Quickstart - Web Scraping API - HasData Documentation

The Web Scraping API lets you scrape any public web page without handling proxies, headless browsers, or captchas. You send a URL, and we return the raw page content and optionally parsed data.

Get Your API Key

Sign in at hasdata.com, go to your account settings, and copy your API key. All requests must include your key in the x-api-key header.

Make Your First Request

curl --request POST \
  --url 'https://api.hasdata.com/scrape/web' \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <your-api-key>' \
  --data '{"url":"https://example.com","outputFormat":["html","text","markdown"],"screenshot":true}'

hasdata web-scraping \
  --url 'https://example.com' \
  --output-format 'html,text,markdown' \
  --screenshot

const axios = require('axios').default;

const options = {
  method: 'POST',
  url: 'https://api.hasdata.com/scrape/web',
  headers: {'Content-Type': 'application/json', 'x-api-key': '<your-api-key>'},
  data: {
    url: 'https://example.com',
    outputFormat: ['html', 'text', 'markdown'],
    screenshot: true
  }
};

try {
  const { data } = await axios.request(options);
  console.log(data);
} catch (error) {
  console.error(error);
}

import requests

url = "https://api.hasdata.com/scrape/web"

payload = {
    "url": "https://example.com",
    "outputFormat": ["html", "text", "markdown"],
    "screenshot": True
}
headers = {
    "Content-Type": "application/json",
    "x-api-key": "<your-api-key>"
}

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

print(response.json())

<?php

$payload = [
    "url" => "https://example.com",
    "outputFormat" => ["html", "text", "markdown"],
    "screenshot" => true,
];

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.hasdata.com/scrape/web",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode($payload),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <your-api-key>",
  ],
]);

$response = curl_exec($curl);
curl_close($curl);

echo $response;

OkHttpClient client = new OkHttpClient();

MediaType mediaType = MediaType.parse("application/json");
String json = """
  {
    "url": "https://example.com",
    "outputFormat": [
      "html",
      "text",
      "markdown"
    ],
    "screenshot": true
  }
""";
RequestBody requestBody = RequestBody.create(json, mediaType);

Request request = new Request.Builder()
  .url("https://api.hasdata.com/scrape/web")
  .post(requestBody)
  .addHeader("Content-Type", "application/json")
  .addHeader("x-api-key", "<your-api-key>")
  .build();

Response response = client.newCall(request).execute();

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

var client = new HttpClient();

var json = """
{
  "url": "https://example.com",
  "outputFormat": [
    "html",
    "text",
    "markdown"
  ],
  "screenshot": true
}
""";
var content = new StringContent(json, Encoding.UTF8, "application/json");

var request = new HttpRequestMessage(new HttpMethod("POST"), "https://api.hasdata.com/scrape/web")
{
    Content = content,
};
request.Headers.Add("x-api-key", "<your-api-key>");

using var response = await client.SendAsync(request);
response.EnsureSuccessStatusCode();
var body = await response.Content.ReadAsStringAsync();
Console.WriteLine(body);

require 'net/http'
require 'uri'
require 'json'

uri = URI("https://api.hasdata.com/scrape/web")
payload = {
  "url" => "https://example.com",
  "outputFormat" => ["html", "text", "markdown"],
  "screenshot" => true,
}

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

request = Net::HTTP::Post.new(uri)
request["Content-Type"] = 'application/json'
request["x-api-key"] = '<your-api-key>'
request.body = payload.to_json

response = http.request(request)
puts response.read_body

use reqwest::blocking::Client;
use serde_json::json;

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = Client::new();
    let payload = json!({
        "url": "https://example.com",
        "outputFormat": [
            "html",
            "text",
            "markdown"
        ],
        "screenshot": true
    });
    let res = client
        .post("https://api.hasdata.com/scrape/web")
        .header("Content-Type", "application/json")
        .header("x-api-key", "<your-api-key>")
        .json(&payload)
        .send()?
        .text()?;
    println!("{}", res);
    Ok(())
}

package main

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

func main() {
	payload := []byte(`{
  "url": "https://example.com",
  "outputFormat": [
    "html",
    "text",
    "markdown"
  ],
  "screenshot": true
}`)

	req, _ := http.NewRequest("POST", "https://api.hasdata.com/scrape/web", bytes.NewBuffer(payload))
	req.Header.Add("Content-Type", "application/json")
	req.Header.Add("x-api-key", "<your-api-key>")

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

	responseBody, _ := io.ReadAll(res.Body)
	fmt.Println(string(responseBody))
}

Response

{
    "requestMetadata": {
        "id": "e29e8506-143b-4872-a079-53b72e0edb10",
        "status": "ok"
    },
    "headers": {
        "accept-ranges":"bytes",
        "alt-svc":"h3=\":443\"; ma=93600,h3-29=\":443\"; ma=93600,quic=\":443\"; ma=93600; v=\"43\"",
        "cache-control":"max-age=2589",
        "content-encoding":"gzip",
        "content-length":"648",
        "content-type":"text/html",
        "date":"Fri, 11 Apr 2025 23:41:30 GMT",
        "etag":"\"84238dfc8092e5d9c0dac8ef93371a07:1736799080.121134\"",
        "last-modified":"Mon, 13 Jan 2025 20:11:20 GMT",
        "vary":"Accept-Encoding"
    },
    "screenshot": "https://f005.backblazeb2.com/file/hasdata-screenshots/e29e8506-143b-4872-a079-53b72e0edb10.jpeg",
    "content": "<!DOCTYPE html><html><head><title>Example Domain</title> ... </body></html>",
    "markdown": "# Example Domain\n\nThis domain is for use in ... [More information...](https://www.iana.org/domains/example)",
    "text": "Example Domain\n\nThis domain is for use in ... More information..."
}

Maximum page load time is restricted to 300 seconds. In cases where a request fails after 300 seconds, you will not be charged for the unsuccessful request.

Add Optional Parameters

You can include additional parameters to control what data is returned:

outputFormat – Array of formats to return. Supports: html, text, markdown, json.
screenshot – Set to true to include a screenshot of the rendered page.
extractLinks – Set to true to extract all hyperlinks from the page.
extractEmails – Set to true to extract all email addresses found on the page.

Proxy Configuration

To scrape content with location-specific views or bypass stricter anti-bot systems, you can configure proxies:

proxyType – Choose proxy type. Options: residential, datacenter.
proxyCountry – Set a specific country for the proxy. Use ISO 3166-1 alpha-2 format (e.g. US, DE, IN).

That’s it. You’re ready to start scraping. For advanced usage and all parameters, see the API Params section.

Get Started

Features

Quickstart - Web Scraping API

Get Your API Key

Make Your First Request

Add Optional Parameters

Proxy Configuration

​Get Your API Key

​Make Your First Request

​Add Optional Parameters

​Proxy Configuration

Get Your API Key

Make Your First Request

Add Optional Parameters

Proxy Configuration