Private pages

If the target page changes based on cookies, authorization, locale, or geolocation, the extraction rules are only half the problem. You also need the request to reach the right page variant. The general patterns for headers, secrets, endpoint selection, and proxy are covered in private pages patterns.

This page shows the data-extraction-specific setup.

microlink https://example.com&data.title.selector=h1&data.title.attr=text&headers.accept-language=en-US

curl -G "https://api.microlink.io" \
  -d "url=https://example.com" \
  -d "data.title.selector=h1" \
  -d "data.title.attr=text" \
  -d "meta=false" \
  -d "headers.accept-language=en-US"

import mql from '@microlink/mql'

const { data } = await mql('https://example.com', {
  data: {
    title: {
      selector: "h1",
      attr: "text"
    }
  },
  meta: false,
  headers: {
    "accept-language": "en-US"
  }
})

import requests

url = "https://api.microlink.io/"

querystring = {
    "url": "https://example.com",
    "data.title.selector": "h1",
    "data.title.attr": "text",
    "meta": "false",
    "headers.accept-language": "en-US"
}

response = requests.get(url, params=querystring)

print(response.json())

require 'uri'
require 'net/http'

base_url = "https://api.microlink.io/"

params = {
  url: "https://example.com",
  data.title.selector: "h1",
  data.title.attr: "text",
  meta: "false",
  headers.accept-language: "en-US"
}

uri = URI(base_url)
uri.query = URI.encode_www_form(params)

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

request = Net::HTTP::Get.new(uri)
response = http.request(request)

puts response.body

<?php

$baseUrl = "https://api.microlink.io/";

$params = [
    "url" => "https://example.com",
    "data.title.selector" => "h1",
    "data.title.attr" => "text",
    "meta" => "false",
    "headers.accept-language" => "en-US"
];

$query = http_build_query($params);
$url = $baseUrl . '?' . $query;

$curl = curl_init();

curl_setopt_array($curl, [
    CURLOPT_URL => $url,
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_ENCODING => "",
    CURLOPT_MAXREDIRS => 10,
    CURLOPT_TIMEOUT => 30,
    CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
    CURLOPT_CUSTOMREQUEST => "GET"
]);

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

curl_close($curl);

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

package main

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

func main() {
    baseURL := "https://api.microlink.io"

    u, err := url.Parse(baseURL)
    if err != nil {
        panic(err)
    }
    q := u.Query()
    q.Set("url", "https://example.com")
    q.Set("data.title.selector", "h1")
    q.Set("data.title.attr", "text")
    q.Set("meta", "false")
    q.Set("headers.accept-language", "en-US")
    u.RawQuery = q.Encode()

    req, err := http.NewRequest("GET", u.String(), nil)
    if err != nil {
        panic(err)
    }

    client := &http.Client{}
    resp, err := client.Do(req)
    if err != nil {
        panic(err)
    }
    defer resp.Body.Close()

    body, err := io.ReadAll(resp.Body)
    if err != nil {
        panic(err)
    }

    fmt.Println(string(body))
}

import mql from '@microlink/mql'

const { data } = await mql('https://example.com', {
  data: {
    title: {
      selector: "h1",
      attr: "text"
    }
  },
  meta: false,
  headers: {
    "accept-language": "en-US"
  }
})

Use x-api-header-* to forward secrets without exposing them in the URL:

curl -G https://pro.microlink.io \
  -d url=https://example.com/private \
  -d data.title.selector=h1 \
  -d data.title.attr=text \
  -d meta=false \
  -H 'x-api-key: YOUR_API_TOKEN' \
  -H 'x-api-header-cookie: session=YOUR_SESSION_COOKIE'

If the target blocks headless traffic, geofences content, or rate-limits the origin, use proxy . If the API returns EPROXYNEEDED, that confirms it.

For other errors, continue with troubleshooting.

If extraction still fails after the auth setup is correct, continue with troubleshooting.