PDF Table Extraction
for Developers & AI Agents

// 1. Register (fully automated — no human step)
const reg = await fetch('https://www.tableforge.ai/api/v1/auth/register', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ email: 'bot@example.com', password: 'securepass' }),
}).then(r => r.json())
const apiKey = reg.apiKey.key  // store this — shown once

// 2. Submit extraction job
const form = new FormData()
form.append('file', fs.createReadStream('report.pdf'), 'report.pdf')
form.append('mode', 'data_clean')      // table | data_clean | markdown | layout_match
// form.append('layout_scope', 'pages') // layout_match only: 'tables' (default) | 'pages'
// form.append('table_names', JSON.stringify(['Revenue Summary'])) // selective by name
// form.append('pages', JSON.stringify([1, 2, 3]))                 // selective by page

const { jobId } = await fetch('https://www.tableforge.ai/api/v1/jobs', {
  method: 'POST',
  headers: { 'Authorization': `Bearer ${apiKey}` },
  body: form,
}).then(r => r.json())

// 3. Poll until complete
let job
do {
  await new Promise(r => setTimeout(r, 30_000))
  job = await fetch(`https://www.tableforge.ai/api/v1/jobs/${jobId}`, {
    headers: { 'Authorization': `Bearer ${apiKey}` },
  }).then(r => r.json())
} while (job.status === 'queued' || job.status === 'processing')

// 4. Retrieve result — choose your format
// ?format=json (default) | excel | csv | markdown
const result = await fetch(
  `https://www.tableforge.ai/api/v1/jobs/${jobId}/result?format=json`,
  { headers: { 'Authorization': `Bearer ${apiKey}` } }
).then(r => r.json())

console.log(`Extracted ${result.tables.length} tables from ${result.pageCount} pages`)

// Download as Excel:
// const xlsx = await fetch(`…/result?format=excel`, { headers: … })
// fs.writeFileSync('output.xlsx', Buffer.from(await xlsx.arrayBuffer()))