Use this to extract PDF content and images from a Protected PDF file. #Python #PDF #Public

extract_pdf_to_md.py

# Required Libraries
# pip install pymupdf pdfplumber Pillow

import fitz  # PyMuPDF
import pdfplumber
import os

pdf_file = "2024-SOC2-Report-for-Forsta-Division-Products.pdf"
output_dir = "extracted_markdown"
images_dir = os.path.join(output_dir, "images")
os.makedirs(images_dir, exist_ok=True)

start_page = 35
end_page = 141

markdown_output = ""

with pdfplumber.open(pdf_file) as plumber_pdf:
    fitz_pdf = fitz.open(pdf_file)

    for page_num in range(start_page - 1, end_page):
        page_markdown = f"# Page {page_num + 1}\n\n"

        # Extract text using pdfplumber
        plumber_page = plumber_pdf.pages[page_num]
        text = plumber_page.extract_text()
        if text:
            markdown_output += f"{text}\n\n"

        # Extract tables using pdfplumber and format as Markdown tables
        tables = plumber_page.extract_tables()
        for table in tables:
            if table:
                header_row = table[0]
                markdown_output += "| " + " | ".join(cell.strip().replace("\n", " ") if cell else "" for cell in header_row) + " |\n"
                markdown_output += "|" + "|".join(["---"] * len(header_row)) + "|\n"
                for row in table[1:]:
                    markdown_output += "| " + " | ".join(cell.strip().replace("\n", " ") if cell else "" for cell in row) + " |\n"
                markdown_output += "\n"

        # Extract images using PyMuPDF (fitz)
        fitz_pdf = fitz.open(pdf_file)
        fitz_page = fitz_pdf.load_page(page_num)
        images = fitz_page.get_images(full=True)
        for img_index, img in enumerate(images):
            xref = img[0]
            base_image = fitz_pdf.extract_image(xref)
            image_bytes = base_image["image"]
            image_ext = base_image["ext"]
            image_filename = f"page_{page_num+1}_img_{xref}.{image_ext}"
            image_path = os.path.join(images_dir, image_filename)
            with open(image_path, 'wb') as img_file:
                img_file.write(image_bytes)
            # Embed image in Markdown output
            markdown_output += f"![Image from page {page_num+1}](images/{image_filename})\n\n"

# Save final Markdown file
output_markdown_path = os.path.join(output_dir, "Extracted_SOC2_Report.md")
with open(output_markdown_path, 'w', encoding="utf-8") as md_file:
    md_file.write(markdown_output)

print(f"Extraction complete. Markdown saved at '{output_markdown_path}'.")