NAVNavbar
Logo
cURL php NodeJS Python cSharp

OnPage API Instant Pages

‌‌
Using this function you will get page-specific data with detailed information on how well a particular page is optimized for organic search.

This endpoint is working based on the Live method and doesn’t require making a separate GET request for obtaining task results.

Instead of ‘login’ and ‘password’ use your credentials from https://app.dataforseo.com/api-dashboard

<?php
// You can download this file from here https://cdn.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-dashboard
$client = new RestClient($api_url, null, 'login', 'password');
$post_array = array();
// example #1 - a simple way to set a task
$post_array[] = array(
   "url" => "https://dataforseo.com/apis/on-page-api"
);
// example #2 - a way to set a task with additional parameters
$post_array[] = array(
   "url" => "https://dataforseo.com/blog",
   "enable_javascript" => true,
   "custom_js" => "meta = {}; meta.url = document.URL; meta;"
);
// this example has a 2 elements, but in the case of large number of tasks - send up to 20 elements per POST request
if (count($post_array) > 0) {
   try {
      // POST /v3/on_page/instant_pages
      // the full list of possible parameters is available in documentation
      $result = $client->post('/v3/on_page/instant_pages', $post_array);
      print_r($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;
?>

The above command returns JSON structured like this:

{
  "version": "0.1.20220627",
  "status_code": 20000,
  "status_message": "Ok.",
  "time": "0.9929 sec.",
  "cost": 0.00025,
  "tasks_count": 1,
  "tasks_error": 0,
  "tasks": [
    {
      "id": "07201459-1535-0275-0000-b1297fdec539",
      "status_code": 20000,
      "status_message": "Ok.",
      "time": "0.9231 sec.",
      "cost": 0.00025,
      "result_count": 1,
      "path": [
        "v3",
        "on_page",
        "instant_pages"
      ],
      "data": {
        "api": "on_page",
        "function": "instant_pages",
        "url": "https://dataforseo.com/blog",
        "custom_js": "meta = {}; meta.url = document.URL; meta;"
      },
      "result": [
        {
          "crawl_progress": "finished",
          "crawl_status": null,
          "crawl_gateway_address": "168.119.99.193",
          "items_count": 1,
          "items": [
            {
              "resource_type": "html",
              "status_code": 200,
              "location": null,
              "url": "https://dataforseo.com/blog",
              "meta": {
                "title": "DataForSEO Blog – The Brightest SEO Data Insights",
                "charset": 65001,
                "follow": true,
                "generator": "Powered by WPBakery Page Builder - drag and drop page builder for WordPress.",
                "htags": {
                  "h4": [
                    "Products",
                    "By industry",
                    "By company type",
                    "By application",
                    "Docs",
                    "Resources",
                    "Login",
                    "Categories",
                    "APIs",
                    "Databases",
                    "Solutions",
                    "Knowledge Base",
                    "Resources",
                    "Legal information",
                    "Payment Methods:"
                  ],
                  "h1": [
                    "Blog"
                  ],
                  "h2": [
                    "Seznam in SERP API: Add This Popular Search Engine to Your Rank Tracking Tool",
                    "Introduce Page Screenshots to Your SEO Tool With This New OnPage API Endpoint",
                    "Meet App Data API! 3 ASO Tools You Can Develop With This Powerful Data Source",
                    "Analyze Historical Google SERPs by Keyword with API from DataForSEO",
                    "How to Build an Amazon Keyword Research Tool with API",
                    "How to Use Bing API Data for Keyword Research and Competitor Analysis",
                    "DataForSEO during the invasion of Ukraine: important information to know",
                    "Getting Reviews & Ratings Data at a Low Cost with API from DataForSEO",
                    "SEO Tools Don’t Track Bing SERP Features? Use This API to Get Ahead",
                    "How to Get Google Trends Data with API: 3 SEO Use Cases"
                  ]
                },
                "description": "DataForSEO Blog is dedicated to SEO API best practices, software development use cases, and the latest martech industry insights",
                "favicon": "https://dataforseo.com/wp-content/uploads/2022/04/cropped-favicon_512-32x32.png",
                "meta_keywords": null,
                "canonical": "https://dataforseo.com/blog",
                "internal_links_count": 98,
                "external_links_count": 7,
                "inbound_links_count": 0,
                "images_count": 11,
                "images_size": 0,
                "scripts_count": 43,
                "scripts_size": 0,
                "stylesheets_count": 0,
                "stylesheets_size": 0,
                "title_length": 49,
                "description_length": 128,
                "render_blocking_scripts_count": 23,
                "render_blocking_stylesheets_count": 0,
                "cumulative_layout_shift": 0,
                "meta_title": null,
                "content": {
                  "plain_text_size": 2480,
                  "plain_text_rate": 0.016461342395921834,
                  "plain_text_word_count": 432,
                  "automated_readability_index": 7.008611111111112,
                  "coleman_liau_readability_index": 8.658888888888892,
                  "dale_chall_readability_index": 7.147202962962964,
                  "flesch_kincaid_readability_index": 57.98100000000002,
                  "smog_readability_index": 16.966058625362727,
                  "description_to_content_consistency": 0.4736842215061188,
                  "title_to_content_consistency": 0.7142857313156128,
                  "meta_keywords_to_content_consistency": null
                },
                "deprecated_tags": null,
                "duplicate_meta_tags": [
                  "generator"
                ],
                "spell": null,
                "social_media_tags": {
                  "og:locale": "en_US",
                  "og:type": "article",
                  "og:title": "DataForSEO Blog – The Brightest SEO Data Insights",
                  "og:description": "DataForSEO Blog is dedicated to SEO API best practices, software development use cases, and the latest martech industry insights",
                  "og:url": "https://dataforseo.com/blog",
                  "og:site_name": "DataForSEO",
                  "og:updated_time": "2021-12-10T13:19:44+03:00",
                  "article:published_time": "2017-05-11T11:01:40+03:00",
                  "article:modified_time": "2021-12-10T13:19:44+03:00",
                  "twitter:card": "summary_large_image",
                  "twitter:title": "DataForSEO Blog – The Brightest SEO Data Insights",
                  "twitter:description": "DataForSEO Blog is dedicated to SEO API best practices, software development use cases, and the latest martech industry insights",
                  "twitter:label1": "Time to read",
                  "twitter:data1": "Less than a minute"
                }
              },
              "page_timing": {
                "time_to_interactive": 38,
                "dom_complete": 38,
                "largest_contentful_paint": 0,
                "first_input_delay": 0,
                "connection_time": 15,
                "time_to_secure_connection": 21,
                "request_sent_time": 0,
                "waiting_time": 0,
                "download_time": 2,
                "duration_time": 38,
                "fetch_start": 0,
                "fetch_end": 38
              },
              "onpage_score": 98.17,
              "total_dom_size": 150673,
              "custom_js_response": {
                "url": "https://dataforseo.com/blog"
              },
              "resource_errors": {
                "errors": null,
                "warnings": [
                  {
                    "line": 3,
                    "column": 1,
                    "message": "Has node with more than 60 childs.",
                    "status_code": 1
                  },
                  {
                    "line": 0,
                    "column": 0,
                    "message": "Has more that 1500 nodes.",
                    "status_code": 2
                  }
                ]
              },
              "broken_resources": false,
              "broken_links": false,
              "duplicate_title": false,
              "duplicate_description": false,
              "duplicate_content": false,
              "click_depth": 0,
              "size": 150673,
              "encoded_size": 0,
              "total_transfer_size": 0,
              "fetch_time": "2022-07-20 14:59:26 +00:00",
              "cache_control": {
                "cachable": false,
                "ttl": 0
              },
              "checks": {
                "no_content_encoding": false,
                "high_loading_time": false,
                "is_redirect": false,
                "is_4xx_code": false,
                "is_5xx_code": false,
                "is_broken": false,
                "is_www": false,
                "is_https": true,
                "is_http": false,
                "high_waiting_time": false,
                "no_doctype": false,
                "has_html_doctype": true,
                "canonical": true,
                "no_encoding_meta_tag": false,
                "no_h1_tag": false,
                "https_to_http_links": false,
                "size_greater_than_3mb": false,
                "meta_charset_consistency": true,
                "has_meta_refresh_redirect": false,
                "has_render_blocking_resources": false,
                "low_content_rate": true,
                "high_content_rate": false,
                "low_character_count": false,
                "high_character_count": false,
                "small_page_size": false,
                "large_page_size": false,
                "low_readability_rate": false,
                "irrelevant_description": false,
                "irrelevant_title": false,
                "irrelevant_meta_keywords": false,
                "title_too_long": false,
                "has_meta_title": false,
                "title_too_short": false,
                "deprecated_html_tags": false,
                "duplicate_meta_tags": true,
                "duplicate_title_tag": false,
                "no_image_alt": false,
                "no_image_title": true,
                "no_description": false,
                "no_title": false,
                "no_favicon": false,
                "seo_friendly_url": true,
                "flash": false,
                "frame": false,
                "lorem_ipsum": false,
                "seo_friendly_url_characters_check": true,
                "seo_friendly_url_dynamic_check": true,
                "seo_friendly_url_keywords_check": true,
                "seo_friendly_url_relative_length_check": true
              },
              "content_encoding": "br",
              "media_type": "text/html",
              "server": "cloudflare",
              "is_resource": false,
              "last_modified": {
                "header": null,
                "sitemap": null,
                "meta_tag": "2021-12-10 10:19:44 +00:00"
              }
            }
          ]
        }
      ]
    }
  ]
}

All POST data should be sent in the JSON format (UTF-8 encoding). The task setting is done using the POST method. When setting a task, you should send all task parameters in the task array of the generic POST array.

You can send up to 2000 API requests per minute, with each request containing no more than 20 tasks. The maximum number of simultaneous requests you can send is limited to 30.
Note: in a single request, you can set up to 20 tasks each containing one URL, but these URLs cannot contain more than 5 identical domains.

Description of the fields for setting a task:

Field name Type Description
url string target page url
required field
absolute URL of the target page;
Note #1: results will be returned for the specified URL only;
Note #2: to prevent denial-of-service events, tasks that contain a duplicate crawl host will be returned with a 40501 error;
to prevent this error from occurring, avoid setting tasks with the same domain if at least one of your previous tasks with this domain (including a page URL on the domain) is still in a crawling queue
custom_user_agent string custom user agent
optional field
custom user agent for crawling a website
example: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36

default value: Mozilla/5.0 (compatible; RSiteAuditor)
browser_preset string preset for browser screen parameters
optional field
if you use this field, you don’t need to indicate browser_screen_width, browser_screen_height, browser_screen_scale_factorpossible values:
desktop, mobile, tabletdesktop preset will apply the following values:

browser_screen_width: 1920
browser_screen_height: 1080
browser_screen_scale_factor: 1

mobile preset will apply the following values:

browser_screen_width: 390
browser_screen_height: 844
browser_screen_scale_factor: 3

tablet preset will apply the following values:

browser_screen_width: 1024
browser_screen_height: 1366
browser_screen_scale_factor: 2

Note: to use this parameter, set enable_javascript or enable_browser_rendering to true

browser_screen_width integer browser screen width
optional field
you can set a custom browser screen width to perform audit for a particular device;
if you use this field, you don’t need to indicate browser_preset as it will be ignored;Note: to use this parameter, set enable_javascript or enable_browser_rendering to trueminimum value, in pixels: 240
maximum value, in pixels: 9999
browser_screen_height integer browser screen height
optional field
you can set a custom browser screen height to perform audit for a particular device;
if you use this field, you don’t need to indicate browser_preset as it will be ignored;Note: to use this parameter, set enable_javascript or enable_browser_rendering to trueminimum value, in pixels: 240
maximum value, in pixels: 9999
browser_screen_scale_factor float browser screen scale factor
optional field
you can set a custom browser screen resolution ratio to perform audit for a particular device;
if you use this field, you don’t need to indicate browser_preset as it will be ignored;Note: to use this parameter, set enable_javascript or enable_browser_rendering to trueminimum value: 0.5
maximum value: 3
store_raw_html boolean store HTML of a crawled page
optional field
set to true if you want get the HTML of the page using the OnPage Raw HTML endpoint
default value: false
accept_language string language header for accessing the website
optional field
all locale formats are supported (xx, xx-XX, xxx-XX, etc.)
Note: if you do not specify this parameter, some websites may deny access; in this case, pages will be returned with the "type":"broken in the response array
load_resources boolean load resources
optional field
set to true if you want to load image, stylesheets, scripts, and broken resources
default value: false
Note: if you use this parameter, additional charges will apply; learn more about the cost of tasks with this parameter in our help article; the cost can be calculated on the Pricing Page
enable_javascript boolean load javascript on a page
optional field
set to true if you want to load the scripts available on a page
default value: false
Note: if you use this parameter, additional charges will apply; learn more about the cost of tasks with this parameter in our help article; the cost can be calculated on the Pricing Page
enable_browser_rendering boolean emulate browser rendering to measure Core Web Vitals
optional field
by using this parameter you will be able to emulate a browser when loading a web page;
enable_browser_rendering loads styles, images, fonts, animations, videos, and other resources on a page;
default value: false
set to true to obtain Core Web Vitals (FID, CLS, LCP) metrics in the response;
if you use this field, parameters enable_javascript, and load_resources are enabled automatically;
Note: if you use this parameter, additional charges will apply; learn more about the cost of tasks with this parameter in our help article; the cost can be calculated on the Pricing Page
disable_cookie_popup boolean disable the cookie popup
optional field
set to true if you want to disable the popup requesting cookie consent from the user;
default value:
false
return_despite_timeout boolean return data on pages despite the timeout error
optional field
if true, the data will be provided on pages that failed to load within 120 seconds and responded with a timeout error;
default value: false
enable_xhr boolean enable XMLHttpRequest on a page
optional field
set to true if you want our crawler to request data from a web server using the XMLHttpRequest object
default value:
falseif you use this field, enable_javascript must be set to true;
custom_js string custom javascript
optional fieldNote that the execution time for the script you enter here should be 700 ms maximumfor example, you can use the following JS snippet to check if the website contains Google Tag Manager as a scr attribute:
let meta = { haveGoogleAnalytics: false, haveTagManager: false };\r\nfor (var i = 0; i < document.scripts.length; i++) {\r\n let src = document.scripts[i].getAttribute(\"src\");\r\n if (src != undefined) {\r\n if (src.indexOf(\"analytics.js\") >= 0)\r\n meta.haveGoogleAnalytics = true;\r\n\tif (src.indexOf(\"gtm.js\") >= 0)\r\n meta.haveTagManager = true;\r\n }\r\n}\r\nmeta;the returned value depends on what you specified in this field. For instance, if you specify the following script:
meta = {}; meta.url = document.URL; meta.test = 'test'; meta;
as a response you will receive the following data:
"custom_js_response": {
"url": "https://dataforseo.com/",
"test": "test"
}

Note: if you use this parameter, additional charges will apply; learn more about the cost of tasks with this parameter in our help article; the cost can be calculated on the Pricing Page

validate_micromarkup boolean enable microdata validation
optional field
if set to true, you can use the OnPage API Microdata endpoint with the id of the task;
default value: false
check_spell boolean check spelling
optional field
set to true to check spelling on a website using Hunspell library
default value: false
checks_threshold array custom threshold values for checks
optional field
you can specify custom threshold values for the parameters included in the checks array of OnPage API responses;
Note: only integer threshold values can be modified;
switch_pool boolean switch proxy pool
optional field
if true, additional proxy pools will be used to obtain the requested data;
the parameter can be used if a multitude of tasks is set simultaneously, resulting in occasional rate-limit and/or site_unreachable errors
ip_pool_for_scan string proxy pool
optional field
you can choose a location of the proxy pool that will be used to obtain the requested data;
the parameter can be used if page content is inaccessible in one of the locations, resulting in occasional site_unreachable errors
possible values: us, de

As a response of the API server, you will receive JSON-encoded data containing a 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
you can find the full list of the response codes here
Note: we strongly recommend designing a necessary system for handling related exceptional or error conditions
status_message string general informational message
you can find the full list of general informational messages here
time string execution time, seconds
cost float total tasks cost, USD
tasks_count integer the number of tasks in the tasks array
tasks_error integer the number of tasks in the tasks array returned with an error
tasks array array of tasks
        id string task identifier
unique task identifier in our system in the UUID format
        status_code integer status code of the task
generated by DataForSEO; can be within the following range: 10000-60000
you can find the full list of the response codes here
        status_message string informational message of the task
you can find the full list of general informational messages here
        time string execution time, seconds
        cost float cost of the task, USD
        result_count integer number of elements in the result array
        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
possible values: in_progress, finished
            crawl_status object details of the crawling session
in this case the value will be null
            crawl_gateway_address string crawler ip address
displays the IP address used by the crawler to initiate the current crawling session
you can find the full list of IPs used by our crawler in the Overview section
            total_items_count integer total number of relevant items in the database
            items_count integer number of items in the results array
            items array items array
              ‘html’ page
              resource_type string type of the returned resource = ‘html’
              status_code integer status code of the page
              location string location header
indicates the URL to redirect a page to
              url string page URL
              meta object page properties
the value depends on the resource_type
                  title string page title
                  charset integer code page
example: 65001
                  follow boolean indicates whether a page’s ‘meta robots’ allows crawlers to follow the links on the page
if false, the page’s ‘meta robots’ tag contains “nofollow” parameter instructing crawlers not to follow the links on the page
                  generator string meta tag generator
                  htags object HTML header tags
                  description string content of the meta description tag
                  favicon string favicon of the page
                  meta_keywords string content of the keywords meta tag
                  canonical string canonical page
                  internal_links_count integer number of internal links on the page
                  external_links_count integer number of external links on the page
                  inbound_links_count integer number of internal links pointing at the page
                  images_count integer number of images on the page
                  images_size integer total size of images on the page measured in bytes
                  scripts_count integer number of scripts on the page
                  scripts_size integer total size of scripts on the page measured in bytes
                  stylesheets_count integer number of stylesheets on the page
                  stylesheets_size integer total size of stylesheets on the page measured in bytes
                  title_length integer length of the title tag in characters
                  description_length integer length of the description tag in characters
                  render_blocking_scripts_count integer number of scripts on the page that block page rendering
                  render_blocking_stylesheets_count integer number of CSS styles on the page that block page rendering
                  cumulative_layout_shift float Core Web Vitals metric measuring the layout stability of the page
measures the sum total of all individual layout shift scores for every unexpected layout shift that occurs during the entire lifespan of the page. Learn more.
                  meta_title string meta title of the page
meta tag in the head section of an HTML document that defines the title of a page
                  content object overall information about content of the page
                      plain_text_size integer total size of the text on the page measured in bytes
                      plain_text_rate integer plaintext rate value
plain_text_size to size ratio
                      plain_text_word_count float number of words on the page
                      automated_readability_index float Automated Readability Index
                      coleman_liau_readability_index float Coleman–Liau Index
                      dale_chall_readability_index float Dale–Chall Readability Index
                      flesch_kincaid_readability_index float Flesch–Kincaid Readability Index
                      smog_readability_index float SMOG Readability Index
                      description_to_content_consistency float consistency of the meta description tag with the page content
measured from 0 to 1
                      title_to_content_consistency float consistency of the meta title tag with the page content
measured from 0 to 1
                      meta_keywords_to_content_consistency float consistency of meta keywordstag with the page content
measured from 0 to 1
                  deprecated_tags array deprecated tags on the page
                  duplicate_meta_tags array duplicate meta tags on the page
                  spell object spellcheck
hunspell spellcheck errors
                      hunspell_language_code string spellcheck language code
                      misspelled array array of misspelled words
                          word string misspelled word
                  social_media_tags object object of social media tags found on the page
contains social media tags and their content
supported tags include but are not limited to Open Graph and Twitter card
              page_timing object object of page load metrics
                  time_to_interactive integer Time To Interactive (TTI) metric
the time it takes until the user can interact with a page (in milliseconds)
                  dom_complete integer time to load resources
the time it takes until the page and all of its subresources are downloaded (in milliseconds)
                  largest_contentful_paint float Core Web Vitals metric measuring how fast the largest above-the-fold content element is displayed
The amount of time (in milliseconds) to render the largest content element visible in the viewport, from when the user requests the URL. Learn more.
                  first_input_delay float Core Web Vitals metric indicating the responsiveness of a page
The time (in milliseconds) from when a user first interacts with your page to the time when the browser responds to that interaction. Learn more.
                  connection_time integer time to connect to a server
the time it takes until the connection with a server is established (in milliseconds)
                  time_to_secure_connection integer time to establish a secure connection
the time it takes until the secure connection with a server is established (in milliseconds)
                  request_sent_time integer time to send a request to a server
the time it takes until the request to a server is sent (in milliseconds)
                  waiting_time integer time to first byte (TTFB) in milliseconds
                  download_time integer time it takes for a browser to receive a response (in milliseconds)
                  duration_time integer total time it takes until a browser receives a complete response from a server (in milliseconds)
                  fetch_start integer time to start downloading the HTML resource
the amount of time the browser needs to start downloading a page
                  fetch_end integer time to complete downloading the HTML resource
the amount of time the browser needs to complete downloading a page
              onpage_score float shows how page is optimized on a 100-point scale
this field shows how page is optimized considering critical on-page issues and warnings detected;
100 is the highest possible score that means the page does not have any critical on-page issues and important warnings;
learn more about how the metric is calculated in this help center article
              total_dom_size integer total DOM size of a page
              custom_js_response string/object/integer the result of executing a specified JS script
note that you should specify a custom_js field when setting a task to receive this data and the field type and its value will totally depend on the script you specified;you can also filter the results by this value specifying filters in the following way:
["custom_js_response.url", "like", "pixel"]
              resource_errors object resource errors and warnings
                  errors array resource errors
                      line integer line where the error was found
                      column integer column where the error was found
                      message string text message of the error
the full list of possible HTML errors can be found here
                      status_code integer status code of the error
possible values:
0 — Unidentified Error;
501 — Html Parse Error;
1501 — JS Parse Error;
2501 — CSS Parse Error;
3501 — Image Parse Error;
3502 — Image Scale Is Zero;
3503 — Image Size Is Zero;
3504 — Image Format Invalid
                  warnings array resource warnings
                      line integer line the warning relates to
note that if "line": 0, the warning relates to the whole page
                      column integer column the warning relates to
note that if "column": 0, the warning relates to the whole page
                      message string text message of the warning
possible messages:
"Has node with more than 60 childs." – HTML page has at least 1 tag nesting over 60 tags of the same level
"Has more that 1500 nodes." – DOM tree contains over 1,500 elements
"HTML depth more than 32 tags." – DOM depth exceeds 32 nodes
                      status_code integer status code of the warning
possible values:
0 — Unidentified Warning;
1 — Has node with more than 60 childs;
2 — Has more that 1500 nodes;
3 — HTML depth more than 32 tags
              broken_resources boolean indicates whether a page contains broken resources
              broken_links boolean indicates whether a page contains broken links
              duplicate_title boolean indicates whether a page has duplicate title tags
              duplicate_description boolean indicates whether a page has a duplicate description
              duplicate_content boolean indicates whether a page has duplicate content
              click_depth integer number of clicks it takes to get to the page
indicates the number of clicks from the homepage needed before landing at the target page
              size integer resource size
indicates the size of a given page measured in bytes
              encoded_size integer page size after encoding
indicates the size of the encoded page measured in bytes
              total_transfer_size integer compressed page size
indicates the compressed size of a given page
              fetch_time string date and time when a resource was fetched
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
              cache_control object instructions for caching
                  cachable boolean indicates whether the page is cacheable
                  ttl integer time to live
the amount of time the browser caches a resource
              checks object website checks
on-page check-ups related to the page
                  no_content_encoding boolean page with no content encoding
indicates whether a page has no compression algorithm of the content
                  high_loading_time boolean page with high loading time
indicates whether a page loading time exceeds 3 seconds
                  is_redirect boolean page with redirects
indicates whether a page has 3XX redirects to other pages
                  is_4xx_code boolean page with 4xx status codes
indicates whether a page has 4xx response code
                  is_5xx_code boolean page with 5xx status codes
indicates whether a page has 5xx response code
                  is_broken boolean broken page
indicates whether a page returns a response code less than 200 or greater than 400
                  is_www boolean page with www
indicates whether a page is on a www subdomain
                  is_https boolean page with the https protocol
                  is_http boolean page with the http protocol
                  high_waiting_time boolean page with high waiting time
indicates whether a page waiting time (aka Time to First Byte) exceeds 1.5 seconds
                  has_micromarkup boolean page contains microdata markup</em>
indicates whether a page is without the <!DOCTYPE HTML> declaration
                  has_micromarkup_errors boolean page contains microdata markup errors
indicates whether a page is without the <!DOCTYPE HTML> declaration
                  no_doctype boolean page with no doctype
indicates whether a page is without the <!DOCTYPE HTML> declaration
                  has_html_doctype boolean page with HTML doctype declaration
if true, the page has HTML DOCTYPE declaration
                  canonical boolean page is canonical
                  no_encoding_meta_tag boolean page with no meta tag encoding
indicates whether a page is without Content-Type
informative only if the encoding is not explicit in the Content-Type header
for example: Content-Type: "text/html; charset=utf8"
                  no_h1_tag boolean page with empty or absent h1 tags
                  https_to_http_links boolean HTTPS page has links to HTTP pages
if true, this HTTPS page has links to HTTP pages
                  size_greater_than_3mb boolean page with size larger than 3 MB
if true, the page size is exceeding 3 MB
                  meta_charset_consistency boolean page with meta charset tag
if true, the page has meta charset tag that sets character encoding for this page
                  has_meta_refresh_redirect boolean pages with meta refresh redirect
if true, the page has <meta http-equiv=”refresh”> tag that instructs a browser to load another page after a specified time span
                  has_render_blocking_resources boolean page with render-blocking resources
if true, the page has render-blocking scripts or stylesheets
                  low_content_rate boolean page with low content rate
indicates whether a page has the plaintext size to page size ratio of less than 0.1
                  high_content_rate boolean page with high content rate
indicates whether a page has the plaintext size to page size ratio of more than 0.9
available for canonical pages only
                  low_character_count boolean indicates whether the page has less than 1024 characters
                  high_character_count boolean indicates whether the page has more than 256,000 characters
                  small_page_size boolean indicates whether a page is too small
the value will be true if a page size is smaller than 1024 bytes
                  large_page_size boolean indicates whether a page is too heavy
the value will be true if a page size exceeds 1 megabyte
                  low_readability_rate boolean page with a low readability rate
indicates whether a page is scored less than 15 points on the Flesch–Kincaid readability test
                  irrelevant_description boolean page with irrelevant description
indicates whether a page description tag is irrelevant to the content of a page
the relevance threshold is 0.2
available for canonical pages only
                  irrelevant_title boolean page with irrelevant title
indicates whether a page title tag is irrelevant to the content of the page
the relevance threshold is 0.3
available for canonical pages only
                  irrelevant_meta_keywords boolean page with irrelevant meta keywords
indicates whether a page keywords tags are irrelevant to the content of a page
the relevance threshold is 0.6
available for canonical pages only
                  title_too_long boolean page with a long title
indicates whether the content of the title tag exceeds 65 characters
                  has_meta_title boolean page has a meta title
indicates whether the HTML of a page contains the meta_title tag
                  title_too_short boolean page with short titles
indicates whether the content of title tag is shorter than 30 characters
                  deprecated_html_tags boolean page with deprecated tags
indicates whether a page has deprecated HTML tags
                  duplicate_meta_tags boolean page with duplicate meta tags
indicates whether a page has more than one meta tag of the same type
available for canonical pages only
                  duplicate_title_tag boolean page with more than one title tag
indicates whether a page has more than one title tag
                  no_image_alt boolean images without alt tags
                  no_image_title boolean images without title tags
                  no_description boolean pages with no description
indicates whether a page has an empty or absent description meta tag
available for canonical pages only
                  no_title boolean page with no title
indicates whether a page has an empty or absent title tag
                  no_favicon boolean page with no favicon
                  seo_friendly_url boolean page with seo-frienldy URL
the ‘SEO-friendliness’ of a page URL is checked by four parameters:
– the length of the relative path is less than 120 characters
– no special characters
– no dynamic parameters
– relevance of the URL to the page
if at least one of them is failed then such URL is considered as not ‘SEO-friendly’
the data is available for canonical pages only
                  flash boolean page with flash
indicates whether a page has flash elements
                  frame boolean page with frames
indicates whether a page contains frame, iframe, frameset tags
                  lorem_ipsum boolean page with lorem ipsum
indicates whether a page has lorem ipsum content
                  has_misspelling boolean page with misspelling
indicates whether a page has spelling mistakes
informative if the check_spell was set to true in the POST array
                  seo_friendly_url_characters_check boolean URL characters check-up
indicates whether a page URL containing only uppercase and lowercase Latin characters, digits and dashes
                  seo_friendly_url_dynamic_check boolean URL dynamic check-up
the value will be true if a page has no dynamic parameters in the url
                  seo_friendly_url_keywords_check boolean URL keyword check-up
indicates whether a page URL is consistent with the title meta tag
                  seo_friendly_url_relative_length_check boolean URL length check-up
the value will be true if a page URL no longer than 120 characters
              content_encoding string type of encoding
              media_type string types of media used to display a page
              server string server version
              is_resource boolean indicates whether a page is a single resource
              url_length integer page URL length in characters
              relative_url_length integer relative URL length in characters
              last_modified object contains data on changes related to the resource
if there is no data, the value will be null
                  header string date and time when the header was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                 sitemap string date and time when the sitemap was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                  meta_tag string date and time when the meta tag was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
              ‘broken’ page
              resource_type string type of the returned resource = ‘broken’
              status_code integer status code of the page
              location string location header
indicates the URL to redirect a page to
              url string page URL
              size integer resource size
indicates the size of a given page measured in bytes
              encoded_size integer page size after encoding
indicates the size of the encoded page measured in bytes
              total_transfer_size integer compressed page size
indicates the compressed size of a given page
              fetch_time string date and time when a resource was fetched
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
              fetch_timing object time range within which a result was fetched
                  duration_time integer indicates how many seconds it took to download a page
                  fetch_start integer time to start downloading the HTML resource
the amount of time the browser needs to start downloading a page
                  fetch_end integer time to complete downloading the HTML resource
the amount of time the browser needs to complete downloading a page
              cache_control object instructions for caching
                  cachable boolean indicates whether the page is cacheable
                  ttl integer time to live
the amount of time the browser caches a resource
              checks object on-page check-ups
                  no_content_encoding boolean page with no content encoding
indicates whether a page has no compression algorithm of the content
                  high_loading_time boolean page with high loading time
indicates whether a page loading time exceeds 3 seconds
                  is_redirect boolean page with redirects
indicates whether a page has 3XX redirects to other pages
                  is_4xx_code boolean page with with 4xx status code
indicates whether a page has 4XX response code
                  is_5xx_code boolean page with 5xx status code
indicates whether a page has 5XX response code
                  is_broken boolean broken page
indicates whether a page returns a response code less than 200 or greater than 400
                  is_www boolean page with www
indicates whether a page is on a www subdomain
                  is_https boolean page with the https protocol
                  is_http boolean page with the http protocol
              resource_errors object resource errors and warnings
                  errors array resource errors
                      line integer line where the error was found
                      column integer column where the error was found
                      message string text message of the error
the full list of possible HTML errors can be found here
                      status_code integer status code of the error
possible values:
0 — Unidentified Error;
501 — Html Parse Error;
1501 — JS Parse Error;
2501 — CSS Parse Error;
3501 — Image Parse Error;
3502 — Image Scale Is Zero;
3503 — Image Size Is Zero;
3504 — Image Format Invalid
                  warnings array resource warnings
                      line integer line the warning relates to
note that if "line": 0, the warning relates to the whole page
                      column integer columnthe warning relates to
note that if "column": 0, the warning relates to the whole page
                      message string text message of the warning
possible messages:
"Has node with more than 60 childs." – HTML page has at least 1 tag nesting over 60 tags of the same level
"Has more that 1500 nodes." – DOM tree contains over 1,500 elements
"HTML depth more than 32 tags." – DOM depth exceeds 32 nodes
                      status_code integer status code of the warning
possible values:
0 — Unidentified Warning;
1 — Has node with more than 60 childs;
2 — Has more that 1500 nodes;
3 — HTML depth more than 32 tags
              content_encoding string type of encoding
              media_type string types of media used to display a page
example: "text/html"
              server string server version
              is_resource boolean indicates whether a page is a single resource
              last_modified object contains data on changes related to the resource
if there is no data, the value will be null
                  header string date and time when the header was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                 sitemap string date and time when the sitemap was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                  meta_tag string date and time when the meta tag was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
              ‘redirect’ page
              resource_type string type of the returned resource = ‘redirect’
              status_code integer status code of the page
              location string location header
target URL for “redirect” resources
              url string page url
source URL for “redirect” resources
              size integer resource size
indicates the size of a given page measured in bytes
equals 0 for “redirect” resources
              encoded_size integer page size after encoding
equals 0 for “redirect” resources
              total_transfer_size integer compressed page size
indicates the compressed size of a given page
              fetch_time string date and time when a resource was fetched
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
              fetch_timing object time range within which a result was fetched
                  duration_time integer indicates how many seconds it took to download a page
                  fetch_start integer time to start downloading the HTML resource
the amount of time the browser needs to start downloading a page
                  fetch_end integer time to complete downloading the HTML resource
the amount of time the browser needs to complete downloading a page
              resource_errors object resource errors and warnings
                  errors array resource errors
                      line integer line where the error was found
                      column integer column where the error was found
                      message string text message of the error
the full list of possible HTML errors can be found here
                      status_code integer status code of the error
possible values:
0 — Unidentified Error;
501 — Html Parse Error;
1501 — JS Parse Error;
2501 — CSS Parse Error;
3501 — Image Parse Error;
3502 — Image Scale Is Zero;
3503 — Image Size Is Zero;
3504 — Image Format Invalid
                  warnings array resource warnings
                      line integer line the warning relates to
note that if "line": 0, the warning relates to the whole page
                      column integer column the warning relates to
note that if "column": 0, the warning relates to the whole page
                      message string text message of the warning
possible messages:
"Has node with more than 60 childs." – HTML page has at least 1 tag nesting over 60 tags of the same level
"Has more that 1500 nodes." – DOM tree contains over 1,500 elements
"HTML depth more than 32 tags." – DOM depth exceeds 32 nodes
                      status_code integer status code of the warning
possible values:
0 — Unidentified Warning;
1 — Has node with more than 60 childs;
2 — Has more that 1500 nodes;
3 — HTML depth more than 32 tags
              cache_control object instructions for caching
                  cachable boolean indicates whether the page is cacheable
                  ttl integer time to live
the amount of time the browser caches a resource
              checks object on-page check-ups
                  no_content_encoding boolean page with no content encoding
indicates whether a page has no compression algorithm of the content
                  high_loading_time boolean page with high loading time
indicates whether a page loading time exceeds 3 seconds
                  is_redirect boolean page with redirects
indicates whether a page has 3XX redirects to other pages
                  is_4xx_code boolean page with 4xx status codes
indicates whether a page has 4xx response code
                  is_5xx_code boolean page with 5xx status codes
indicates whether a page has 5xx response code
                  is_broken boolean broken page
indicates whether a page returns a response code less than 200 or greater than 400
                  is_www boolean page with www
indicates whether a page is on a www subdomain
                  is_https boolean page with the https protocol
                  is_http boolean page with the http protocol
              content_encoding string type of encoding
              media_type string types of media used to display a page
example: "text/html"
              server string server version
              is_resource boolean indicates whether a page is a single resource
              last_modified object contains data on changes related to the resource
if there is no data, the value will be null
                  header string date and time when the header was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                 sitemap string date and time when the sitemap was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                  meta_tag string date and time when the meta tag was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
              resources Note: the following types of resources will be displayed only if the first URL to crawl is a script, image, or stylesheet
                resource_type string type of the returned resource
possible types: script, image, stylesheet
                meta object resource properties
available only for items with the following resource_type: image
                    alternative_text string content of the image alt attribute
                    title string title
                    original_width integer original image width in px
                    original_height integer original image height in px
                    width integer image width in px
                    height integer image height in px
                status_code integer status code of the page where a given resource is located
                location string location header
indicates the URL to redirect a page to
                url string resource URL
                size integer resource size
indicates the size of a given resource measured in bytes
                encoded_size integer resource size after encoding
indicates the size of the encoded resource measured in bytes
                total_transfer_size integer compressed resource size
indicates the compressed size of a given resource in bytes
                fetch_time string date and time when a resource was fetched
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2021-02-17 13:54:15 +00:00
                fetch_timing object resource fetching time range
                    duration_time integer indicates how many milliseconds it took to fetch a resource
                   fetch_start integer time to start downloading the resource
the amount of time a browser needs to start downloading a resource
                    fetch_end integer time to complete downloading the resource
the amount of time a browser needs to complete downloading a resource
                cache_control object instructions for caching
                   cachable boolean indicates whether the resource is cacheable
                   ttl integer time to live
the amount of time it takes for the browser to cache a resource; measured in milliseconds
                checks object resource check-ups
contents of the array depend on the resource_type
                    no_content_encoding boolean resource with no content encoding
indicates whether a page has no compression algorithm of the content;
                    high_loading_time boolean resource with high loading time
indicates whether a resource loading time exceeds 3 seconds;
                    is_redirect boolean resource with redirects
indicates whether a page with a resource has 3XX redirects to other pages;
                    is_4xx_code boolean resource with 4xx status codes
indicates whether a resource has 4xx response code
                    is_5xx_code boolean resource with 5xx status codes
indicates whether a resource has 5xx response code
                    is_broken boolean broken resource
indicates whether a page with this resource returns 4xx, 5xx response codes or has broken elements inside the resource
                    is_www boolean page with www
indicates whether a page with this resource is on a www subdomain
                    is_https boolean page with the https protocol
                    is_http boolean page with the http protocol
                    is_minified boolean resource is minified
indicates whether the content of a stylesheet or script is minified;
available for items with the following resource_type: stylesheet, script
                    has_redirect boolean resource has a redirect
available for items with the following resource_type: script, image;
if the resource_type is image, this field will indicate whether other pages and/or resources have redirects pointing at the image;
if the resource_type is script, this field will indicate whether the script contains a redirect
                    has_subrequests boolean resource contains subrequests
indicates whether the content of a stylesheet or script contain additional requests;
available for items with the following resource_type: stylesheet, script
                    original_size_displayed boolean image desplayes in its original size
indicates whether the image is displayed in its original size;
available only for items with the following resource_type: image
              resource_errors object resource errors and warnings
                  errors array resource errors
                      line integer line where the error was found
                      column integer column where the error was found
                      message string text message of the error
the full list of possible HTML errors can be found here
                      status_code integer status code of the error
possible values:
0 — Unidentified Error;
501 — Html Parse Error;
1501 — JS Parse Error;
2501 — CSS Parse Error;
3501 — Image Parse Error;
3502 — Image Scale Is Zero;
3503 — Image Size Is Zero;
3504 — Image Format Invalid
                  warnings array resource warnings
                      line integer line the warning relates to
note that if "line": 0, the warning relates to the whole page
                      column integer column the warning relates to
note that if "column": 0, the warning relates to the whole page
                      message string text message of the warning
possible messages:
"Has node with more than 60 childs." – HTML page has at least 1 tag nesting over 60 tags of the same level
"Has more that 1500 nodes." – DOM tree contains over 1,500 elements
"HTML depth more than 32 tags." – DOM depth exceeds 32 nodes
                      status_code integer status code of the warning
possible values:
0 — Unidentified Warning;
1 — Has node with more than 60 childs;
2 — Has more that 1500 nodes;
3 — HTML depth more than 32 tags
              content_encoding string type of encoding
              media_type string types of media used to display a resource
              accept_type string indicates the expected type of resource
for example, if "resource_type": "broken", accept_type will indicate the type of the broken resource
possible values:
any, none, image, sitemap, robots, script, stylesheet, redirect, html, text, other, font
              server string server version
              last_modified object contains data on changes related to the resource
if there is no data, the value will be null
                  header string date and time when the header was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                 sitemap string date and time when the sitemap was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null
                  meta_tag string date and time when the meta tag was last modified
in the UTC format: “yyyy-mm-dd hh-mm-ss +00:00”
example:
2019-11-15 12:57:46 +00:00
if there is no data, the value will be null

‌‌