PowerPoint to PDF: Convert .pptx Presentations to PDF (Free)

$ppt = New-Object -ComObject PowerPoint.Application
$ppt.Visible = [Microsoft.Office.Core.MsoTriState]::msoTrue
$presentation = $ppt.Presentations.Open("C:\path\to\slides.pptx")
$presentation.ExportAsFixedFormat(
    "C:\path\to\slides.pdf",
    2,          # ppFixedFormatTypePDF
    2,          # ppFixedFormatIntentPrint
    $false,     # HandoutOrder
    1,          # ppPrintHandoutVerticalFirst
    2,          # ppPrintOutputSlides
    $false,     # PrintHiddenSlides
    $null,      # PrintRange (null = all slides)
    1,          # RangeType: ppPrintAll
    "",         # SlideShowName
    $true,      # IncludeDocProperties
    $true,      # KeepIRM
    1,          # DocStructureTags: ppFixedFormatDocStructureTagsType1
    $true,      # BitmapMissingFonts
    $false,     # UseISO19005_1
    $null       # ExternalExporter
)
$presentation.Close()
$ppt.Quit()

# Convert single .pptx file to PDF
libreoffice --headless --convert-to pdf presentation.pptx
 
# Convert with output directory
libreoffice --headless --convert-to pdf --outdir ./pdfs presentation.pptx
 
# Batch: all PowerPoint files
libreoffice --headless --convert-to pdf *.pptx *.ppt
 
# Install on Ubuntu/Debian
sudo apt-get install libreoffice-impress

import subprocess
from pathlib import Path
 
def pptx_to_pdf(pptx_path: str, output_dir: str = None) -> str:
    input_path = Path(pptx_path).resolve()
    out_dir = Path(output_dir) if output_dir else input_path.parent
    out_dir.mkdir(parents=True, exist_ok=True)
 
    result = subprocess.run(
        [
            "libreoffice",
            "--headless",
            "--convert-to", "pdf",
            "--outdir", str(out_dir),
            str(input_path),
        ],
        capture_output=True,
        text=True,
        timeout=120,
    )
 
    if result.returncode != 0:
        raise RuntimeError(f"Conversion failed: {result.stderr}")
 
    pdf_path = out_dir / (input_path.stem + ".pdf")
    return str(pdf_path)
 
 
def batch_pptx_to_pdf(input_dir: str, output_dir: str):
    files = list(Path(input_dir).glob("*.pptx")) + list(Path(input_dir).glob("*.ppt"))
    print(f"Converting {len(files)} presentations...")
 
    for i, path in enumerate(files, start=1):
        try:
            pdf = pptx_to_pdf(str(path), output_dir)
            print(f"  [{i}/{len(files)}] ✓ {Path(pdf).name}")
        except Exception as e:
            print(f"  [{i}/{len(files)}] ✗ {path.name}: {e}")
 
batch_pptx_to_pdf("./presentations", "./pdfs")

from pptx import Presentation
from pptx.util import Inches
from PIL import Image
import io
import subprocess
from pathlib import Path
 
def pptx_to_pdf_via_images(pptx_path: str, pdf_path: str, dpi: int = 150):
    """
    Fallback: convert each slide to an image, then combine into PDF.
    Requires LibreOffice for slide-to-image rendering.
    """
    # Step 1: Convert PPTX to PNG images (one per slide) via LibreOffice
    temp_dir = Path("./temp_slides")
    temp_dir.mkdir(exist_ok=True)
 
    subprocess.run(
        ["libreoffice", "--headless", "--convert-to", "png", "--outdir", str(temp_dir), pptx_path],
        check=True
    )
 
    # Step 2: Collect and combine images into PDF with Pillow
    png_files = sorted(temp_dir.glob("*.png"))
    if not png_files:
        raise RuntimeError("No slide images generated")
 
    images = [Image.open(f).convert("RGB") for f in png_files]
    first = images[0]
    rest = images[1:]
 
    first.save(pdf_path, "PDF", resolution=dpi, save_all=True, append_images=rest)
    print(f"Saved: {pdf_path} ({len(images)} slides)")
 
    # Cleanup
    for f in png_files:
        f.unlink()
    temp_dir.rmdir()

# Convert PPTX to PDF via Beamer
pandoc presentation.pptx -t beamer -o presentation.pdf
 
# With a custom Beamer theme
pandoc presentation.pptx -t beamer \
  -V theme:metropolis \
  -o presentation.pdf
 
# Extract to HTML for inspection
pandoc presentation.pptx -o presentation.html

# LibreOffice can export Notes view via the filter string
libreoffice --headless \
  --convert-to "pdf:impress_pdf_Export:ExportNotesPages=1" \
  presentation.pptx

from pptx import Presentation
 
def extract_notes(pptx_path: str) -> list[dict]:
    prs = Presentation(pptx_path)
    slides_notes = []
 
    for i, slide in enumerate(prs.slides, start=1):
        notes_text = ""
        if slide.has_notes_slide:
            notes_frame = slide.notes_slide.notes_text_frame
            notes_text = notes_frame.text
 
        slides_notes.append({"slide": i, "notes": notes_text})
 
    return slides_notes