OCR a scanned PDF

FILE0=$(curl -s -X POST https://api.pdfloft.com/v1/files \
  -H "Authorization: Bearer $PDFLOFT_API_KEY" \
  -H "Content-Type: application/pdf" \
  --data-binary @scan.pdf | jq -r .id)

JOB=$(curl -s -X POST https://api.pdfloft.com/v1/tools/ocr/runs \
  -H "Authorization: Bearer $PDFLOFT_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{"files":["'"$FILE0"'"],"options":{"languages":["eng"]}}' | jq -r .id)

until [ "$(curl -s https://api.pdfloft.com/v1/jobs/$JOB -H "Authorization: Bearer $PDFLOFT_API_KEY" | jq -r .status)" = "succeeded" ]; do sleep 1; done

URL=$(curl -s https://api.pdfloft.com/v1/jobs/$JOB/results/0 -H "Authorization: Bearer $PDFLOFT_API_KEY" | jq -r .url)
curl -s -o searchable.pdf "$URL"

import { readFile, writeFile } from 'node:fs/promises';

const apiKey = '<your API key>'; // read it from your secret store, never from source
const headers = { Authorization: `Bearer ${apiKey}` };

async function upload(path, contentType) {
  const response = await fetch('https://api.pdfloft.com/v1/files', {
    method: 'POST',
    headers: { ...headers, 'Content-Type': contentType },
    body: await readFile(path),
  });
  return response.json();
}

const file0 = await upload('scan.pdf', 'application/pdf');

let job = await fetch('https://api.pdfloft.com/v1/tools/ocr/runs', {
  method: 'POST',
  headers: { ...headers, 'Content-Type': 'application/json', 'Idempotency-Key': crypto.randomUUID() },
  body: JSON.stringify({ files: [file0.id], options: {"languages":["eng"]} }),
}).then((r) => r.json());

while (job.status === 'queued' || job.status === 'running') {
  await new Promise((resolve) => setTimeout(resolve, 1000));
  job = await fetch(`https://api.pdfloft.com/v1/jobs/${job.id}`, { headers }).then((r) => r.json());
}
if (job.status !== 'succeeded') throw new Error(`The run ended as ${job.status}: ${job.error}`);

const link = await fetch(`https://api.pdfloft.com/v1/jobs/${job.id}/results/0`, { headers }).then((r) => r.json());
await writeFile('searchable.pdf', Buffer.from(await fetch(link.url).then((r) => r.arrayBuffer())));

import os
import time
import uuid

import requests

headers = {"Authorization": f"Bearer {os.environ['PDFLOFT_API_KEY']}"}


def upload(path, content_type):
    with open(path, "rb") as handle:
        return requests.post("https://api.pdfloft.com/v1/files", headers={**headers, "Content-Type": content_type}, data=handle).json()


file0 = upload("scan.pdf", "application/pdf")

job = requests.post(
    "https://api.pdfloft.com/v1/tools/ocr/runs",
    headers={**headers, "Idempotency-Key": str(uuid.uuid4())},
    json={"files": [file0["id"]], "options": {"languages":["eng"]}},
).json()

while job["status"] in ("queued", "running"):
    time.sleep(1)
    job = requests.get(f"https://api.pdfloft.com/v1/jobs/{job['id']}", headers=headers).json()
if job["status"] != "succeeded":
    raise RuntimeError(f"The run ended as {job['status']}: {job['error']}")

link = requests.get(f"https://api.pdfloft.com/v1/jobs/{job['id']}/results/0", headers=headers).json()
open("searchable.pdf", "wb").write(requests.get(link["url"]).content)