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. Draws each page of the PDF as a picture, reads the printed text on it, and returns the text of all pages. It can also build a searchable copy of the PDF. Progress is reported page by page.
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-scan.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/ocr-pdf \
-H 'Content-Type: application/json' \
-d '{"input":{"pdf":"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": {'pdf': upload("sample-scan.pdf")}, "wait": 30}
reply = call("POST", "/v1/tools/ocr-pdf", 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(`${BASE}/v1/tools/ocr-pdf`, {
method: "POST",
headers: {"Content-Type": "application/json"},
body: JSON.stringify({input: {"pdf":await upload(file, "sample-scan.pdf")}, wait: 30}),
})).json();
// Step 3: a job that is still running comes back as {job}. Wait for it.
while (!reply.result && ["queued", "running"].includes((reply.job || reply).status)) {
reply = await (await fetch(`${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-scan.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": "ocr-pdf",
"input": {
"pdf": "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": {
"pdf": "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/ocr-pdf. Over MCP: run_tool with slug: "ocr-pdf".
Machine-readable: input schema, Markdown. Connect an agent.
Inputs
| Name | Type | Required | What it does |
|---|---|---|---|
pdf |
file | yes | A PDF made of scanned or photographed pages. In the API: a file reference such as DROP_ID/f1. Accepts: pdf. |
language |
string | no | Language of the text: eng (English), deu (German), fra (French), spa (Spanish), ita (Italian), por (Portuguese), nld (Dutch), nor (Norwegian), swe (Swedish), dan (Danish), pol (Polish), rus (Russian). One of: eng, deu, fra, spa, ita, por, nld, nor, swe, dan, pol, rus. Default: "eng". |
output |
string | no | text gives a .txt file. searchable_pdf gives a PDF that looks like the scan and can be searched. both gives the two files. One of: text, searchable_pdf, both. Default: "text". |
pages |
string | no | Pages to read, such as 1-3, 7 or 5-. Leave empty for every page. At most 50 pages are read in one job. Default: "". |
dpi |
integer | no | Resolution each page is drawn at before reading, in dots per inch. Higher reads small print better and takes longer. Default: 200. From 100 to 300. |
Examples
Read a two-page scan
{
"pdf": "sample-scan.pdf"
}Press the example button above to run it on the sample file.
Make the first page searchable
{
"pdf": "sample-scan.pdf",
"output": "searchable_pdf",
"pages": "1",
"dpi": 150
}Press the example button above to run it on the sample file.
Questions
- What is a searchable PDF?
- It looks exactly like the scan, with the text that was read placed invisibly behind each page, so you can search, select and copy it in any PDF viewer.
- How many pages can it read?
- Up to 50 pages in one job. For a longer document, run it several times with "pages" set to 1-50, 51-100 and so on.
- My PDF already has text I can select. Should I use this?
- No. Use pdf-text or pdf-to-markdown instead: they take the text straight from the file, which is faster and has no reading mistakes. This tool is for scans and photos saved as PDF.
- Which resolution should I choose?
- 200 dots per inch suits normal print. Use 300 for small print such as footnotes. Use 150 to go faster when the print is large.
- Which languages can it read?
- English, German, French, Spanish, Italian, Portuguese, Dutch, Norwegian, Swedish, Danish, Polish, Russian. Handwriting cannot be read.
- Does the searchable PDF keep my original pages?
- Each page is saved again as a picture at the chosen resolution, so it looks the same on screen and in print, but text that was sharp at any zoom before becomes a picture.
Related tools
- PDF to textGet the text out of a PDF, from all pages or the ones you choose, as plain text in reading order and as a .txt file.
pdf-text - PDF to MarkdownTurn a text PDF into clean Markdown: headings from letter size, joined paragraphs, lists and simple tables.
pdf-to-markdown - Image to text (OCR)Read the printed text in a photo, scan or screenshot and get it back as plain text, in 12 languages.
ocr-image - PDF to imagesTurn PDF pages into PNG, JPG or WebP pictures at the sharpness you choose. Up to 50 pages in one run, as files or one zip.
pdf-to-images - 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 - 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