PDF to PowerPoint: Convert PDF Slides to Editable .pptx (Free)

# Convert PDF to PPTX (headless / no GUI)
libreoffice --headless --convert-to pptx input.pdf
 
# Convert to PPTX with output directory
libreoffice --headless --convert-to pptx --outdir ./output input.pdf
 
# Batch convert all PDFs in folder
libreoffice --headless --convert-to pptx *.pdf

from pdf2image import convert_from_path
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.enum.text import PP_ALIGN
from PIL import Image
import io
 
def pdf_to_pptx_image(pdf_path: str, pptx_path: str, dpi: int = 150):
    """
    Image-based conversion: each PDF page → full-slide image.
    High fidelity, text is not editable.
    """
    pages = convert_from_path(pdf_path, dpi=dpi)
 
    # Detect aspect ratio from first page
    first_w, first_h = pages[0].size
    aspect = first_w / first_h
 
    prs = Presentation()
    
    # Set slide dimensions to match PDF page aspect ratio
    slide_width = Inches(10)
    slide_height = Inches(10 / aspect)
    prs.slide_width = slide_width
    prs.slide_height = slide_height
 
    blank_layout = prs.slide_layouts[6]   # Blank layout
 
    for i, page_img in enumerate(pages):
        slide = prs.slides.add_slide(blank_layout)
 
        # Save page image to a bytes buffer
        img_buffer = io.BytesIO()
        page_img.save(img_buffer, format="JPEG", quality=90)
        img_buffer.seek(0)
 
        # Add image to fill entire slide
        slide.shapes.add_picture(
            img_buffer,
            left=0, top=0,
            width=slide_width, height=slide_height
        )
 
        print(f"Added slide {i+1}/{len(pages)}")
 
    prs.save(pptx_path)
    print(f"Saved: {pptx_path}")
 
 
pdf_to_pptx_image("presentation.pdf", "presentation.pptx")

import pdfplumber
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.dml.color import RGBColor
 
def pdf_to_pptx_text(pdf_path: str, pptx_path: str):
    """
    Text-extraction approach: text becomes editable text boxes.
    Works best on simple, text-heavy PDFs.
    """
    prs = Presentation()
    prs.slide_width = Inches(10)
    prs.slide_height = Inches(7.5)
 
    blank_layout = prs.slide_layouts[6]
 
    with pdfplumber.open(pdf_path) as pdf:
        for page_num, page in enumerate(pdf.pages, start=1):
            slide = prs.slides.add_slide(blank_layout)
 
            # Extract words with position data
            words = page.extract_words(x_tolerance=3, y_tolerance=3)
            if not words:
                continue
 
            # Group words into lines by y-position
            lines = {}
            for word in words:
                y_key = round(word["top"] / 5) * 5   # Snap to 5pt grid
                lines.setdefault(y_key, []).append(word)
 
            page_w = page.width
            page_h = page.height
 
            for y_pos, line_words in sorted(lines.items()):
                line_words.sort(key=lambda w: w["x0"])
                line_text = " ".join(w["text"] for w in line_words)
                if not line_text.strip():
                    continue
 
                # Map PDF coordinates to slide coordinates
                x0 = line_words[0]["x0"]
                x_slide = (x0 / page_w) * Inches(10)
                y_slide = (y_pos / page_h) * Inches(7.5)
                w_slide = Inches(8)
                h_slide = Pt(20)
 
                txBox = slide.shapes.add_textbox(x_slide, y_slide, w_slide, h_slide)
                tf = txBox.text_frame
                p = tf.paragraphs[0]
                run = p.add_run()
                run.text = line_text
                run.font.size = Pt(11)
                run.font.color.rgb = RGBColor(0x22, 0x22, 0x22)
 
    prs.save(pptx_path)
    print(f"Saved text-based PPTX: {pptx_path}")

from pdf2image import convert_from_path
import pdfplumber
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.dml.color import RGBColor
import io
 
def pdf_to_pptx_hybrid(pdf_path: str, pptx_path: str, dpi: int = 150):
    page_images = convert_from_path(pdf_path, dpi=dpi)
    prs = Presentation()
    prs.slide_width = Inches(10)
    prs.slide_height = Inches(7.5)
 
    with pdfplumber.open(pdf_path) as pdf:
        for i, (page_img, pdf_page) in enumerate(zip(page_images, pdf.pages)):
            slide = prs.slides.add_slide(prs.slide_layouts[6])
 
            # Add full-page image as background
            img_buf = io.BytesIO()
            page_img.save(img_buf, "JPEG", quality=92)
            img_buf.seek(0)
            slide.shapes.add_picture(img_buf, 0, 0, Inches(10), Inches(7.5))
 
            # Add invisible text boxes for searchability
            words = pdf_page.extract_words()
            for word in words:
                x_rel = word["x0"] / pdf_page.width
                y_rel = word["top"] / pdf_page.height
                txBox = slide.shapes.add_textbox(
                    x_rel * Inches(10),
                    y_rel * Inches(7.5),
                    Inches(2), Pt(14)
                )
                run = txBox.text_frame.paragraphs[0].add_run()
                run.text = word["text"]
                run.font.size = Pt(1)        # Nearly invisible
                run.font.color.rgb = RGBColor(0xFF, 0xFF, 0xFF)   # White
 
    prs.save(pptx_path)