PDF to Markdown
Turn a text PDF into clean Markdown: headings from letter size, joined paragraphs, lists and simple tables. Reads the text layer of a PDF and rebuilds its structure: lines are joined back into paragraphs, words split at line ends are mended, larger letters become headings, bullets and numbers become lists, and short cells that line up become tables. Made for giving a PDF to a language model.
Input
Result
Choose a file and press Run.
Files you upload and the results are stored for one hour, then deleted. Anyone who has the link can open them, so don't upload anything private.
Use it from code or an agent
# 1. Upload the file. The reply ends with a line "ref <id>/f1": that is the file reference.
curl -T sample.pdf https://setget.net/drop/
# 2. Run the tool with that reference. "wait" holds the reply for up to 30 seconds while the job runs.
curl -s https://setget.net/v1/tools/pdf-to-markdown \
-H 'Content-Type: application/json' \
-d '{"input":{"file":"DROP_ID/f1"},"wait":30}'
# 3. The reply is {"tool", "ms", "result", "files": [{"name", "size", "url", "ref"}], "job"}.
# Download a result file from its "url", or pass its "ref" to another tool.
# Still running after the wait? The reply is 202 with "job": follow it with
# curl -s https://setget.net/v1/jobs/JOB_ID?wait=30
import json, urllib.parse, urllib.request
BASE = "https://setget.net"
def call(method, path, body=None, headers=None):
request = urllib.request.Request(BASE + path, body, headers or {}, method=method)
return json.load(urllib.request.urlopen(request))
def upload(path):
"""Step 1: upload a file and get its reference."""
name = path.replace("\\", "/").rsplit("/", 1)[-1]
with open(path, "rb") as handle:
reply = call("PUT", "/drop/" + urllib.parse.quote(name), handle.read(), {"Accept": "application/json"})
return reply["file"]["ref"]
# Step 2: run the tool with the reference.
body = {"input": {'file': upload("sample.pdf")}, "wait": 30}
reply = call("POST", "/v1/tools/pdf-to-markdown", json.dumps(body).encode(), {"Content-Type": "application/json"})
# Step 3: a job that is still running comes back as {"job": ...}. Wait for it.
while "result" not in reply and reply.get("job", reply).get("status") in ("queued", "running"):
reply = call("GET", "/v1/jobs/" + reply.get("job", reply)["id"] + "?wait=30")
if "error" in reply:
raise SystemExit(reply["error"]["message"])
print(reply["result"])
for file in reply["files"]: # result files: download from "url", or pass "ref" to another tool
print(file["name"], file["size"], file["url"], file["ref"])
const BASE = "https://setget.net";
// Step 1: upload a file and get its reference. file: a File or Blob
// (in Node: new Blob([fs.readFileSync(path)])).
async function upload(file, name) {
const response = await fetch(`${BASE}/drop/${encodeURIComponent(name)}`, {
method: "PUT", headers: {Accept: "application/json"}, body: file,
});
return (await response.json()).file.ref;
}
// Step 2: run the tool with the reference.
let reply = await (await fetch(`${BASE}/v1/tools/pdf-to-markdown`, {
method: "POST",
headers: {"Content-Type": "application/json"},
body: JSON.stringify({input: {"file":await upload(file, "sample.pdf")}, wait: 30}),
})).json();
// Step 3: a job that is still running comes back as {job}. Wait for it.
while (!reply.result && ["queued", "running"].includes((reply.job || reply).status)) {
reply = await (await fetch(`${BASE}/v1/jobs/${(reply.job || reply).id}?wait=30`)).json();
}
if (reply.error) throw new Error(reply.error.message);
console.log(reply.result);
for (const file of reply.files) console.log(file.name, file.size, file.url, file.ref);
1. Upload. Tool: drop
Arguments:
{
"action": "create",
"files": [
{
"name": "sample.pdf",
"size": "<bytes>"
}
]
}
PUT each file's bytes to its "upload.url" with the listed headers, and keep its "ref".
With a shell, one command does both: curl -T FILE https://setget.net/drop/
2. Run. Tool: run_tool
Arguments:
{
"slug": "pdf-to-markdown",
"input": {
"file": "DROP_ID/f1"
}
}
3. The answer holds "result" and "files" (each with "url" and "ref").
If it holds a "job" that is still running instead, follow it. Tool: job
Arguments:
{
"action": "wait",
"id": "JOB_ID"
}
{
"input": {
"file": "DROP_ID/f1"
},
"wait": 30
}
This is a file tool, so a call takes three steps: upload the file to get a reference, run the tool with that reference, then read the result and download its files. Uploads and results are public by link and expire after one hour.
Endpoint: POST /v1/tools/pdf-to-markdown. Over MCP: run_tool with slug: "pdf-to-markdown".
Machine-readable: input schema, Markdown. Connect an agent.
Inputs
| Name | Type | Required | What it does |
|---|---|---|---|
file |
file | yes | The PDF to convert. It needs real text in it, not only scanned pages. In the API: a file reference such as DROP_ID/f1. Accepts: pdf, binary, text. |
pages |
string | no | Pages to convert, such as 1-3, 7, 10-. Leave empty for all pages. |
page_breaks |
boolean | no | Mark where each page starts with a line such as <!-- page 2 --> and a rule between pages. Default: false. |
Examples
A three-page PDF as Markdown
{
"file": "sample.pdf"
}Press the example button above to run it on the sample file.
Two pages, with page marks
{
"file": "sample.pdf",
"pages": "1-2",
"page_breaks": true
}Press the example button above to run it on the sample file.
Questions
- How does it find headings?
- By letter size. The most common size is taken as body text; larger sizes become headings, the largest as #, the next as ## and so on. Bold and italic words are kept.
- Why did I get an error about no text?
- The PDF is a scan: its pages are pictures. Use the ocr-pdf tool, which reads text from pictures.
- Does it keep tables?
- Simple ones, where short cells line up in rows and columns. Tables with long or wrapped cells come out as lines of text. Check tables that matter against the original.
- What is left out?
- Pictures, and lines that repeat at the top or bottom of most pages such as running titles and page numbers. The result says how many of each.
- What are the limits?
- Up to 1,000 pages in one run. For a longer PDF, set "pages" to a range and run it again for the rest. Password-protected PDFs must be unlocked first.
- Where is the Markdown?
- In a file named after your upload, ending in .md. The result also holds the Markdown itself in "markdown" when it is up to 200,000 characters; "truncated" is true when only the start fits there.
- Does it fetch anything from the internet?
- No. Links and picture addresses found in the file are copied as text. Nothing they point to is opened or downloaded.
Conversions this tool does
Related tools
- Scanned PDF to text (OCR)Read the text in a scanned PDF and get it as a text file, or as a PDF you can search and copy from.
ocr-pdf - Anything to MarkdownTurn almost any document into Markdown: PDF, Word, PowerPoint, Excel, HTML, EPUB, e-mail, notebooks, CSV.
any-to-markdown - Word to MarkdownTurn a Word document (.docx) into Markdown with its headings, lists, tables, links, bold and footnotes.
docx-to-markdown - Split a PDFSplit a PDF into single pages, into parts of N pages, or at the page numbers you give. Get the parts as files or as one zip.
pdf-split - HTML to MarkdownTurn a saved web page into Markdown: the main content, without menus, scripts and styling.
html-to-markdown - Compress a PDFMake a PDF file smaller by packing its contents tighter and, if you allow it, re-saving its pictures at a lower resolution.
pdf-compress