Scrape a webpage meta with custom options
curl --request POST \
--url https://api.geekflare.com/metascraping \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"url": "https://example.com",
"device": "desktop",
"blockAds": true,
"renderJS": true,
"proxyCountry": "us",
"format": "json",
"fileOutput": false
}
'import requests
url = "https://api.geekflare.com/metascraping"
payload = {
"url": "https://example.com",
"device": "desktop",
"blockAds": True,
"renderJS": True,
"proxyCountry": "us",
"format": "json",
"fileOutput": False
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
url: 'https://example.com',
device: 'desktop',
blockAds: true,
renderJS: true,
proxyCountry: 'us',
format: 'json',
fileOutput: false
})
};
fetch('https://api.geekflare.com/metascraping', 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.geekflare.com/metascraping",
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',
'device' => 'desktop',
'blockAds' => true,
'renderJS' => true,
'proxyCountry' => 'us',
'format' => 'json',
'fileOutput' => false
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <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://api.geekflare.com/metascraping"
payload := strings.NewReader("{\n \"url\": \"https://example.com\",\n \"device\": \"desktop\",\n \"blockAds\": true,\n \"renderJS\": true,\n \"proxyCountry\": \"us\",\n \"format\": \"json\",\n \"fileOutput\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<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://api.geekflare.com/metascraping")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://example.com\",\n \"device\": \"desktop\",\n \"blockAds\": true,\n \"renderJS\": true,\n \"proxyCountry\": \"us\",\n \"format\": \"json\",\n \"fileOutput\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.geekflare.com/metascraping")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"url\": \"https://example.com\",\n \"device\": \"desktop\",\n \"blockAds\": true,\n \"renderJS\": true,\n \"proxyCountry\": \"us\",\n \"format\": \"json\",\n \"fileOutput\": false\n}"
response = http.request(request)
puts response.read_body{
"timestamp": 1783063255117,
"apiStatus": "success",
"apiCode": 200,
"meta": {
"url": "https://example.com",
"device": "desktop",
"format": "json",
"fileOutput": false,
"blockAds": true,
"renderJS": true,
"test": {
"id": "mxqx9v9y0742lap6altwdteqd28t23nq"
},
"proxyCountry": "<string>"
},
"data": "https://cdn.geekflare.com/tests/webscraping/ZuyhINuAZPQQabbN"
}{
"timestamp": 1700000000000,
"apiStatus": "failure",
"apiCode": 400,
"message": "INVALID_URL",
"details": "The URL must be a valid HTTP or HTTPS URL."
}{
"timestamp": 1700000000000,
"apiStatus": "failure",
"apiCode": 422,
"message": "NO_METADATA",
"details": "Metadata could not be extracted from the target URL."
}{
"timestamp": 1700000000000,
"apiStatus": "failure",
"apiCode": 500,
"message": "CRAWL_FAILED",
"details": "Our crawling service encountered an error while attempting to fetch data from the specified URL."
}Endpoint
Meta Scraping
POST
/
metascraping
Scrape a webpage meta with custom options
curl --request POST \
--url https://api.geekflare.com/metascraping \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"url": "https://example.com",
"device": "desktop",
"blockAds": true,
"renderJS": true,
"proxyCountry": "us",
"format": "json",
"fileOutput": false
}
'import requests
url = "https://api.geekflare.com/metascraping"
payload = {
"url": "https://example.com",
"device": "desktop",
"blockAds": True,
"renderJS": True,
"proxyCountry": "us",
"format": "json",
"fileOutput": False
}
headers = {
"x-api-key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
url: 'https://example.com',
device: 'desktop',
blockAds: true,
renderJS: true,
proxyCountry: 'us',
format: 'json',
fileOutput: false
})
};
fetch('https://api.geekflare.com/metascraping', 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.geekflare.com/metascraping",
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',
'device' => 'desktop',
'blockAds' => true,
'renderJS' => true,
'proxyCountry' => 'us',
'format' => 'json',
'fileOutput' => false
]),
CURLOPT_HTTPHEADER => [
"Content-Type: application/json",
"x-api-key: <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://api.geekflare.com/metascraping"
payload := strings.NewReader("{\n \"url\": \"https://example.com\",\n \"device\": \"desktop\",\n \"blockAds\": true,\n \"renderJS\": true,\n \"proxyCountry\": \"us\",\n \"format\": \"json\",\n \"fileOutput\": false\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("x-api-key", "<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://api.geekflare.com/metascraping")
.header("x-api-key", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://example.com\",\n \"device\": \"desktop\",\n \"blockAds\": true,\n \"renderJS\": true,\n \"proxyCountry\": \"us\",\n \"format\": \"json\",\n \"fileOutput\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.geekflare.com/metascraping")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"url\": \"https://example.com\",\n \"device\": \"desktop\",\n \"blockAds\": true,\n \"renderJS\": true,\n \"proxyCountry\": \"us\",\n \"format\": \"json\",\n \"fileOutput\": false\n}"
response = http.request(request)
puts response.read_body{
"timestamp": 1783063255117,
"apiStatus": "success",
"apiCode": 200,
"meta": {
"url": "https://example.com",
"device": "desktop",
"format": "json",
"fileOutput": false,
"blockAds": true,
"renderJS": true,
"test": {
"id": "mxqx9v9y0742lap6altwdteqd28t23nq"
},
"proxyCountry": "<string>"
},
"data": "https://cdn.geekflare.com/tests/webscraping/ZuyhINuAZPQQabbN"
}{
"timestamp": 1700000000000,
"apiStatus": "failure",
"apiCode": 400,
"message": "INVALID_URL",
"details": "The URL must be a valid HTTP or HTTPS URL."
}{
"timestamp": 1700000000000,
"apiStatus": "failure",
"apiCode": 422,
"message": "NO_METADATA",
"details": "Metadata could not be extracted from the target URL."
}{
"timestamp": 1700000000000,
"apiStatus": "failure",
"apiCode": 500,
"message": "CRAWL_FAILED",
"details": "Our crawling service encountered an error while attempting to fetch data from the specified URL."
}Authorizations
API Key required for all endpoints
Body
application/json
Target URL
Example:
"https://example.com"
Device type to emulate. Defaults to desktop.
Available options:
desktop, mobile Example:
"desktop"
Whether to block ads
Example:
true
Whether to render JavaScript
Example:
true
Proxy country code to route the request
Example:
"us"
Format of the scraped result. Defaults to html.
Available options:
markdown, json Example:
"json"
Whether to get response in file format
Example:
false
Response
Successfully scraped webpage meta
Timestamp of the request in milliseconds
Example:
1783063255117
API status message
Available options:
success, failure Example:
"success"
API status code
Example:
200
Metadata about the request
Show child attributes
Show child attributes
Scraped data (URL or inline content depending on output)
Example:
"https://cdn.geekflare.com/tests/webscraping/ZuyhINuAZPQQabbN"
⌘I