PDF Outline Extractor
A PDF outline extractor reads the bookmark tree already stored inside a PDF and outputs it as plain data — Markdown, JSON, CSV, plain text, or an HTML nav list — instead of producing another PDF. It's the fastest way to pull a document's structure into a script, a spreadsheet, a Notion page, or an LLM prompt without handing over every page of the source file. Nothing is uploaded: parsing happens in your browser, and if a PDF has no bookmarks, extraction simply returns nothing to extract.
1. Upload a PDF
Drag a PDF here, or click to browse
Parsed locally — never uploaded
2. Choose a format
Upload a PDF to see its structure here.
Worked example: an ebook's outline into a prompt
Say you have a 400-page ebook and want an LLM to answer questions about a specific chapter without reading the whole file. Upload it here, switch to the Markdown tab, and copy the result straight into your prompt — the model now has the chapter map and can tell you exactly which section to look at, in a few hundred tokens instead of hundreds of pages.
Frequently asked questions
Does this change or re-upload my PDF?
No. The file never leaves your browser — it's read locally to walk the PDF's existing bookmark tree, and nothing is produced except the structure as data. There is no PDF output from this page.
What if my PDF has no bookmarks?
You'll get an empty result — that means the file has no outline to extract. If you want bookmarks first, use the bookmark editor to add them, or the TOC generator if you're starting from a document with no structure at all.
Which format should I use?
Markdown pastes cleanly into Notion, README files, or an LLM prompt so it can reason over a document’s structure without ingesting every page. JSON and CSV suit scripts and spreadsheets. HTML gives you a ready nav list.
Is there a page or file-size limit?
Signed-out use is capped at 50 pages per file — create a free account for 200.