This endpoint returns a list of pages that have content similar to the page specified in the request. The response also contains data related to page performance and the similarity index that indicates how similar the compared pages are.
The SimHash algorithm is used for calculating the similarity score from 0 to 10, where 0 means that comparative pieces of content are not similar at all, and 10 means they are identical.
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/duplicate_content" \
--header "Authorization: Basic ${cred}" \
--header "Content-Type: application/json" \
--data-raw "[
{
"id": "07281559-0695-0216-0000-c269be8b7592",
"url": "https://www.etsy.com/"
}
]"
<?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",
"url" => "https://www.etsy.com/"
);
try {
// POST /v3/on_page/duplicate_content
// the full list of possible parameters is available in documentation
$result = $client->post('/v3/on_page/duplicate_content', $post_array);
print_r($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",
url="https://www.etsy.com/"
)
# POST /v3/on_page/duplicate_content
# the full list of possible parameters is available in documentation
response = client.post("/v3/on_page/duplicate_content", 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_duplicate_content()
{
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 = "07281559-0695-0216-0000-c269be8b7592",
url = "https://www.etsy.com/"
});
// POST /v3/on_page/duplicate_content
// the full list of possible parameters is available in documentation
var taskPostResponse = await httpClient.PostAsync("/v3/on_page/duplicate_content", 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": "0.1.20210129",
"status_code": 20000,
"status_message": "Ok.",
"time": "1.3879 sec.",
"cost": 0,
"tasks_count": 1,
"tasks_error": 0,
"tasks": [
{
"id": "07281559-0695-0216-0000-c269be8b7592",
"status_code": 20000,
"status_message": "Ok.",
"time": "1.3032 sec.",
"cost": 0,
"result_count": 1,
"path": [
"v3",
"on_page",
"duplicate_content"
],
"data": {
"api": "on_page",
"function": "duplicate_content",
"url": "https://www.etsy.com/"
},
"result": [
{
"crawl_progress": "finished",
"crawl_status": {
"max_crawl_pages": 10,
"pages_in_queue": 0,
"pages_crawled": 10
},
"items_count": 1,
"items": [
{
"url": "https://www.etsy.com/",
"total_count": 1,
"pages": [
{
"similarity": 7,
"page": [
{
"resource_type": "html",
"status_code": 200,
"location": null,
"url": "https://www.etsy.com/de/",
"meta": {
"title": "Etsy - Kaufe Handgefertigtes, Vintage-Sachen, Spezialanfertigungen und einzigartige Geschenke für alle ein.",
"charset": 65001,
"follow": true,
"generator": null,
"htags": {
"h1": [
"Deine Datenschutzeinstellungen",
"Bye-bye Winter, hallo Neustart!",
"Außergewöhnliche Alltagshelfer",
"Aktualisiere deine Einstellungen"
],
"h3": [
"Datenschutzeinstellungen",
"Ostern Korb, personalisierte Osterkorb, Monogramm Osterkorb, Mädchen Korb, jungen Korb, Mädchen Ostern Korb, bestickt, überprüfen",
"Äußere rustische Rusty Metall Robin Vogel Garten Zaun Topper Yard Art Gate Post Rasen Skulptur Geschenk Muttertagsgeschenk",
"Benutzerdefinierte Aufkleber Bulk-Set. Logo-Aufkleber auf wasserdichte dauerhafte, Qualität Vinyl gedruckt. Schneiden Sie in jede Form.",
"Ich werde zeichnen & beschreiben Sie Ihre Zukunft Mann in 12 Stunden, künstlerische psychische, psychische Zeichnung, psychische Lesen Skizze, Liebe psychische schnelle Lesen",
"Silikon Osterhase Kuchen Form",
"Getrocknete englische Lavendel Bund, duftenden Lavendel, Verschmieren Lavendel, Verschmieren Lavendel, Verschmieren Kraut, Lavendel Bouquet, Lavendel Stiele",
"Slipper Socken, Liebe Herz Design, grau, Marineblau, rot, Pflaume, schwarz, Petrol, Valentinstag, Weihnachten, Muttertag, handgefertigt, häkeln",
"Topfschrubber / Schwamm - gehäkelt aus 100% Hanf, plastikfrei + zero waste, unsponge, statt Schwamm",
"Keramikschalen in schwarz. Einzigartige Küche Dekor, Tauchen Schale, kleine Tauchschüssel, Keramik Schale Set, Keramik Dip Schale, Housewarminggeschenk, Gewürzschale",
"Fisch Wärmepackung - Mikrowellen - Linsen Kissen",
"Gekochte Wolle Eco Schuhe, Frauen Clogs, Filz rustikale Hygge Hausschuhe, nordische Hausschuhe, Frauen Filz Hausschuhe, natürliche Hauszimmer Schuhe",
"Frankfurt Schneidebrett, Käsebrett, Holz, Buche, Stadt, Küche, Geschenk, Hochzeit, Dekoration, Servieren, individuell, minimal, Geburtstag",
"Designideen und -inspiration",
"Große Keramik hellblau Teekanne",
"Speisekammer Etiketten Basic, Glutenfrei, Kräuter, Gewürze, Tees, Nüsse, Öle & Esses - gedruckt wasserdicht Matt Vinyl - benutzerdefinierte Etiketten",
"Aufhängung aus Makrame zur Dekoration",
"Grüne Keramik Votiv Kerze Halter",
"Leinen Schürze. Gewaschene LeinenSchürze in gestreift in natürlicher Leinenfarbe. Weiche Leinen Küche Schürze für Frauen und Mann. Weihnachtsgeschenk.",
"Blass rosa und Taube grau Ombre bemalt samt Kissenbezug, sofort zu versenden UK 12 \"x 20\" (30cm x 50cm) + andere Größen auf Bestellung",
"Eine einzigartige Community",
"Support für unabhängige Kreative",
"Sicher Stöbern, Kaufen und Verkaufen",
"Einkaufen auf Etsy",
"Verkaufen auf Etsy",
"Über Etsy",
"Hilfe"
],
"h2": [
"Notwendige Cookies und Technologien",
"Benutzerdefinierte Website-Gestaltung",
"Personalisierte Werbung",
"Alles für den Frühling",
"Aktuell im Trend",
"Entdecke einzigartige handverlesene Produkte",
"Unsere Lieblingsstücke",
"Stöbere in unserer Auswahl",
"Stöbere in unserer Auswahl",
"Was ist Etsy?",
"Das Neueste von unserem Blog",
"Fußzeile"
],
"h4": [
"Noch Fragen? Hier gibt’s Antworten."
]
},
"description": "Finde das perfekte handgemachte Geschenk, trendige und Vintage-Kleidung, ganz besonderen Schmuck und mehr… vieles mehr.",
"favicon": "https://www.etsy.com/images/favicon.ico",
"meta_keywords": null,
"canonical": "https://www.etsy.com/de/",
"internal_links_count": 99,
"external_links_count": 8,
"inbound_links_count": 28,
"images_count": 30,
"images_size": 758551,
"scripts_count": 7,
"scripts_size": 282064,
"stylesheets_count": 3,
"stylesheets_size": 97246,
"title_length": 107,
"description_length": 119,
"render_blocking_scripts_count": 4,
"render_blocking_stylesheets_count": 31,
"cumulative_layout_shift": 0.10156329069412295,
"content": {
"plain_text_size": 9667,
"plain_text_rate": 0.038021482708032614,
"plain_text_word_count": 1226,
"automated_readability_index": 21.083439863562212,
"coleman_liau_readability_index": 9.494734111543448,
"dale_chall_readability_index": 11.653761227940086,
"flesch_kincaid_readability_index": -4.964475900934303,
"smog_readability_index": 25.173868470299045,
"description_to_content_consistency": 0.2142857164144516,
"title_to_content_consistency": 0.5,
"meta_keywords_to_content_consistency": null
},
"deprecated_tags": null,
"duplicate_meta_tags": [
"description",
"viewport"
],
"spell": null,
"resource_errors": {
"errors": [
{
"line": 755,
"message": "No paragraph has been found within the local scope."
},
{
"line": 899,
"message": "No paragraph has been found within the local scope."
},
{
"line": 1055,
"message": "No paragraph has been found within the local scope."
},
{
"line": 1220,
"message": "No paragraph has been found within the local scope."
}
],
"warnings": [
{
"line": 0,
"message": "Has node with more than 60 childs."
},
{
"line": 0,
"message": "Has more that 1500 nodes."
}
]
},
"social_media_tags": {
"fb:app_id": "89186614300",
"og:site_name": "Etsy",
"og:locale": "de_DE",
"og:title": "Etsy - Kaufe Handgefertigtes, Vintage-Sachen, Spezialanfertigungen und einzigartige Geschenke für alle ein.",
"og:description": "Finde das perfekte handgemachte Geschenk, trendige und Vintage-Kleidung, ganz besonderen Schmuck und mehr… vieles mehr."
}
},
"page_timing": {
"time_to_interactive": 1142,
"dom_complete": 1845,
"largest_contentful_paint": 1648.4750006347895,
"first_input_delay": 0.0550001859664917,
"connection_time": 9,
"time_to_secure_connection": 21,
"request_sent_time": 0,
"waiting_time": 632,
"download_time": 6,
"duration_time": 668,
"fetch_start": 0,
"fetch_end": 668
},
"onpage_score": 88.36,
"total_dom_size": 2992954,
"custom_js_response": null,
"custom_js_client_exception": null,
"broken_resources": false,
"broken_links": false,
"duplicate_title": true,
"duplicate_description": true,
"duplicate_content": true,
"click_depth": 1,
"size": 254576,
"encoded_size": 44751,
"total_transfer_size": 46552,
"fetch_time": "2021-02-24 17:02:10 +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": true,
"is_https": true,
"is_http": false,
"high_waiting_time": false,
"no_doctype": false,
"canonical": true,
"no_encoding_meta_tag": true,
"no_h1_tag": false,
"https_to_http_links": false,
"has_html_doctype": true,
"size_greater_than_3mb": false,
"meta_charset_consistency": true,
"has_meta_refresh_redirect": false,
"has_render_blocking_resources": true,
"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": true,
"irrelevant_description": false,
"irrelevant_title": false,
"irrelevant_meta_keywords": false,
"title_too_long": true,
"title_too_short": false,
"deprecated_html_tags": false,
"duplicate_meta_tags": true,
"duplicate_title_tag": false,
"no_image_alt": true,
"no_image_title": true,
"no_description": false,
"no_title": false,
"no_favicon": false,
"seo_friendly_url": false,
"flash": false,
"frame": false,
"lorem_ipsum": false,
"seo_friendly_url_characters_check": true,
"seo_friendly_url_dynamic_check": true,
"seo_friendly_url_keywords_check": false,
"seo_friendly_url_relative_length_check": true,
"is_orphan_page": false,
"is_link_relation_conflict": false,
"has_links_to_redirects": false,
"recursive_canonical": false,
"canonical_chain": false,
"canonical_to_redirect": false,
"canonical_to_broken": false
},
"content_encoding": "gzip",
"media_type": "text/html",
"server": "Apache",
"is_resource": false,
"last_modified": {
"header": "2021-10-21 14:11:10 +00:00",
"sitemap": null,
"meta_tag": "2021-03-15 00:00:00 +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.
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”
url
string
page URL required field
specify the initial page you want to receive duplicate content for
similarity
integer
content similarity score
by default, the content is considered duplicate if the value is greater than or equals 6
you can specify any similarity score in the 0-to-10 range
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
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
items_count
integer
number of items in the results array
items
array
items array
url
string
URL of the specified page
total_count
integer
total count of duplicate pages
pages
array
pages with duplicate content
similarity
integer
content similarity score
by default, the content is considered duplicate if the value is greater than or equals 6
can take values from 0 to 10
page
array
information about the page with duplicate content
‘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 a 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.
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
text message of the error
the full list of possible HTML errors can be found here
warnings
array
resource warnings
line
integer
line the warning relates to
note that if "line": 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
social_media_tags
object
array 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
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
no_doctype
boolean
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
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 misspelled content
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
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
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 redirect 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
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
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