This endpoint will provide you with a list of resources, including images, scripts, stylesheets, and broken elements.
You will get a detailed overview of every resource found on the crawled pages.
If you would like to receive a list of pages that contain a specific resource, please refer to the Pages By Resource endpoint.
Instead of ‘login’ and ‘password’ use your credentials from https://app.dataforseo.com/api-dashboard
# Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-dashboard \
login="login" \
password="password" \
cred="$(printf ${login}:${password} | base64)" \
curl --location --request POST "https://api.dataforseo.com/v3/on_page/resources" \
--header "Authorization: Basic ${cred}" \
--header "Content-Type: application/json" \
--data-raw "[
{
"id": "07281559-0695-0216-0000-c269be8b7592",
"filters": [
["resource_type", "=", "image"],
"and",
["size", ">", 100000]
],
"order_by": ["size,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-dashboard
$client = new RestClient($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", "=", "image"],
"and",
["size", ">", 100000]
],
"order_by" => ["size,desc"],
"limit" => 10
);
try {
// POST /v3/on_page/resources
// the full list of possible parameters is available in documentation
$result = $client->post('/v3/on_page/resources', $post_array);
print_r($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", "=", "image"],
"and",
["size", ">", 100000]
],
order_by=["size,desc"],
limit=10
)
# POST /v3/on_page/resources
# the full list of possible parameters is available in documentation
response = client.post("/v3/on_page/resources", 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_resources()
{
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-dashboard
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",
filters = new object[]
{
new object[] { "resource_type", "=", "image" },
"and",
new object[] { "size", ">", 100000 }
},
order_by = new object[] { "size,desc" },
limit = 10
});
// POST /v3/on_page/resources
// the full list of possible parameters is available in documentation
var taskPostResponse = await httpClient.PostAsync("/v3/on_page/resources", 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:
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
optional field
specify this field if you want to get the resources for a specific page
note that to obtain resource’s meta from a particular URL, you should specify the URL in this field;
if you do not indicate a url when setting a task, resource’s meta in the results will be returned based on the data from the page where our crawler first saw the resource
limit
integer
the maximum number of returned resources
optional field
default value: 100
maximum value: 1000
offset
integer
offset in the results array of returned resources
optional field
default value: 0
if you specify the 10 value, the first ten resources in the results array will be omitted and the data will be provided for the successive resources
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: ["resource_type","=","stylesheet"]
The full list of possible filters is available by this link.
relevant_pages_filters
array
filter the resources by relevant pages
optional field
you can use this field to obtain resources from pages matching to the defined parameters
you can apply the same filters here as available for the pages endpoint 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: ["checks.no_image_title","=",true]
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: ["size,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: ["size,desc","fetch_timing.fetch_end,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 crawled
items_count
integer
number of items in the results array
items
array
items array
resource_type
string
type of the returned resource
possible types: script, image, stylesheet, broken
meta
object
resource properties
the value depends on the resource_type
note that if you do not indicate a url when setting a task, resource’s meta is returned based on the data from the page where our crawler first saw the resource;
to obtain resource’s meta from a particular url, specify that URL when setting a task
alternative_text
string
content of the image alt attribute
the value depends on the resource_type
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 fething 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;
available for items with the following resource_type: script, image, stylesheet, broken
high_loading_time
boolean
resource with high loading time
indicates whether a resource loading time exceeds 3 seconds;
available for items with the following resource_type: script, image, stylesheet, broken
is_redirect
boolean
resource with redirects
indicates whether a page with this resource has 3XX redirects to other pages;
available for items with the following resource_type: script, image, stylesheet, broken
is_4xx_code
boolean
resource with with 4xx status code
indicates whether a page with this resource has 4XX response code
is_5xx_code
boolean
resource with 5xx status code
indicates whethera page with this 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;
available for items with the following resource_type: script, image, stylesheet, broken
is_www
boolean
page with www
indicates whether a page with this resource is on a www subdomain;
available for items with the following resource_type: script, image, stylesheet, broken
is_https
boolean
page with the https protocol
available for items with the following resource_type: script, image, stylesheet, broken
is_http
boolean
page with the http protocol
available for items with the following resource_type: script, image, stylesheet, broken
original_size_displayed
boolean
image desplayes in its original size
indicates whether the image is displayed in its original size;
available for items with the following resource_type: image
is_minified
boolean
resource is minified
indicates whether the content of a stylesheet or script is minified;
available for items with the following resource_type: stylesheet, script
has_redirect
boolean
resource has a redirect
available for items with the following resource_type: script, image;
if the resource_type is image, this field will indicate whether other pages and/or resources have redirects pointing at the image;
if the resource_type is script, this field will indicate whether the script contains a redirect
has_subrequests
boolean
resource contains subrequests
indicates whether the content of a stylesheet or script contain additional requests;
available for items with the following resource_type: stylesheet, script
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