PDF to JSON converter
Paste the URL of a PDF and get one JSON object back: the title, the full text, the published date, and a status. It runs on the SpecStream Extract API.
Runs after sign-up, on $10 of credit. No card.
What the JSON holds
One PDF address in, one JSON object out.
status- ok when the PDF was read. Any other status comes with one sentence that says why, and is not charged.
title- The title of the document.
text- The text of the whole document, in Markdown or in plain text.
published- The date the document was published, when the file gives one.
url- The address the PDF was read from.
PDF to JSON questions
Something we didn't answer? Talk to a human
What does it cost?
Each PDF is one Extract API page at $0.80 per 1,000, whatever its length. A file that gives no text is not charged. Sign-up comes with $10 of credit and needs no card.
Can I upload a PDF from my computer?
Not yet. The Extract API reads a PDF at a public http or https address, so the file must be online first.
Does it fill a JSON schema of my own?
No. The JSON has the same fields for every document: status, title, text, published, and url. The text arrives whole, and your code or your model takes the values you need from it.
Why do I sign up first?
Each PDF is a real Extract API call and comes out of a balance. The sign-up credit pays for the first ones, and the address you pasted is in the box when you are in.
Which other files does it read?
Word, Excel, and EPUB files, images, and web pages, in the same call. One call takes up to 20 addresses.
Can I convert PDFs from code?
Yes. The tool runs on the Extract API: one POST request with your key returns the same JSON. Read the docs.