Skip to main content
POST
/
v1
/
extract
Parse a document by URL
curl --request POST \
  --url https://api.hanji.dev/v1/extract \
  --header 'Content-Type: application/json' \
  --header 'X-API-KEY: <api-key>' \
  --data '
{
  "url": "<string>",
  "extract_text": true,
  "extract_images": true,
  "ocr": "auto",
  "table_output_format": "markdown"
}
'
import requests

url = "https://api.hanji.dev/v1/extract"

payload = {
"url": "<string>",
"extract_text": True,
"extract_images": True,
"ocr": "auto",
"table_output_format": "markdown"
}
headers = {
"X-API-KEY": "<api-key>",
"Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
method: 'POST',
headers: {'X-API-KEY': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
url: '<string>',
extract_text: true,
extract_images: true,
ocr: 'auto',
table_output_format: 'markdown'
})
};

fetch('https://api.hanji.dev/v1/extract', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
CURLOPT_URL => "https://api.hanji.dev/v1/extract",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'url' => '<string>',
'extract_text' => true,
'extract_images' => true,
'ocr' => 'auto',
'table_output_format' => 'markdown'
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"X-API-KEY: <api-key>"
],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}
package main

import (
"fmt"
"strings"
"net/http"
"io"
)

func main() {

url := "https://api.hanji.dev/v1/extract"

payload := strings.NewReader("{\n \"url\": \"<string>\",\n \"extract_text\": true,\n \"extract_images\": true,\n \"ocr\": \"auto\",\n \"table_output_format\": \"markdown\"\n}")

req, _ := http.NewRequest("POST", url, payload)

req.Header.Add("X-API-KEY", "<api-key>")
req.Header.Add("Content-Type", "application/json")

res, _ := http.DefaultClient.Do(req)

defer res.Body.Close()
body, _ := io.ReadAll(res.Body)

fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://api.hanji.dev/v1/extract")
.header("X-API-KEY", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"<string>\",\n \"extract_text\": true,\n \"extract_images\": true,\n \"ocr\": \"auto\",\n \"table_output_format\": \"markdown\"\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.hanji.dev/v1/extract")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-API-KEY"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"url\": \"<string>\",\n \"extract_text\": true,\n \"extract_images\": true,\n \"ocr\": \"auto\",\n \"table_output_format\": \"markdown\"\n}"

response = http.request(request)
puts response.read_body
{
  "chunks": [
    {
      "page_no": 123,
      "page_content": "",
      "bbox": [
        123
      ],
      "chunk_type": "text",
      "confidence": 123,
      "image_url": "<string>",
      "image_b64": "<string>",
      "image_mime": "<string>",
      "image_width": 123,
      "image_height": 123,
      "cells": [
        {
          "row": 123,
          "col": 123,
          "text": "",
          "row_span": 1,
          "col_span": 1,
          "bbox": [
            123
          ],
          "confidence": 123,
          "page_no": 123
        }
      ],
      "n_rows": 123,
      "n_cols": 123,
      "merged_from_pages": [
        123
      ]
    }
  ]
}
{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}

Authorizations

X-API-KEY
string
header
required

Body

application/json

Input to a parse request.

Server-side limits (page count, file size) are not user-configurable. Unknown fields are accepted and ignored for backward compatibility. The ocr knob is deprecated and currently has no effect.

url
string | null
extract_text
boolean
default:true
extract_images
boolean
default:true
ocr
enum<string>
default:auto

Deprecated. Accepted for backward compatibility but currently has no effect.

Available options:
auto,
never,
force
table_output_format
enum<string>
default:markdown

How table chunks are structured. 'markdown' (default) keeps the existing markdown-derived cells; 'cell_grid' returns true per-cell bounding boxes on table chunks (cells become the primary representation; page_content remains a markdown render).

Available options:
markdown,
cell_grid

Response

Successful Response

chunks
Chunk · object[]
required