Skip to main content
POST
/
scrape
Scrape
curl --request POST \
  --url https://api.blat.ai/scrape \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "https://example.com",
  "allow_external_links": false,
  "allow_subdomain_links": false,
  "extract_links": false,
  "format": "html"
}
'
import requests

url = "https://api.blat.ai/scrape"

payload = {
"url": "https://example.com",
"allow_external_links": False,
"allow_subdomain_links": False,
"extract_links": False,
"format": "html"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}

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

print(response.text)
const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
url: 'https://example.com',
allow_external_links: false,
allow_subdomain_links: false,
extract_links: false,
format: 'html'
})
};

fetch('https://api.blat.ai/scrape', 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.blat.ai/scrape",
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://example.com',
'allow_external_links' => false,
'allow_subdomain_links' => false,
'extract_links' => false,
'format' => 'html'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);

$response = curl_exec($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.blat.ai/scrape"

payload := strings.NewReader("{\n \"url\": \"https://example.com\",\n \"allow_external_links\": false,\n \"allow_subdomain_links\": false,\n \"extract_links\": false,\n \"format\": \"html\"\n}")

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

req.Header.Add("Authorization", "Bearer <token>")
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.blat.ai/scrape")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://example.com\",\n \"allow_external_links\": false,\n \"allow_subdomain_links\": false,\n \"extract_links\": false,\n \"format\": \"html\"\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.blat.ai/scrape")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"url\": \"https://example.com\",\n \"allow_external_links\": false,\n \"allow_subdomain_links\": false,\n \"extract_links\": false,\n \"format\": \"html\"\n}"

response = http.request(request)
puts response.read_body
{
  "extracted_links": [
    "extracted_links",
    "extracted_links"
  ],
  "content": "content"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}
{
"code": "code",
"details": {
"key": ""
},
"message": "message"
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Scraping request parameters

url
string
required

The URL to fetch content from

Example:

"https://example.com"

Whether to include external links

Whether to include subdomain links

Whether to extract links from HTML

format
enum<string>
default:html

The desired output format

Available options:
html,
markdown

Response

OK

content
string

The HTML or Markdown content

Extracted links, omitted if empty or not requested