Google Dataset Search API provides top 20 Google Dataset search engine results. These results are specific to the indicated keyword. You can specify other parameters optionally.
There are two different priorities that stand for the relative speed of task execution: normal and high.
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/serp/google/dataset_search/task_post'
--header "Authorization: Basic ${cred}"
--header "Content-Type: application/json"
--data-raw '[
{
"keyword": "water quality",
"last_updated": "1m",
"file_formats": [ "archive", "image" ],
"usage_rights": "noncommercial",
"is_free": true,
"topics": [ "natural_sciences", "geo" ]
}
]'
<?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/';
try {
// Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-access
$client = new RestClient($api_url, null, 'login', 'password');
} 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";
exit();
}
$post_array = array();
// example #1 - a simple way to set a task
// this way requires you to specify a keyword.
$post_array[] = array(
"keyword" => "water quality",
"last_updated" => "1m",
"file_formats" => [ "archive", "image" ],
"usage_rights" => "noncommercial",
"is_free" => true,
"topics" => [ "natural_sciences", "geo" ]
);
// example #2 - a way to set a task with additional parameters
// high priority allows us to complete a task faster, but you will be charged more credits.
// after a task is completed, we will send a GET request to the address you specify. Instead of $id and $tag, you will receive actual values that are relevant to this task.
$post_array[] = array(
"keyword" => "water quality",
"last_updated" => "1m",
"file_formats" => [ "archive", "image" ],
"usage_rights" => "noncommercial",
"is_free" => true,
"topics" => [ "natural_sciences", "geo" ],
"priority" => 2,
"tag" => "some_string_123",
"pingback_url" => 'https://your-server.com/pingscript?id=$id&tag=$tag'
);
// this example has a 3 elements, but in the case of large number of tasks - send up to 100 elements per POST request
if (count($post_array) > 0) {
try {
// POST /v3/serp/google/dataset_search/task_post
// in addition to 'google' and 'dataset_search' you can also set other search engine and type parameters
$result = $client->post('/v3/serp/google/dataset_search/task_post', $post_array);
print_r($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 client import RestClient
# You can download this file from here https://cdn.dataforseo.com/v3/examples/python/python_Client.zip
client = RestClient("login", "password")
post_data = dict()
# example #1 - a simple way to set a task
# this way requires you to specify a keyword.
post_data[len(post_data)] = dict(
keyword="water quality",
last_updated="1m",
file_formats=[ "archive", "image" ],
usage_rights="noncommercial",
is_free=true,
topics=[ "natural_sciences", "geo" ]
)
# example #2 - a way to set a task with additional parameters
# high priority allows us to complete a task faster, but you will be charged more.
# after a task is completed, we will send a GET request to the address you specify. Instead of $id and $tag, you will receive actual values that are relevant to this task.
post_data[len(post_data)] = dict(
keyword="water quality",
last_updated="1m",
file_formats=[ "archive", "image" ],
usage_rights="noncommercial",
is_free=true,
topics=[ "natural_sciences", "geo" ],
priority=2,
tag="some_string_123",
pingback_url="https://your-server.com/pingscript?id=$id&tag=$tag"
)
# POST /v3/serp/google/dataset_search/task_post
# in addition to 'google' and 'dataset_search' you can also set other search engine and type parameters
# the full list of possible parameters is available in documentation
response = client.post("/v3/serp/google/dataset_search/task_post", 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 serp_task_post()
{
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>();
// example #1 - a simple way to set a task
// this way requires you to specify a keyword.
postData.Add(new
{
keyword="water quality",
last_updated="1m",
file_formats=[ "archive", "image" ],
usage_rights="noncommercial",
is_free=true,
topics=[ "natural_sciences", "geo" ]
});
// example #2 - a way to set a task with additional parameters
// high priority allows us to complete a task faster, but you will be charged more money.
// after a task is completed, we will send a GET request to the address you specify. Instead of $id and $tag, you will receive actual values that are relevant to this task.
postData.Add(new
{
keyword="water quality",
last_updated="1m",
file_formats=[ "archive", "image" ],
usage_rights="noncommercial",
is_free=true,
topics=[ "natural_sciences", "geo" ]
priority = 2,
tag = "some_string_123",
pingback_url = "https://your-server.com/pingscript?id=$id&tag=$tag"
});
// POST /v3/serp/google/dataset_search/task_post
// in addition to 'google' and 'dataset_search' you can also set other search engine and type parameters
// the full list of possible parameters is available in documentation
var taskPostResponse = await httpClient.PostAsync("/v3/serp/google/dataset_search/task_post", new StringContent(JsonConvert.SerializeObject(postData)));
var result = JsonConvert.DeserializeObject<dynamic>(await taskPostResponse.Content.ReadAsStringAsync());
// you can find the full list of the response codes here https://docs.dataforseo.com/v3/appendix/errors
if (result.status_code == 20000)
{
// do something with result
Console.WriteLine(result);
}
else
Console.WriteLine($"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. You can send up to 2000 API calls per minute, with each POST call containing no more than 100 tasks. If your POST call contains over 100 tasks, the tasks over this limit will return the 40006 error. Visit DataForSEO Help Center to get practical tips for request handling depending on your SERP API payload volume.
You can retrieve the results of completed tasks using the unique task identifier id. Alternatively, we can send them to you as soon as they are ready if you specify the postback_url or pingback_url when setting a task. Note that if your server doesn’t respond within 10 seconds, the connection will be aborted by timeout, and the task will be transferred to the ‘Tasks Ready’ list. The error code and message depend on your server’s configuration. See Help Center to learn more about using pingbacks and postbacks with DataForSEO APIs.
Below you will find a detailed description of the fields you can use for setting a task.
Description of the fields for setting a task:
Field name
Type
Description
keyword
string
keyword required field
you can specify up to 700 characters in the keyword field
all %## will be decoded (plus character ‘+’ will be decoded to a space character)
if you need to use the “%” character for your keyword, please specify it as “%25”;
if you need to use the “+” character for your keyword, please specify it as “%2B”.
learn more about rules and limitations of keyword and keywords fields in DataForSEO APIs in this Help Center article
priority
integer
task priority
optional field
can take the following values:
1 – normal execution priority (set by default)
2 – high execution priority
depth
integer
parsing depth
optional field
number of results in SERP
default value: 20
max value: 700 Note: your account will be billed per each SERP containing up to 20 results;
thus, setting a depth above 20 may result in additional charges if the search engine returns more than 20 results;
if the specified depth is higher than the number of results in the response, the difference will be refunded automatically to your account balance
language_name
string
full name of search engine language
optional field
if you use this field, you don’t need to specify language_code
possible value: English
language_code
string
search engine language code
optional field
possible value: en
device
string
device type
optional field
possible value: desktop
os
string
device operating system
optional field
possible values: windows, macos
default value: windows
last_updated
string
last time the dataset was updated
optional field
possible values: 1m, 1y, 3y
file_formats
array
file formats of the dataset
optional field
possible values: other, archive, text, image, document, tabular
usage_rights
string
usage rights of the dataset
optional field
possible values: commercial, noncommercial
is_free
boolean
indicates whether displayed datasets are free
optional field
possible values: true, false
topics
array
dataset topics
optional field
possible values: humanities, social_sciences, life_sciences, agriculture, natural_sciences, geo, computer, architecture_and_urban_planning, engineering
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
postback_url
string
return URL for sending task results
optional field
once the task is completed, we will send a POST request with its results compressed in the gzip format to the postback_url you specified
you can use the ‘$id’ string as a $id variable and ‘$tag’ as urlencoded $tag variable. We will set the necessary values before sending the request
example: http://your-server.com/postbackscript?id=$id http://your-server.com/postbackscript?id=$id&tag=$tag Note: special characters in postback_url will be urlencoded;
i.a., the # character will be encoded into %23
postback_url datatype required field if you specify postback_url
corresponds to the datatype that will be sent to your server
only value: advanced
pingback_url
string
notification URL of a completed task
optional field
when a task is completed we will notify you by GET request sent to the URL you have specified
you can use the ‘$id’ string as a $id variable and ‘$tag’ as urlencoded $tag variable. We will set the necessary values before sending the request.
example: http://your-server.com/pingscript?id=$id http://your-server.com/pingscript?id=$id&tag=$tag Note: special characters in pingback_url will be urlencoded;
i.a., the # character will be encoded into %23
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 tasksarray
tasks_error
integer
the number of tasks in the tasks array returned with an error