:
                image_file.write(image_bytes)

pdf_path = "clcoding.pdf"
output_dir = "images"
os.makedirs(output_dir, exist_ok=True)
extract_images(pdf_path, output_dir)