Using this function, you can get the overall information on a website as well as drill down into exact on-page issues of a website that has been scanned. As a result, you will know what functions to use for receiving detailed data for each of the found issues.
GET
Your account will be charged only for posting a task.
The cost can be calculated on the Pricing page.
Description of the fields for sending a request:
| Field name | Type | Description |
|---|---|---|
id | string | task identifier |
tasks array with the information specific to the set tasks.
Description of the fields in the results array:
| Field name | Type | Description |
|---|---|---|
version | string | the current version of the API |
status_code | integer | general status code |
status_message | string | general informational message |
time | string | execution time, seconds |
cost | float | total tasks cost, USD |
tasks_count | integer | the number of tasks in the |
tasks_error | integer | the number of tasks in the |
tasks | array | array of tasks |
id | string | task identifier |
status_code | integer | status code of the task |
status_message | string | informational message of the task |
time | string | execution time, seconds |
cost | float | cost of the task, USD |
result_count | integer | number of elements in the |
path | array | URL path |
data | object | contains the same parameters that you specified in the POST request |
result | array | array of results |
crawl_progress | string | status of the crawling session |
crawl_status | object | details of the crawling session |
max_crawl_pages | integer | maximum number of pages to crawl |
pages_in_queue | integer | number of pages that are currently in the crawling queue |
pages_crawled | integer | number of crawled pages |
crawl_gateway_address | string | crawler ip address |
crawl_stop_reason | string | reason why the crawling stopped |
domain_info | object | domain-wide info |
name | string | domain name |
cms | string | content management system |
ip | string | domain ip address |
server | string | website server |
crawl_start | string | time when the crawling start |
crawl_end | string | time when the crawling ended |
extended_crawl_status | string | crawl status and errors |
ssl_info | object | ssl certificate info |
valid_certificate | boolean | ssl certificate validity |
certificate_issuer | string | ssl certificate authority |
certificate_subject | string | ssl certificate subject |
certificate_version | string | ssl certificate version |
certificate_hash | string | ssl certificate hash |
certificate_expiration_date | string | ssl certificate expiration date |
checks | object | website checks |
sitemap | boolean | website sitemap |
robots_txt | boolean | robots.txt file |
start_page_deny_flag | boolean | deny flag on a start page |
ssl | boolean | ssl certificate |
http2 | boolean | HTTP/2 protocol |
test_canonicalization | boolean | canonical tags |
test_www_redirect | boolean | www to non-www redirect |
test_hidden_server_signature | object | hidden server signature |
test_page_not_found | boolean | 404 status for a page that cannot be found |
test_directory_browsing | boolean | directory browsing not accessible |
test_https_redirect | boolean | http requests are redirected to https |
total_pages | integer | total crawled pages |
total_uncrawlable_resources | integer | total uncrawlable resources |
page_not_found_status_code | integer | status code returned by a non-existent page |
canonicalization_status_code | integer | status code returned by a canonicalized page |
directory_browsing_status_code | integer | status code returned by a directory |
www_redirect_status_code | integer | redirect status code |
main_domain | string | root domain name |
page_metrics | object | page-specific info |
links_external | integer | number of external links |
links_internal | integer | number of internal links |
duplicate_title | integer | number of pages with duplicate titles |
duplicate_description | integer | number of pages with duplicate descriptions |
duplicate_content | integer | number of pages with duplicate content |
broken_links | integer | number of broken links |
broken_resources | integer | number of broken resources |
links_relation_conflict | integer | number of links present on the target website that may have a conflict |
redirect_loop | integer | number of redirect chains that start and end at the same URL |
onpage_score | float | shows how website is optimized on a 100-point scale |
non_indexable | integer | number of non-indexable pages |
checks | object | page-specific on-page check-ups |
canonical | integer | number of canonical pages |
duplicate_meta_tags | integer | number of pages with duplicate meta tags |
no_description | integer | number of pages with no description |
frame | integer | number of pages with frames |
large_page_size | integer | number of heavy pages |
irrelevant_description | integer | number of pages with irrelevant description |
irrelevant_meta_keywords | integer | number of pages with irrelevant meta keywords |
is_https | integer | number of pages with the https protocol |
is_http | integer | number of pages with the http protocol |
title_too_long | integer | number of pages with long titles |
low_content_rate | integer | number of pages with a low content rate |
small_page_size | integer | number of small pages |
no_h1_tag | integer | number of pages with empty or absent h1 tags |
recursive_canonical | integer | recursive canonical error |
no_favicon | integer | number of pages with no favicon |
no_image_alt | integer | number of pages containing images without |
no_image_title | integer | number of pages containing images without |
seo_friendly_url | integer | number of pages with seo-frienldy urls |
seo_friendly_url_characters_check | integer | url characters check-up |
seo_friendly_url_dynamic_check | integer | url dynamic check-up |
seo_friendly_url_keywords_check | integer | url keyword check-up |
seo_friendly_url_relative_length_check | integer | url leghth check-up |
title_too_short | integer | pages with short titles |
no_content_encoding | integer | pages with no content encoding |
high_waiting_time | integer | pages with high waiting time |
high_loading_time | integer | pages with high loading time |
is_redirect | integer | pages with redirects |
is_broken | integer | broken pages |
is_4xx_code | integer | pages with |
is_5xx_code | integer | pages with |
is_www | integer | pages with www |
no_doctype | integer | pages with no doctype |
no_encoding_meta_tag | integer | pages with no meta tag encoding |
high_content_rate | integer | pages with high content rate |
low_character_count | integer | pages with low character count |
high_character_count | integer | pages with high character count |
low_readability_rate | integer | pages with low readability rate |
irrelevant_title | integer | pages with irrelevant titles |
deprecated_html_tags | integer | pages with deprecated tags |
duplicate_title_tag | integer | pages with more than one title tag |
no_title | integer | pages with no title |
flash | integer | pages with flash |
lorem_ipsum | integer | pages with lorem ipsum |
has_misspelling | integer | pages with misspelling |
canonical_to_broken | integer | canonical pages pointing to broken pages |
canonical_to_redirect | integer | canonical pages pointing to pages that redirect elsewhere |
has_links_to_redirects | integer | pages pointing to pages that redirect elsewhere |
is_orphan_page | integer | pages with no internal links pointing to them |
has_meta_refresh_redirect | integer | pages with meta refresh redirect |
meta_charset_consistency | integer | pages with meta charset inconsistency |
size_greater_than_3mb | integer | pages with size larger than 3 MB |
has_html_doctype | integer | pages with HTML doctype declaration |
https_to_http_links | integer | pages with HTTPS protocol that link to pages with HTTP protocol |
has_render_blocking_resources | integer | pages with render-blocking resources |
redirect_chain | integer | pages with multiple redirects |
canonical_chain | integer | pages with canonical pointing to a page that has a canonical pointing elsewhere |
is_link_relation_conflict | integer | pages on the target website that may have a link relation conflict |
Instead of ‘login’ and ‘password’ use your credentials from https://app.dataforseo.com/api-access
# Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-access
login="login"
password="password"
cred="$(printf ${login}:${password} | base64)"
id="07281559-0695-0216-0000-c269be8b7592"
curl --location --request GET "https://api.dataforseo.com/v3/on_page/summary/${id}"
--header "Authorization: Basic ${cred}"
--header "Content-Type: application/json" <?php
// You can download this file from here https://api.dataforseo.com/v3/_examples/php/_php_RestClient.zip
require('RestClient.php');
$api_url = 'https://api.dataforseo.com/';
// Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-access
$client = new RestClient($api_url, null, 'login', 'password');
try {
$result = array();
// using this method you can get summary for task
// GET /v3/on_page/summary/$id
$id = "07281559-0695-0216-0000-c269be8b7592";
$result[] = $client->get('/v3/on_page/summary/' . $id);
print_r($result);
// do something with result
} catch (RestClientException $e) {
echo "n";
print "HTTP code: {$e->getHttpCode()}n";
print "Error code: {$e->getCode()}n";
print "Message: {$e->getMessage()}n";
print $e->getTraceAsString();
echo "n";
}
$client = null;
?>const task_id = '02231934-2604-0066-2000-570459f04879';
const axios = require('axios');
axios({
method: 'get',
url: 'https://api.dataforseo.com/v3/on_page/summary/' + task_id,
auth: {
username: 'login',
password: 'password'
},
headers: {
'content-type': 'application/json'
}
}).then(function (response) {
var result = response['data']['tasks'];
// Result data
console.log(result);
}).catch(function (error) {
console.log(error);
});from random import Random
from client import RestClient
# You can download this file from here https://api.dataforseo.com/v3/_examples/python/_python_Client.zip
client = RestClient("login", "password")
# using this method you can get summary for task
# GET /v3/on_page/summary/$id
id = "07281559-0695-0216-0000-c269be8b7592"
response = client.get("/v3/on_page/summary/" + id)
# you can find the full list of the response codes here https://docs.dataforseo.com/v3/appendix/errors
if response["status_code"] == 20000:
print(response)
# do something with result
else:
print("error. Code: %d Message: %s" % (response["status_code"], response["status_message"]))using Newtonsoft.Json;
using System;
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text;
using System.Threading.Tasks;
namespace DataForSeoDemos
{
public static partial class Demos
{
public static async Task on_page_summary()
{
var httpClient = new HttpClient
{
BaseAddress = new Uri("https://api.dataforseo.com/"),
// Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-access
DefaultRequestHeaders = { Authorization = new AuthenticationHeaderValue("Basic", Convert.ToBase64String(Encoding.ASCII.GetBytes("login:password"))) }
};
// using this method you can get summary for task
// GET /v3/on_page/summary/$id
// use the task identifier that you recieved upon setting a task
string id = "07281559-0695-0216-0000-c269be8b7592";
var taskGetResponse = await httpClient.GetAsync("/v3/on_page/summary/" + id);
var result = JsonConvert.DeserializeObject(await taskGetResponse.Content.ReadAsStringAsync());
if (result.tasks != null)
{
foreach (var taskResult in result.tasks)
{
// you can find the full list of the response codes here https://docs.dataforseo.com/v3/appendix/errors
if (taskResult.status_code >= 40000 || taskResult.result == null)
Console.WriteLine($"error. Code: {taskResult.status_code} Message: {taskResult.status_message}");
else
// do something with result
Console.WriteLine(String.Join(Environment.NewLine, taskResult));
}
}
else
Console.WriteLine($"error. Code: {result.status_code} Message: {result.status_message}");
}
}
}The above command returns JSON structured like this:
{
"version": "0.1.20221214",
"status_code": 20000,
"status_message": "Ok.",
"time": "1.0297 sec.",
"cost": 0,
"tasks_count": 1,
"tasks_error": 0,
"tasks": [
{
"id": "05021654-1535-0216-0000-bb170c8efb5b",
"status_code": 20000,
"status_message": "Ok.",
"time": "1.0125 sec.",
"cost": 0,
"result_count": 1,
"path": [
"v3",
"on_page",
"summary",
"05021654-1535-0216-0000-bb170c8efb5b"
],
"data": {
"api": "on_page",
"function": "summary",
"target": "dataforseo.com",
"max_crawl_pages": 1000,
"enable_www_redirect_check": "true"
},
"result": [
{
"crawl_progress": "in_progress",
"crawl_status": {
"max_crawl_pages": 1000,
"pages_in_queue": 142,
"pages_crawled": 15
},
"crawl_gateway_address": "168.119.141.170",
"crawl_stop_reason": null,
"domain_info": {
"name": "dataforseo.com",
"cms": "powered by wpbakery page builder - drag and drop page builder for wordpress.",
"ip": "104.26.6.202",
"server": "cloudflare",
"crawl_start": "2023-05-02 13:54:55 +00:00",
"crawl_end": null,
"extended_crawl_status": "no_errors",
"ssl_info": {
"valid_certificate": true,
"certificate_issuer": "CN=GTS CA 1P5, O=Google Trust Services LLC, C=US",
"certificate_subject": "CN=dataforseo.com",
"certificate_version": 3,
"certificate_hash": "sha256RSA",
"certificate_expiration_date": "2023-07-23 14:16:19 +00:00"
},
"checks": {
"sitemap": true,
"robots_txt": true,
"start_page_deny_flag": false,
"ssl": true,
"http2": true,
"test_canonicalization": false,
"test_www_redirect": true,
"test_hidden_server_signature": true,
"test_page_not_found": true,
"test_directory_browsing": true,
"test_https_redirect": true
},
"total_pages": 15,
"total_uncrawlable_resources": 5,
"page_not_found_status_code": 404,
"canonicalization_status_code": 403,
"directory_browsing_status_code": 301,
"www_redirect_status_code": 301,
"main_domain": "dataforseo.com"
},
"page_metrics": {
"links_external": 386,
"links_internal": 1407,
"duplicate_title": 0,
"duplicate_description": 0,
"duplicate_content": 4,
"broken_links": 0,
"broken_resources": 0,
"links_relation_conflict": 0,
"redirect_loop": 0,
"onpage_score": 96.93,
"non_indexable": 45,
"checks": {
"canonical": 15,
"duplicate_meta_tags": 15,
"no_description": 1,
"frame": 0,
"large_page_size": 0,
"irrelevant_description": 0,
"irrelevant_meta_keywords": 15,
"is_https": 15,
"is_http": 0,
"title_too_long": 1,
"low_content_rate": 15,
"small_page_size": 0,
"no_h1_tag": 0,
"recursive_canonical": 0,
"no_favicon": 0,
"no_image_alt": 0,
"no_image_title": 0,
"seo_friendly_url": 15,
"seo_friendly_url_characters_check": 15,
"seo_friendly_url_dynamic_check": 15,
"seo_friendly_url_keywords_check": 15,
"seo_friendly_url_relative_length_check": 15,
"title_too_short": 2,
"no_content_encoding": 0,
"high_waiting_time": 0,
"high_loading_time": 0,
"is_redirect": 0,
"is_broken": 0,
"is_4xx_code": 0,
"is_5xx_code": 0,
"is_www": 0,
"no_doctype": 0,
"no_encoding_meta_tag": 0,
"high_content_rate": 0,
"low_character_count": 0,
"high_character_count": 0,
"low_readability_rate": 0,
"irrelevant_title": 0,
"deprecated_html_tags": 0,
"duplicate_title_tag": 0,
"no_title": 0,
"flash": 0,
"lorem_ipsum": 0,
"has_misspelling": null,
"canonical_to_broken": 0,
"canonical_to_redirect": 0,
"has_links_to_redirects": 0,
"is_orphan_page": 0,
"has_meta_refresh_redirect": 0,
"meta_charset_consistency": 15,
"size_greater_than_3mb": 0,
"has_html_doctype": 15,
"https_to_http_links": 1,
"has_render_blocking_resources": 15,
"redirect_chain": 0,
"canonical_chain": 0,
"is_link_relation_conflict": 0
}
}
}
]
}
]
}