This endpoint returns a list of crawled pages with on-page check-ups and other metrics related to the page performance.
Using this function you will get page-specific data with detailed information on how well your pages are optimized for search.
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)" \
curl --location --request POST "https://api.dataforseo.com/v3/on_page/pages" \
--header "Authorization: Basic ${cred}" \
--header "Content-Type: application/json" \
--data-raw "[
{
"id": "07281559-0695-0216-0000-c269be8b7592",
"filters": [
["resource_type", "=", "html"],
"and",
["meta.scripts_count", ">", 40]
],
"order_by": ["meta.content.plain_text_word_count,desc"],
"limit": 10
}
]"
<?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-access
$client = new RestClient($api_url, null, 'login', 'password');
$post_array = array();
// simple way to get a result
$post_array[] = array(
"id" => "07281559-0695-0216-0000-c269be8b7592",
"filters" => [
["resource_type", "=", "html"],
"and",
["meta.scripts_count", ">", 40]
],
"order_by" => ["meta.content.plain_text_word_count,desc"],
"limit" => 10
);
try {
// POST /v3/on_page/pages
// the full list of possible parameters is available in documentation
$result = $client->post('/v3/on_page/pages', $post_array);
print_r($result);
// do something with post 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;
?>
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")
post_data = dict()
# simple way to get a result
post_data[len(post_data)] = dict(
id="07281559-0695-0216-0000-c269be8b7592",
filters=[
["resource_type", "=", "html"],
"and",
["meta.scripts_count", ">", 40]
],
order_by=["meta.content.plain_text_word_count,desc"],
limit=10
)
# POST /v3/on_page/pages
# the full list of possible parameters is available in documentation
response = client.post("/v3/on_page/pages", post_data)
# 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.Collections.Generic;
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_pages()
{
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"))) }
};
var postData = new List<object>();
// simple way to get a result
postData.Add(new
{
id = "07291316-0696-0216-1000-ce5782824ea4",
filters = new object[]
{
new object[] { "resource_type", "=", "html" },
"and",
new object[] { "meta.scripts_count", ">", 40 }
},
order_by = new object[] { "meta.content.plain_text_word_count,desc" },
limit = 10
});
// POST /v3/on_page/pages
// the full list of possible parameters is available in documentation
var taskPostResponse = await httpClient.PostAsync("/v3/on_page/pages", new StringContent(JsonConvert.SerializeObject(postData)));
var result = JsonConvert.DeserializeObject<dynamic>(await taskPostResponse.Content.ReadAsStringAsync());
// you can find the full list of the response codes here https://docs.dataforseo.com/v3/appendix/errors
if (result.status_code == 20000)
{
// do something with result
Console.WriteLine(result);
}
else
Console.WriteLine($"error. Code: {result.status_code} Message: {result.status_message}");
}
}
}
The above command returns JSON structured like this:
{
"version": "0.1.20220627",
"status_code": 20000,
"status_message": "Ok.",
"time": "0.8376 sec.",
"cost": 0,
"tasks_count": 1,
"tasks_error": 0,
"tasks": [
{
"id": "06281251-1535-0216-0000-fdebbdd9eba5",
"status_code": 20000,
"status_message": "Ok.",
"time": "0.8019 sec.",
"cost": 0,
"result_count": 1,
"path": [
"v3",
"on_page",
"pages"
],
"data": {
"api": "on_page",
"function": "pages",
"filters": [
"resource_type",
"=",
"html"
],
"limit": 3,
"target": "dataforseo.com",
"max_crawl_pages": 10,
"store_raw_html": true,
"support_cookies": true,
"load_resources": true
},
"result": [
{
"crawl_progress": "finished",
"crawl_status": {
"max_crawl_pages": 10,
"pages_in_queue": 0,
"pages_crawled": 10
},
"total_items_count": 10,
"items_count": 3,
"items": [
{
"resource_type": "html",
"status_code": 200,
"location": null,
"url": "https://dataforseo.com/",
"meta": {
"title": "Powerful API Stack For Data-Driven SEO Tools – DataForSEO",
"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",
"We will assist you during the whole process of implementation. We can make Skype call or group chat. Any communication channel that will satisfy your needs.",
"APIs",
"Databases",
"Solutions",
"Knowledge Base",
"Resources",
"Legal information",
"Payment Methods:"
],
"h1": [
"Powerful API Stack For\nData-Driven Marketers"
],
"h2": [
"Our APIs",
"Need Any Help? Our 5-Star Support Will Help You.",
"Benefits",
"Insights",
"DataForSEO – the best data provider for SEO-software companies and agencies",
"Reviews",
"DataForSEO in Figures",
"Questions & Answers",
"Our happy customers"
],
"h5": [
"Simple pricing",
"Tech Support",
"Clear stats",
"High speed",
"Availability",
"Accuracy and freshness",
"Predictable pricing",
"Introduction to APIs for SEO software",
"Why You Must Build Your Own SEO Software (If You Haven’t Yet)",
"Development of SEO Tools. Where to Start?"
]
},
"description": "We provide comprehensive data solutions for SEO and SEM analytics via API. DataForSEO is a trusted partner for 750+ SEO software companies and agencies.",
"favicon": "https://dataforseo.com/wp-content/uploads/2022/04/cropped-favicon_512-32x32.png",
"meta_keywords": null,
"canonical": "https://dataforseo.com/",
"internal_links_count": 70,
"external_links_count": 38,
"inbound_links_count": 11,
"images_count": 11,
"images_size": 5292,
"scripts_count": 46,
"scripts_size": 1789111,
"stylesheets_count": 31,
"stylesheets_size": 1696169,
"title_length": 57,
"description_length": 152,
"render_blocking_scripts_count": 23,
"render_blocking_stylesheets_count": 0,
"cumulative_layout_shift": 0,
"meta_title": null,
"content": {
"plain_text_size": 9108,
"plain_text_rate": 0.03768214276848734,
"plain_text_word_count": 1538,
"automated_readability_index": 11.117851738638478,
"coleman_liau_readability_index": 10.883198959687903,
"dale_chall_readability_index": 7.705054991302585,
"flesch_kincaid_readability_index": 49.14068675797546,
"smog_readability_index": 19.778111272854503,
"description_to_content_consistency": 0.8095238208770752,
"title_to_content_consistency": 1,
"meta_keywords_to_content_consistency": null
},
"deprecated_tags": null,
"duplicate_meta_tags": [
"generator"
],
"spell": null,
"social_media_tags": {
"og:locale": "en_US",
"og:type": "website",
"og:title": "Powerful API Stack For Data-Driven SEO Tools – DataForSEO",
"og:description": "We provide comprehensive data solutions for SEO and SEM analytics via API. DataForSEO is a trusted partner for 750+ SEO software companies and agencies.",
"og:url": "https://dataforseo.com",
"og:site_name": "DataForSEO",
"og:updated_time": "2022-05-28T14:18:10+03:00",
"article:published_time": "2016-07-21T16:24:26+03:00",
"article:modified_time": "2022-05-28T14:18:10+03:00",
"og:video": "https://www.youtube.com/embed/SoZMBkkVv4E",
"video:duration": "69",
"ya:ovs:upload_date": "2018-09-03",
"ya:ovs:allow_embed": "true",
"twitter:card": "summary_large_image",
"twitter:title": "Powerful API Stack For Data-Driven SEO Tools – DataForSEO",
"twitter:description": "We provide comprehensive data solutions for SEO and SEM analytics via API. DataForSEO is a trusted partner for 750+ SEO software companies and agencies.",
"twitter:label1": "Written by",
"twitter:data1": "admin",
"twitter:label2": "Time to read",
"twitter:data2": "23 minutes"
}
},
"page_timing": {
"time_to_interactive": 812,
"dom_complete": 812,
"largest_contentful_paint": 0,
"first_input_delay": 0,
"connection_time": 13,
"time_to_secure_connection": 17,
"request_sent_time": 0,
"waiting_time": 0,
"download_time": 5,
"duration_time": 35,
"fetch_start": 0,
"fetch_end": 35
},
"onpage_score": 98.17,
"total_dom_size": 3731747,
"custom_js_response": null,
"custom_js_client_exception": null,
"resource_errors": {
"errors": null,
"warnings": [
{
"line": 4,
"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": 241785,
"encoded_size": 0,
"total_transfer_size": 0,
"fetch_time": "2022-06-28 12:51:45 +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,
"has_micromarkup": false,
"has_micromarkup_errors": 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,
"redirect_chain": 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,
"recursive_canonical": false,
"canonical_chain": false,
"canonical_to_redirect": false,
"canonical_to_broken": false,
"has_links_to_redirects": false,
"is_orphan_page": false,
"is_link_relation_conflict": false
},
"content_encoding": "br",
"media_type": "text/html",
"server": "cloudflare",
"is_resource": false,
"url_length": 23,
"relative_url_length": 1,
"last_modified": {
"header": null,
"sitemap": null,
"meta_tag": "2022-05-28 11:18:10 +00:00"
}
},
{
"resource_type": "html",
"status_code": 200,
"location": null,
"url": "https://dataforseo.com/apis",
"meta": {
"title": "DataForSEO APIs – Powerful Data Solutions for SEO and SEM",
"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",
"Build rank tracking and SEO competitor analysis tools faster using the most comprehensive source of real-time SERP data.",
"Get a complete, real-time overview of Google, Bing, and Yahoo SERPs for any location and language.",
"Learn more about DataForSEO SERP Database, a full-fledged on-premises solution for in-house SEO analytics and enterprise-grade reporting",
"Get search volume, impressions, CPC, and other essential keyword data from Google Ads and Bing Ads APIs.",
"Eliminate the guesswork with a systhesis of market research and SEO data using Google Trends API.",
"DataForSEO Backlinks API features nine endpoints that can provide all the data you, or your users, need to facilitate the process of analysing backlinks.",
"DataForSEO Labs API encompasses the power of industry-leading infrastructure and sophisticated data-mining algorithms into a comprehensive, integration-ready source of SEO data.",
"From inbound and broken links to duplicate content and page speed insights – you will get everything you need to build an innovative and effective solution.",
"Analyze any website for 100+ advanced on-page SEO parameters and get comprehensive insights in real-time.",
"Get information about the products in Amazon and Google Shopping search results for any location and language.",
"Compare product prices and specifications in different stores and fetch a list of product modifications – we have all the data you need to take your ecommerce analytics to a whole new level.",
"Find out what customers are saying about any local establishment with real-time data collected from Google Reviews and Yelp.",
"Get access to structured data on customer reviews, including their natural language text, rating, as well as specific details about the time of submission and the reviewer’s profile.",
"With DataForSEO you can build your SEO tool exactly the way you want, without having to think about the proxies, networks and creating parsers for hundreds of constantly changing variables.",
"APIs",
"Databases",
"Solutions",
"Knowledge Base",
"Resources",
"Legal information",
"Payment Methods:"
],
"h1": [
"DataForSEO APIs"
],
"h2": [
"All the data for your SEO tool in one place",
"DataForSEO APIs in Figures",
"SERP API",
"Keyword Data API",
"Merchant API Amazon response examples",
"Backlinks API",
"DataForSEO Labs API",
"On-Page API",
"Merchant API",
"Business Data API",
"Jumpstart your journey with DataForSEO APIs",
"Data industry leaders trust",
"Solutions developers praise"
],
"h3": [
"Your one-stop datasource of structured SERP data",
"Google SERP API",
"Bing SERP API",
"Yahoo SERP API",
"Baidu SERP API",
"Need an on-premises solution?",
"Go beyond limitations with Google Ads, Bing Ads, and Google Trends data",
"Google Ads API",
"Google Trends API",
"Bing Ads API",
"Keyword data on local storage?",
"Empower your tool’s capabilities with the accurate and up-to-date backlink data",
"Backlinks",
"Relevant Domains",
"Links Intersection",
"Your Ultimate Datasource of Advanced Search Analytics",
"Keyword Research",
"Market-specific keyword data",
"Competitor intelligence data",
"Srart yout unlimited free trial today!",
"Scale up your on-page SEO analytics",
"Power-up your ecommerce business with product and pricing data from Google Shopping and Amazon",
"Collect customer feedback at scale and automate customer sentiment analysis",
"DataForSEO Knowledge Hub",
"DataForSEO API Documentation",
"DataForSEO White Papers",
"See for yourself why industry leaders choose DataForSEO"
]
},
"description": "Explore our data suite and find the best API for your SEO and SEM analytics",
"favicon": "https://dataforseo.com/wp-content/uploads/2022/04/cropped-favicon_512-32x32.png",
"meta_keywords": null,
"canonical": "https://dataforseo.com/apis",
"internal_links_count": 72,
"external_links_count": 44,
"inbound_links_count": 11,
"images_count": 13,
"images_size": 6364,
"scripts_count": 44,
"scripts_size": 1809398,
"stylesheets_count": 32,
"stylesheets_size": 1440969,
"title_length": 57,
"description_length": 75,
"render_blocking_scripts_count": 23,
"render_blocking_stylesheets_count": 0,
"cumulative_layout_shift": 0,
"meta_title": null,
"content": {
"plain_text_size": 12129,
"plain_text_rate": 0.052246167365206264,
"plain_text_word_count": 1917,
"automated_readability_index": 15.52626791049326,
"coleman_liau_readability_index": 13.60730307772561,
"dale_chall_readability_index": 8.647992293152857,
"flesch_kincaid_readability_index": 33.88912871166394,
"smog_readability_index": 22.65993575924352,
"description_to_content_consistency": 0.8571428656578064,
"title_to_content_consistency": 0.8888888955116272,
"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 APIs – Powerful Data Solutions for SEO and SEM",
"og:description": "Explore our data suite and find the best API for your SEO and SEM analytics",
"og:url": "https://dataforseo.com/apis",
"og:site_name": "DataForSEO",
"og:updated_time": "2022-05-18T12:29:22+03:00",
"twitter:card": "summary_large_image",
"twitter:title": "DataForSEO APIs – Powerful Data Solutions for SEO and SEM",
"twitter:description": "Explore our data suite and find the best API for your SEO and SEM analytics",
"twitter:label1": "Time to read",
"twitter:data1": "38 minutes"
}
},
"page_timing": {
"time_to_interactive": 602,
"dom_complete": 602,
"largest_contentful_paint": 0,
"first_input_delay": 0,
"connection_time": 12,
"time_to_secure_connection": 18,
"request_sent_time": 0,
"waiting_time": 0,
"download_time": 5,
"duration_time": 35,
"fetch_start": 0,
"fetch_end": 35
},
"onpage_score": 98.17,
"total_dom_size": 3488044,
"custom_js_response": null,
"custom_js_client_exception": null,
"resource_errors": {
"errors": null,
"warnings": [
{
"line": 4,
"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": 1,
"size": 232228,
"encoded_size": 0,
"total_transfer_size": 0,
"fetch_time": "2022-06-28 12:51:48 +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,
"has_micromarkup": false,
"has_micromarkup_errors": 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,
"redirect_chain": 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,
"recursive_canonical": false,
"canonical_chain": false,
"canonical_to_redirect": false,
"canonical_to_broken": false,
"has_links_to_redirects": false,
"is_orphan_page": false,
"is_link_relation_conflict": false
},
"content_encoding": "br",
"media_type": "text/html",
"server": "cloudflare",
"is_resource": false,
"url_length": 23,
"relative_url_length": 1,
"last_modified": null
},
{
"resource_type": "html",
"status_code": 200,
"location": null,
"url": "https://dataforseo.com/apis/serp-api",
"meta": {
"title": "SERP API – Structured Search Results Data",
"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",
"Moving a product to the market or integrating a new data source can take a lot of time and money. We accelerate this process by providing everything you need to build an efficient product.",
"APIs",
"Databases",
"Solutions",
"Knowledge Base",
"Resources",
"Legal information",
"Payment Methods:"
],
"h1": [
"SERP API"
],
"h2": [
"Available search engines",
"Get actionable SERP data hassle-free",
"Build up the product, not expenses",
"All the data you need, under one roof",
"The most comprehensive reflection of SERP at your fingertips",
"Release in days, not weeks",
"Business benefits",
"Reviews",
"Insights, trends and related articles",
"SERP API in figures",
"SERP API Pricing",
"SERP API response examples",
"Questions and answers"
],
"h5": [
"Google SERP",
"Google Images",
"Google News",
"Google Maps",
"Yahoo SERP",
"Bing SERP",
"Baidu SERP",
"Pay-as-you-go pricing model",
"No bureaucracy",
"24/7 support",
"SLA",
"Custom solutions"
],
"h3": [
"Start your unlimited free trial",
"All major search engines supported",
"Advanced SERP features",
"Google vertical search",
"Device and OS",
"Сhoose the format that’s right for you",
"All locations supported",
"Location-specific results",
"100% accuracy",
"Real-time results",
"Didn’t find the feature you were looking for?",
"Want to discuss your use case?",
"If you need any assistance with DataForSEO APIs integration into your system, or looking for best practices to implement in your solution, we’re always happy to help!",
"Making your first call to SERP API",
"SERP API Use Cases",
"Google SERP extra elements",
"Live priority",
"High priority",
"Standard priority",
"Want to discuss individual pricing or custom solutions?"
]
},
"description": "Eliminate the challenges of web scraping and proxy rotation. Collect search results data in HTML or JSON from Google, Bing, and other SE using SERP API.",
"favicon": "https://dataforseo.com/wp-content/uploads/2022/04/cropped-favicon_512-32x32.png",
"meta_keywords": null,
"canonical": "https://dataforseo.com/apis/serp-api",
"internal_links_count": 76,
"external_links_count": 41,
"inbound_links_count": 11,
"images_count": 23,
"images_size": 892451,
"scripts_count": 45,
"scripts_size": 1780216,
"stylesheets_count": 30,
"stylesheets_size": 1644289,
"title_length": 41,
"description_length": 152,
"render_blocking_scripts_count": 23,
"render_blocking_stylesheets_count": 0,
"cumulative_layout_shift": 0,
"meta_title": null,
"content": {
"plain_text_size": 10386,
"plain_text_rate": 0.038073382724376714,
"plain_text_word_count": 1773,
"automated_readability_index": 10.176452043815122,
"coleman_liau_readability_index": 10.42210941906373,
"dale_chall_readability_index": 7.42693346632232,
"flesch_kincaid_readability_index": 52.67396152818597,
"smog_readability_index": 18.965066093208936,
"description_to_content_consistency": 0.7599999904632568,
"title_to_content_consistency": 1,
"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": "SERP API – Structured Search Results Data",
"og:description": "Eliminate the challenges of web scraping and proxy rotation. Collect search results data in HTML or JSON from Google, Bing, and other SE using SERP API.",
"og:url": "https://dataforseo.com/apis/serp-api",
"og:site_name": "DataForSEO",
"og:updated_time": "2022-03-08T15:50:15+03:00",
"twitter:card": "summary_large_image",
"twitter:title": "SERP API – Structured Search Results Data",
"twitter:description": "Eliminate the challenges of web scraping and proxy rotation. Collect search results data in HTML or JSON from Google, Bing, and other SE using SERP API.",
"twitter:label1": "Time to read",
"twitter:data1": "39 minutes"
}
},
"page_timing": {
"time_to_interactive": 573,
"dom_complete": 817,
"largest_contentful_paint": 0,
"first_input_delay": 0,
"connection_time": 12,
"time_to_secure_connection": 19,
"request_sent_time": 0,
"waiting_time": 0,
"download_time": 5,
"duration_time": 36,
"fetch_start": 0,
"fetch_end": 36
},
"onpage_score": 98.17,
"total_dom_size": 4588911,
"custom_js_response": null,
"custom_js_client_exception": null,
"resource_errors": {
"errors": null,
"warnings": [
{
"line": 4,
"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": 1,
"size": 272881,
"encoded_size": 0,
"total_transfer_size": 0,
"fetch_time": "2022-06-28 12:51:50 +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,
"has_micromarkup": false,
"has_micromarkup_errors": 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,
"redirect_chain": 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,
"recursive_canonical": false,
"canonical_chain": false,
"canonical_to_redirect": false,
"canonical_to_broken": false,
"has_links_to_redirects": false,
"is_orphan_page": false,
"is_link_relation_conflict": false
},
"content_encoding": "br",
"media_type": "text/html",
"server": "cloudflare",
"is_resource": false,
"url_length": 23,
"relative_url_length": 1,
"last_modified": null
}
]
}
]
}
]
}
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.
Description of the fields for setting a task:
Field name
Type
Description
id
string
ID of the task required field
you can get this ID in the response of the Task POST endpoint
example:
“07131248-1535-0216-1000-17384017ad04”
limit
integer
the maximum number of returned pages
optional field
default value: 100
maximum value: 1000
offset
integer
offset in the results array of returned pages
optional field
default value: 0
if you specify the 10 value, the first ten pages in the results array will be omitted and the data will be provided for the successive pages
filters
array
array of results filtering parameters
optional field you can add several filters at once (8 filters maximum)
you should set a logical operator and, or between the conditions
the following operators are supported: regex, not_regex, <, <=, >, >=, =, <>, in, not_in, like, not_like
you can use the % operator with like and not_like to match any string of zero or more characters
example: ["meta.external_links_count","<=",50]["url","like","https://dataforseo.com/apis/dataforseo-labs-api"][["checks.high_waiting_time","=",false],
"and",["resource_type","=","html"]][["page_timing.duration_time","<",100],"and",[["checks.large_page_size","=",false],"or",["checks.high_waiting_time","=",false]]]The full list of possible filters is available by this link.
order_by
array
results sorting rules
optional field
you can use the same values as in the filters array to sort the results
possible sorting types: asc – results will be sorted in the ascending order desc – results will be sorted in the descending order
you should use a comma to set up a sorting type
example: ["meta.external_links_count,desc"] note that you can set no more than three sorting rules in a single request
you should use a comma to separate several sorting rules
example: ["page_timing.dom_complete,asc","size,desc"]
tag
string
user-defined task identifier
optional field the character limit is 255
you can use this parameter to identify the task and match it with the result
you will find the specified tag value in the data object of the response
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
max_crawl_pages
integer
maximum number of pages to crawl
indicates the max_crawl_pages limit you specified when setting a task
pages_in_queue
integer
number of pages that are currently in the crawling queue
pages_crawled
integer
number of crawled pages
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
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
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)
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
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"]
custom_js_client_exception
string
error when executing a custom js
if the error occurred when executing the script you specified in the custom_js field, the error message would be displayed here
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
page with no doctype
indicates whether a page is without the <!DOCTYPE HTML> 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
has_html_doctype
boolean
page with HTML doctype declaration
if true, the page has HTML DOCTYPE declaration
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
redirect_chain
boolean
page with multiple redirects
if true, there were at least two redirects before our crawler reached this page
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
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
is_orphan_page
boolean
page with no internal links pointing to it true if the page has no reference from other pages of the domain Note: to use this field, set the respect_sitemap parameter in the POST request to true
is_link_relation_conflict
boolean
mix of both followed and nofollowed incoming internal links true if the page receives at least one link with the rel="nofollow" attribute and at least one dofollow link
has_links_to_redirects
boolean
page is pointing to a page that redirect elsewhere true if the page is pointing to a page that responds with a 3XX redirect
canonical_chain
boolean
pages with canonical pointing to a page that has a canonical pointing elsewhere true if the page has a canonical link element pointing to a page that has a canonical pointing to a different page
e.g. page a is canonicalized to page b, which is canonicalized to page c
canonical_to_redirect
boolean
canonical page pointing to a page that redirects elsewhere true if the page has a canonical link element pointing to a page that responds with a 3XX redirect
canonical_to_broken
boolean
canonical link pointing to a broken page true if the page has a a canonical link pointing to a page that responds with a 4xx or 5xx response codes
recursive_canonical
boolean
recursive canonical error true if the page contains rel="canonical" tag to another page, which in turn, refers back to the initial page
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
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
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
is_orphan_page
boolean
page with no internal links pointing to it true if the page has no reference from other pages of the domain Note: to use this field, set the respect_sitemap parameter in the POST request to true
is_link_relation_conflict
boolean
mix of both followed and nofollowed incoming internal links true if the page receives at least one link with the rel="nofollow" attribute and at least one dofollow link
has_links_to_redirects
boolean
page is pointing to a page that redirect elsewhere true if the page is pointing to a page that responds with a 3XX redirect
canonical_chain
boolean
pages with canonical pointing to a page that has a canonical pointing elsewhere true if the page has a canonical link element pointing to a page that has a canonical pointing to a different page
e.g. page a is canonicalized to page b, which is canonicalized to page c
canonical_to_redirect
boolean
canonical page pointing to a page that redirects elsewhere true if the page has a canonical link element pointing to a page that responds with a 3XX redirect
canonical_to_broken
boolean
canonical link pointing to a broken page true if the page has a canonical link pointing to a page that responds with a 4xx or 5xx response codes
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
is_orphan_page
boolean
page with no internal links pointing to it true if the page has no reference from other pages of the domain Note: to use this field, set the respect_sitemap parameter in the POST request to true
is_link_relation_conflict
boolean
mix of both followed and nofollowed incoming internal links true if the page receives at least one link with the rel="nofollow" attribute and at least one dofollow link
has_links_to_redirects
boolean
page is pointing to a page that redirect elsewhere true if the page is pointing to a page that responds with a 3XX redirect
canonical_chain
boolean
pages with canonical pointing to a page that has a canonical pointing elsewhere true if the page has a canonical link element pointing to a page that has a canonical pointing to a different page
e.g. page a is canonicalized to page b, which is canonicalized to page c
canonical_to_redirect
boolean
canonical page pointing to a page that redirects elsewhere true if the page has a canonical link element pointing to a page that responds with a 3XX redirect
canonical_to_broken
boolean
canonical link pointing to a broken page true if the page has a canonical link pointing to a page that responds with a 4xx or 5xx response codes
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_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
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
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
recursive_canonical
boolean
recursive canonical error true if the page contains rel="canonical" tag to another page, which in turn, refers back to the initial page
canonical_chain
boolean
pages with canonical pointing to a page that has a canonical pointing elsewhere true if the page has a canonical link element pointing to a page that has a canonical pointing to a different page
e.g. page a is canonicalized to page b, which is canonicalized to page c
canonical_to_redirect
boolean
canonical page pointing to a page that redirects elsewhere true if the page has a canonical link element pointing to a page that responds with a 3XX redirect
canonical_to_broken
boolean
canonical link pointing to a broken page true if the page has a a canonical link pointing to a page that responds with a 4xx or 5xx response codes
has_links_to_redirects
boolean
page is pointing to a page that redirect elsewhere true if the page is pointing to a page that responds with a 3XX redirect
is_orphan_page
boolean
page with no internal links pointing to it true if the page has no reference from other pages of the domain Note: to use this field, set the respect_sitemap parameter in the POST request to true
is_link_relation_conflict
boolean
mix of both followed and nofollowed incoming internal links true if the page receives at least one link with the rel="nofollow" attribute and at least one dofollow link
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