PDF & HTML Tables

Tables from a public PDF or HTML page as structured JSON rows.

Extract tables as structured JSON (rows, header, records keyed by column) from a public PDF (multi-column / ruled tables, up to 30 pages, 10 MB) or an HTML page (colspan/rowspan expanded). robots.txt respected; nothing stored. No OCR.

What agents use it for

Pull figures out of reports and datasheets
Turn PDF tables into data an agent can compute on
Parse HTML tables with merged cells

Parameters

Parameter	Type	Required	Description
`url`	string	yes	Public URL of a PDF or HTML page
`pages`	string	no	PDF pages, e.g. '1-3,7' (default: first 30)

Call it

MCP · tools/calljson

{
  "name": "extract_tables",
  "arguments": {
    "url": "https://example.org/report.pdf",
    "pages": "1-2"
  }
}

HTTPSreturns 402, then pay with an x402 client

curl -i -X POST "https://api.ishob.com/v1/pdf-tables" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.org/report.pdf","pages":"1-2"}'

Paid with x402: the first call returns HTTP 402 with the price; an x402 client (for example @x402/fetch or @x402/mcp) signs a USDC payment and retries. Calls that fail are not charged. Connect the MCP server: setup for Claude, Cursor and other clients.

PDF & HTML Tables

What agents use it for

Parameters

Call it

More web data & browser tools