Trích văn bản, siêu dữ liệu và ảnh thu nhỏ

curl -sS http://localhost:8080/v1/extract/text \
  -H "Authorization: Bearer O3O_DEMO_KEY" \
  -F "file=@bao-gia.docx"

import { readFile } from "node:fs/promises";

const BASE_URL = "http://localhost:8080";
const HEADERS = { Authorization: "Bearer O3O_DEMO_KEY" };

const form = new FormData();
form.append("file", new Blob([await readFile("bao-gia.docx")]), "bao-gia.docx");

const res = await fetch(`${BASE_URL}/v1/extract/text`, {
  method: "POST",
  headers: HEADERS,
  body: form,
  signal: AbortSignal.timeout(90_000),
});
if (!res.ok) throw new Error(`${res.status}: ${await res.text()}`);
console.log(await res.json());

import requests

BASE_URL = "http://localhost:8080"
HEADERS = {"Authorization": "Bearer O3O_DEMO_KEY"}

with open("bao-gia.docx", "rb") as f:
    r = requests.post(
        f"{BASE_URL}/v1/extract/text",
        headers=HEADERS,
        files={"file": ("bao-gia.docx", f)},
        timeout=90,
    )
if not r.ok:
    raise RuntimeError(f"{r.status_code}: {r.text}")
print(r.json())

<?php
$ch = curl_init("http://localhost:8080/v1/extract/text");
curl_setopt_array($ch, [
    CURLOPT_HTTPHEADER => ["Authorization: Bearer O3O_DEMO_KEY"],
    CURLOPT_POSTFIELDS => [
        'file' => new CURLFile('bao-gia.docx'),
    ],
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_TIMEOUT => 90,
]);
$body = curl_exec($ch);
$status = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
if ($body === false || $status >= 400) {
    throw new RuntimeException("HTTP $status: " . ($body === false ? curl_error($ch) : $body));
}
print_r(json_decode($body, true));

using System.Net.Http.Headers;

using var http = new HttpClient { Timeout = TimeSpan.FromSeconds(90) };
http.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", "O3O_DEMO_KEY");

using var form = new MultipartFormDataContent();
form.Add(new ByteArrayContent(await File.ReadAllBytesAsync("bao-gia.docx")), "file", "bao-gia.docx");

using var res = await http.PostAsync("http://localhost:8080/v1/extract/text", form);
if (!res.IsSuccessStatusCode)
    throw new HttpRequestException($"{(int)res.StatusCode}: {await res.Content.ReadAsStringAsync()}");
Console.WriteLine(await res.Content.ReadAsStringAsync());

curl -sS http://localhost:8080/v1/extract/meta \
  -H "Authorization: Bearer O3O_DEMO_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com/files/bang-luong.xlsx"}'

const BASE_URL = "http://localhost:8080";
const HEADERS = { Authorization: "Bearer O3O_DEMO_KEY" };

const payload = {"url": "https://example.com/files/bang-luong.xlsx"};

const res = await fetch(`${BASE_URL}/v1/extract/meta`, {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify(payload),
  signal: AbortSignal.timeout(90_000),
});
if (!res.ok) throw new Error(`${res.status}: ${await res.text()}`);
console.log(await res.json());

import requests

BASE_URL = "http://localhost:8080"
HEADERS = {"Authorization": "Bearer O3O_DEMO_KEY"}

payload = {"url": "https://example.com/files/bang-luong.xlsx"}
r = requests.post(f"{BASE_URL}/v1/extract/meta", headers=HEADERS, json=payload, timeout=90)
if not r.ok:
    raise RuntimeError(f"{r.status_code}: {r.text}")
print(r.json())

<?php
$payload = json_encode(['url' => 'https://example.com/files/bang-luong.xlsx'], JSON_UNESCAPED_UNICODE);

$ch = curl_init("http://localhost:8080/v1/extract/meta");
curl_setopt_array($ch, [
    CURLOPT_HTTPHEADER => ["Authorization: Bearer O3O_DEMO_KEY", "Content-Type: application/json"],
    CURLOPT_POSTFIELDS => $payload,
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_TIMEOUT => 90,
]);
$body = curl_exec($ch);
$status = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
if ($body === false || $status >= 400) {
    throw new RuntimeException("HTTP $status: " . ($body === false ? curl_error($ch) : $body));
}
print_r(json_decode($body, true));

using System.Net.Http.Headers;
using System.Text;

using var http = new HttpClient { Timeout = TimeSpan.FromSeconds(90) };
http.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", "O3O_DEMO_KEY");

var json = """
    {
      "url": "https://example.com/files/bang-luong.xlsx"
    }
    """;
using var res = await http.PostAsync("http://localhost:8080/v1/extract/meta",
    new StringContent(json, Encoding.UTF8, "application/json"));
if (!res.IsSuccessStatusCode)
    throw new HttpRequestException($"{(int)res.StatusCode}: {await res.Content.ReadAsStringAsync()}");
Console.WriteLine(await res.Content.ReadAsStringAsync());

curl -sS http://localhost:8080/v1/extract/thumbnail \
  -H "Authorization: Bearer O3O_DEMO_KEY" \
  -F "file=@gioi-thieu.pptx" \
  -F "page=1" \
  -F "width=320" \
  -F "format=png" \
  -D - \
  -o trang-bia.png -w "HTTP %{http_code}\n"

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

const BASE_URL = "http://localhost:8080";
const HEADERS = { Authorization: "Bearer O3O_DEMO_KEY" };

const form = new FormData();
form.append("file", new Blob([await readFile("gioi-thieu.pptx")]), "gioi-thieu.pptx");
form.append("page", "1");
form.append("width", "320");
form.append("format", "png");

const res = await fetch(`${BASE_URL}/v1/extract/thumbnail`, {
  method: "POST",
  headers: HEADERS,
  body: form,
  signal: AbortSignal.timeout(90_000),
});
if (!res.ok) throw new Error(`${res.status}: ${await res.text()}`);
await writeFile("trang-bia.png", Buffer.from(await res.arrayBuffer()));
console.log("X-O3O-Page-Count:", res.headers.get("X-O3O-Page-Count"));

import requests

BASE_URL = "http://localhost:8080"
HEADERS = {"Authorization": "Bearer O3O_DEMO_KEY"}

with open("gioi-thieu.pptx", "rb") as f:
    r = requests.post(
        f"{BASE_URL}/v1/extract/thumbnail",
        headers=HEADERS,
        files={"file": ("gioi-thieu.pptx", f)},
        data={
            "page": "1",
            "width": "320",
            "format": "png",
        },
        timeout=90,
    )
if not r.ok:
    raise RuntimeError(f"{r.status_code}: {r.text}")
with open("trang-bia.png", "wb") as fh:
    fh.write(r.content)
print("X-O3O-Page-Count:", r.headers.get("X-O3O-Page-Count"))

<?php
$headers = [];
$ch = curl_init("http://localhost:8080/v1/extract/thumbnail");
curl_setopt_array($ch, [
    CURLOPT_HTTPHEADER => ["Authorization: Bearer O3O_DEMO_KEY"],
    CURLOPT_POSTFIELDS => [
        'file' => new CURLFile('gioi-thieu.pptx'),
        'page' => '1',
        'width' => '320',
        'format' => 'png',
    ],
    CURLOPT_HEADERFUNCTION => function ($ch, $line) use (&$headers) {
        $parts = explode(":", $line, 2);
        if (count($parts) === 2) {
            $headers[strtolower(trim($parts[0]))] = trim($parts[1]);
        }
        return strlen($line);
    },
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_TIMEOUT => 90,
]);
$body = curl_exec($ch);
$status = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
if ($body === false || $status >= 400) {
    throw new RuntimeException("HTTP $status: " . ($body === false ? curl_error($ch) : $body));
}
file_put_contents("trang-bia.png", $body);
echo "X-O3O-Page-Count: " . ($headers["x-o3o-page-count"] ?? "") . "\n";

using System.Net.Http.Headers;

using var http = new HttpClient { Timeout = TimeSpan.FromSeconds(90) };
http.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", "O3O_DEMO_KEY");

using var form = new MultipartFormDataContent();
form.Add(new ByteArrayContent(await File.ReadAllBytesAsync("gioi-thieu.pptx")), "file", "gioi-thieu.pptx");
form.Add(new StringContent("1"), "page");
form.Add(new StringContent("320"), "width");
form.Add(new StringContent("png"), "format");

using var res = await http.PostAsync("http://localhost:8080/v1/extract/thumbnail", form);
if (!res.IsSuccessStatusCode)
    throw new HttpRequestException($"{(int)res.StatusCode}: {await res.Content.ReadAsStringAsync()}");
await File.WriteAllBytesAsync("trang-bia.png", await res.Content.ReadAsByteArrayAsync());
Console.WriteLine("X-O3O-Page-Count: " + string.Join(",", res.Headers.GetValues("X-O3O-Page-Count")));