Scrape Single Page

Scrapes a single webpage to extract its content for the knowledge base. Use this endpoint to add a specific page without crawling an entire website. Extraction: Returns the page title, descriptio

POST /ai-agents/agent-builder/knowledge-base/website/individual-page

Scrape Single Page

cURL

curl --request POST \
  --url https://{appId}.api-{region}.cometchat.io/v3/ai-agents/agent-builder/knowledge-base/website/individual-page \
  --header 'Content-Type: application/json' \
  --header 'apikey: <api-key>' \
  --data '
{
  "url": "https://docs.example.com/getting-started",
  "timeout": 30000,
  "format": "markdown"
}
'

import requests

url = "https://{appId}.api-{region}.cometchat.io/v3/ai-agents/agent-builder/knowledge-base/website/individual-page"

payload = {
    "url": "https://docs.example.com/getting-started",
    "timeout": 30000,
    "format": "markdown"
}
headers = {
    "apikey": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {apikey: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    url: 'https://docs.example.com/getting-started',
    timeout: 30000,
    format: 'markdown'
  })
};

fetch('https://{appId}.api-{region}.cometchat.io/v3/ai-agents/agent-builder/knowledge-base/website/individual-page', 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://{appId}.api-{region}.cometchat.io/v3/ai-agents/agent-builder/knowledge-base/website/individual-page",
  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' => 'https://docs.example.com/getting-started',
    'timeout' => 30000,
    'format' => 'markdown'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "apikey: <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://{appId}.api-{region}.cometchat.io/v3/ai-agents/agent-builder/knowledge-base/website/individual-page"

	payload := strings.NewReader("{\n  \"url\": \"https://docs.example.com/getting-started\",\n  \"timeout\": 30000,\n  \"format\": \"markdown\"\n}")

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

	req.Header.Add("apikey", "<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://{appId}.api-{region}.cometchat.io/v3/ai-agents/agent-builder/knowledge-base/website/individual-page")
  .header("apikey", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"https://docs.example.com/getting-started\",\n  \"timeout\": 30000,\n  \"format\": \"markdown\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{appId}.api-{region}.cometchat.io/v3/ai-agents/agent-builder/knowledge-base/website/individual-page")

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

request = Net::HTTP::Post.new(url)
request["apikey"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"url\": \"https://docs.example.com/getting-started\",\n  \"timeout\": 30000,\n  \"format\": \"markdown\"\n}"

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

200

{
  "success": true,
  "message": "Page scraped successfully",
  "data": {
    "url": "https://docs.example.com/getting-started",
    "title": "Getting Started Guide",
    "description": "Learn how to get started with our platform",
    "content": "# Getting Started\n\nWelcome to our platform...",
    "metadata": {
      "og": {},
      "twitter": {},
      "canonical": "",
      "language": "en"
    },
    "scraper": "Firecrawl",
    "crawlDuration": 2500,
    "contentLength": 1024,
    "timestamp": "2025-12-05T17:30:00Z"
  }
}

For the complete error reference, see Error Guide.

Authorizations

apikey · string · header · required

API Key (i.e. Rest API Key from the Dashboard).

Body

application/json

Single page scraping configuration

url · string · required

Target page URL to crawl and extract content from

Example:

"https://docs.example.com/getting-started"

timeout · number · default: 30000

Request timeout in milliseconds

Required range: 5000 <= x <= 120000

Example:

30000

format · enum<string> · default: markdown

Extract content in specific format

Available options: markdown, html, text

Example:

"markdown"

Response

200 - application/json

Page scraped successfully

success · boolean

Example:

true

message · string

Example:

"Page scraped successfully"

data · object

Show child attributes