glukicov/slideops/slides-to-pdf

find_chrome() {
  local base c
  for base in "$HOME/Library/Caches/ms-playwright" "$HOME/.cache/ms-playwright"; do
    [ -d "$base" ] || continue
    c=$(find "$base" -maxdepth 6 -type f \
          \( -name chrome -o -name Chromium -o -name "Google Chrome for Testing" \) \
          2>/dev/null | grep -v headless_shell | sort -V | tail -1)
    [ -n "$c" ] && { printf '%s\n' "$c"; return; }
  done
  for c in "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
           "$(command -v google-chrome || true)" "$(command -v chromium || true)"; do
    [ -x "$c" ] && { printf '%s\n' "$c"; return; }
  done
}
CHROME=$(find_chrome)
[ -x "$CHROME" ] || { npx --yes playwright install chromium; CHROME=$(find_chrome); }
"$CHROME" --version   # sanity-check; quote "$CHROME" everywhere (macOS path has spaces)
 
DECK="/absolute/path/to/deck.html"
STAGE=$(mktemp -d -t slidespdf)   # or a per-deck subdir of your session scratchpad
 
# Per-deck settings. The defaults match SlideOps decks; change all three for a foreign one.
SLIDE_MATCH='<section class="slide'   # the literal that starts one slide element
W=1280; H=720                         # the deck's canvas size in CSS pixels
CHROME_SANDBOX_ARGS=()                # see "Sandbox" below before adding --no-sandbox
 
N=$(grep -c "$SLIDE_MATCH" "$DECK")
[ "$N" -gt 0 ] || { echo "No slides matched $SLIDE_MATCH; check the selector"; exit 1; }
echo "$N slides at ${W}x${H}"

IMG_DIR="/absolute/path/to/the/deck's/image/folder"   # any path is fine for an image-free deck
CHROME_HIDE='.hud,.progress,.hint'                    # SlideOps chrome; change for a foreign deck
python3 - "$DECK" "$STAGE" "$IMG_DIR" "$CHROME_HIDE" <<'EOF'
import sys
from pathlib import Path
 
deck, stage, img_dir, hide = Path(sys.argv[1]), Path(sys.argv[2]), sys.argv[3], sys.argv[4]
content = deck.read_text()
content = content.replace('src="../img/', f'src="file://{img_dir}/')
content = content.replace('</head>',
    f'<style>{hide}{{display:none !important;}}</style></head>', 1)
(stage / "export.html").write_text(content)
EOF

for i in $(seq 1 $N); do
  "$CHROME" --headless=new --disable-gpu --hide-scrollbars "${CHROME_SANDBOX_ARGS[@]}" \
    --window-size=$W,$H --force-device-scale-factor=2 \
    --screenshot="$STAGE/slide-$(printf "%02d" $i).png" \
    "file://$STAGE/export.html#${i}"
done

python3 - "$STAGE" "$N" "$W" "$H" <<'EOF'
import sys
from pathlib import Path
 
stage, n, w, h = Path(sys.argv[1]), int(sys.argv[2]), int(sys.argv[3]), int(sys.argv[4])
pages = "\n".join(
    f'<div class="page"><img src="slide-{i:02d}.png"><div class="folio">'
    f'<span>{i} / {n}</span></div></div>' for i in range(1, n + 1))
(stage / "print.html").write_text(f'''<style>
  @page {{ size: {w}px {h}px; margin: 0; }}
  * {{ margin: 0; padding: 0; box-sizing: border-box; }}
  .page {{ width: {w}px; height: {h}px; overflow: hidden; page-break-after: always;
           position: relative; }}
  .page:last-child {{ page-break-after: auto; }}
  .page img {{ width: {w}px; height: {h}px; display: block; }}
  .folio {{ position: absolute; left: 0; right: 0; bottom: 18px; text-align: center;
            font: 13px/1 -apple-system, "Segoe UI", Roboto, sans-serif;
            font-variant-numeric: tabular-nums; }}
  .folio span {{ background: rgba(0, 0, 0, 0.38); color: #fff;
                 padding: 6px 13px; border-radius: 999px; }}
</style>
{pages}''')
EOF

"$CHROME" --headless=new --disable-gpu "${CHROME_SANDBOX_ARGS[@]}" \
  --print-to-pdf="$STAGE/output.pdf" --no-pdf-header-footer \
  "file://$STAGE/print.html"

python3 -m venv "$STAGE/venv"
"$STAGE/venv/bin/pip" install --quiet pypdfium2 Pillow
"$PDFPY" - "$STAGE" <<'EOF'
import sys
import pypdfium2 as pdfium
stage = sys.argv[1]
pdf = pdfium.PdfDocument(f"{stage}/output.pdf")
n = len(pdf)
print("page count:", n)                 # must equal the slide count
for i in range(n):
    pdf[i].render(scale=1.5).to_pil().save(f"{stage}/check-{i+1:02d}.png")
    footer = f"{i+1} / {n}"             # the folio is real text, so it extracts
    assert footer in pdf[i].get_textpage().get_text_range(), f"page {i+1} has no footer"
print("every page is numbered")
EOF