Batch Processing

The Web API can receive batch requests with up to 1,000 URLs per batch. This is useful if you need to make many requests and would like to save time. In the following examples, we'll demonstrate real-world use cases, and show how to use batch requests most efficiently to achieve the intended goal.

Example one - collecting data from multiple URLs

In this first example, we'll collect data from several unique URLs. To do so, we set the URLs we want to collect in the url fields of the requests object.

Nimble APIs requires that a base64 encoded credential string be sent with every request to authenticate your account. For detailed examples, see Web API Authentication.

cURL

curl -X POST 'https://api.webit.live/api/v1/batch/web' \
--header 'Authorization: Basic <credential string>' \
--header 'Content-Type: application/json' \
--data-raw '{ 
    "requests": [
        { "url": "https://www.finance.com" },
        { "url": "https://www.travel.com" },
        { "url": "https://www.socialmedia.com" }
    ],
    "storage_type": "s3",
    "storage_url": "s3://Your.Repository.Path/",
    "callback_url": "https://your.callback.url/path"
}'

Python

import requests

url = 'https://api.webit.live/api/v1/batch/web'
headers = {
    'Authorization': 'Basic <credential string>',
    'Content-Type': 'application/json'
}
data = {
    "requests": [
        { "url": "https://www.finance.com" },
        { "url": "https://www.travel.com" },
        { "url": "https://www.socialmedia.com" }
    ],
    "storage_type": "s3",
    "storage_url": "s3://Your.Repository.Path/",
    "callback_url": "https://your.callback.url/path"
}

response = requests.post(url, headers=headers, json=data)

print(response.status_code)
print(response.json())

Node.js

const axios = require('axios');

const url = 'https://api.webit.live/api/v1/batch/web';
const headers = {
  'Authorization': 'Basic <credential string>',
  'Content-Type': 'application/json'
};
const data = {
  "requests": [
    { "url": "https://www.finance.com" },
    { "url": "https://www.travel.com" },
    { "url": "https://www.socialmedia.com" }
  ],
  "storage_type": "s3",
  "storage_url": "s3://Your.Repository.Path/",
  "callback_url": "https://your.callback.url/path"
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error(error);
  });

Go

package main

import (
	"bytes"
	"fmt"
	"net/http"
	"encoding/json"
)

func main() {
	url := "https://api.webit.live/api/v1/batch/web"
	payload := []byte(`{
		"requests": [
			{ "url": "https://www.finance.com" },
			{ "url": "https://www.travel.com" },
			{ "url": "https://www.socialmedia.com" }
		],
		"storage_type": "s3",
		"storage_url": "s3://Your.Repository.Path/",
		"callback_url": "https://your.callback.url/path"
	}`)
	headers := map[string]string{
		"Authorization":  "Basic <credential string>",
		"Content-Type":   "application/json",
	}

	req, err := http.NewRequest("POST", url, bytes.NewBuffer(payload))
	if err != nil {
		fmt.Println(err)
		return
	}

	for key, value := range headers {
		req.Header.Set(key, value)
	}

	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		fmt.Println(err)
		return
	}
	defer resp.Body.Close()

	fmt.Println(resp.StatusCode)
	// Read the response body if needed
	// body, err := ioutil.ReadAll(resp.Body)
	// fmt.Println(string(body))
}

Parameters that are placed outside the requests object, such as storage_type, storage_url, and callback_url , are automatically applied as defaults to all defined requests.

If a parameter is set both inside and outside the requests object, the value inside the request overrides the one outside.

Example two - collecting multiple URLs from multiple countries

In this example, we'll collect multiple URLs with a different country set for each URL. To do so, we'll take advantage of the requests object, which allows us to set any parameter inside each request:

cURL

curl -X POST 'https://api.webit.live/api/v1/batch/web' \
--header 'Authorization: Basic <credential string>' \
--header 'Content-Type: application/json' \
--data-raw '{ 
    "requests": [
        { "url": "https://www.finance.com", "country": "US", "locale": "en-US" },
        { "url": "https://www.travel.com",  "country": "FR", "locale": "fr" },
        { "url": "https://www.socialmedia.com",  "country": "GR", "locale": "de" },
        { "url": "https://www.searchengine.com" }
    ],
    "country": "CA", 
    "locale": "ca",
    "storage_type": "s3",
    "storage_url": "s3://Your.Repository.Path/",
    "callback_url": "https://your.callback.url/path"
}'

Python

import requests

url = 'https://api.webit.live/api/v1/batch/web'
headers = {
    'Authorization': 'Basic <credential string>',
    'Content-Type': 'application/json'
}
data = {
    "requests": [
        { "url": "https://www.finance.com", "country": "US", "locale": "en-US" },
        { "url": "https://www.travel.com",  "country": "FR", "locale": "fr" },
        { "url": "https://www.socialmedia.com",  "country": "GR", "locale": "de" },
        { "url": "https://www.searchengine.com" }
    ],
    "country": "CA",
    "locale": "ca",
    "storage_type": "s3",
    "storage_url": "s3://Your.Repository.Path/",
    "callback_url": "https://your.callback.url/path"
}

response = requests.post(url, headers=headers, json=data)

print(response.status_code)
print(response.json())

Node.js

const axios = require('axios');

const url = 'https://api.webit.live/api/v1/batch/web';
const headers = {
  'Authorization': 'Basic <credential string>',
  'Content-Type': 'application/json'
};
const data = {
  "requests": [
    { "url": "https://www.finance.com", "country": "US", "locale": "en-US" },
    { "url": "https://www.travel.com",  "country": "FR", "locale": "fr" },
    { "url": "https://www.socialmedia.com",  "country": "GR", "locale": "de" },
    { "url": "https://www.searchengine.com" }
  ],
  "country": "CA",
  "locale": "ca",
  "storage_type": "s3",
  "storage_url": "s3://Your.Repository.Path/",
  "callback_url": "https://your.callback.url/path"
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error(error);
  });

Go

package main

import (
	"bytes"
	"fmt"
	"net/http"
	"encoding/json"
)

func main() {
	url := "https://api.webit.live/api/v1/batch/web"
	payload := []byte(`{
		"requests": [
			{ "url": "https://www.finance.com", "country": "US", "locale": "en-US" },
			{ "url": "https://www.travel.com",  "country": "FR", "locale": "fr" },
			{ "url": "https://www.socialmedia.com",  "country": "GR", "locale": "de" },
			{ "url": "https://www.searchengine.com" }
		],
		"country": "CA",
		"locale": "ca",
		"storage_type": "s3",
		"storage_url": "s3://Your.Repository.Path/",
		"callback_url": "https://your.callback.url/path"
	}`)
	headers := map[string]string{
		"Authorization":  "Basic <credential string>",
		"Content-Type":   "application/json",
	}

	req, err := http.NewRequest("POST", url, bytes.NewBuffer(payload))
	if err != nil {
		fmt.Println(err)
		return
	}

for key, value := range headers {
	req.Header.Set(key, value)
}

client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
	fmt.Println(err)
	return
}
defer resp.Body.Close()

fmt.Println(resp.StatusCode)
// Read the response body if needed
// body, err := ioutil.ReadAll(resp.Body)
// fmt.Println(string(body))

For the above request, each URL would be requested from the corresponding country. "examplefour.com" does not have a country set in its request, and thus will default to the country defined outside the requests object (CA - Canada). If no default country had been set, by default the request would have used a randomly selected country.

Example three - collecting the same URL from different countries

Any parameter can be defined inside and/or outside the requests object. We can take advantage of this in some cases by setting our URL once as a default and setting various other parameters in the requests object. For example:

cURL

curl -X POST 'https://api.webit.live/api/v1/batch/web' \
--header 'Authorization: Basic <credential string>' \
--header 'Content-Type: application/json' \
--data-raw '{ 
    "requests": [
        { "country": "US", "locale": "en-US" },
        { "country": "FR", "locale": "fr" },
        { "country": "GR", "locale": "de" },
    ],
    "url": "https://www.finance.com",
    "storage_type": "s3",
    "storage_url": "s3://Your.Repository.Path/",
    "callback_url": "https://your.callback.url/path"
}'

Python

import requests

url = 'https://api.webit.live/api/v1/batch/web'
headers = {
    'Authorization': 'Basic <credential string>',
    'Content-Type': 'application/json'
}
data = {
    "requests": [
        { "country": "US", "locale": "en-US" },
        { "country": "FR", "locale": "fr" },
        { "country": "GR", "locale": "de" }
    ],
    "url": "https://www.finance.com",
    "storage_type": "s3",
    "storage_url": "s3://Your.Repository.Path/",
    "callback_url": "https://your.callback.url/path"
}

response = requests.post(url, headers=headers, json=data)

print(response.status_code)
print(response.json())

Node.js

const axios = require('axios');

const url = 'https://api.webit.live/api/v1/batch/web';
const headers = {
  'Authorization': 'Basic <credential string>',
  'Content-Type': 'application/json'
};
const data = {
  "requests": [
    { "country": "US", "locale": "en-US" },
    { "country": "FR", "locale": "fr" },
    { "country": "GR", "locale": "de" }
  ],
  "url": "https://www.finance.com",
  "storage_type": "s3",
  "storage_url": "s3://Your.Repository.Path/",
  "callback_url": "https://your.callback.url/path"
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error(error);
  });

Go

package main

import (
	"bytes"
	"fmt"
	"net/http"
	"encoding/json"
)

func main() {
	url := "https://api.webit.live/api/v1/batch/web"
	payload := []byte(`{
		"requests": [
			{ "country": "US", "locale": "en-US" },
			{ "country": "FR", "locale": "fr" },
			{ "country": "GR", "locale": "de" }
		],
		"url": "https://www.finance.com",
		"storage_type": "s3",
		"storage_url": "s3://Your.Repository.Path/",
		"callback_url": "https://your.callback.url/path"
	}`)
	headers := map[string]string{
		"Authorization":  "Basic <credential string>",
		"Content-Type":   "application/json",
	}

	req, err := http.NewRequest("POST", url, bytes.NewBuffer(payload))
	if err != nil {
		fmt.Println(err)
		return
	}

	for key, value := range headers {
		req.Header.Set(key, value)
	}

	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		fmt.Println(err)
		return
	}
	defer resp.Body.Close()

	fmt.Println(resp.StatusCode)
	// Read the response body if needed
	// body, err := ioutil.ReadAll(resp.Body)
	// fmt.Println(string(body))
}

In the above example, the URL "exampleone.com" would be requested three times - once from the US, once from France, and once from Germany.

Request options

Batch requests use the same parameters as asynchronous requests, with the exception of the requests object.

Parameter	Required	Description
requests	No	Object array - Allows for defining custom parameters for each request within the bulk. Any of the parameters below can be used in an individual request.
url	Required	The URL to be fetched. Note: when using a URL with a query string, encode the URL and place it at the end of the query string.
method	Optional (default = GET)	The method for requesting a URL from the target server.
country	Optional (default = all)	Country used to access the target URL, use ISO Alpha-2 Country Codes i.e. US, DE, GB
locale	Optional (default = EN)	String || LCID standard locale used for the URL request.
headers*	Optional	JSON with key/value structure to pass the required headers.
format	Optional (default = JSON)	Enum: JSON | HTML - The data response format. HTML - in case of error, returns JSON with error message.
parse	Optional (default = false)	Enum: true | false - True - the page's content will be parsed and returned in a JSON format. False - Response will include page headers and raw data (without parsing). When using parse = true, format must be set to “JSON”.
parser	Optional (default = null)	String | Define a custom parsing template. See Parsing Templates.
render	Optional (default = false)	Enum: true | false - enables or disables Javascript rendering on the target page.
render_flow	Optional (default = null)	String | Define a series of actions to be performed on the page prior to data collection. See Page Interactions.
render_options	N/A	A collection of rendering-related settings. See Rendering options.
storage_type	Optional	ENUM: s3 | gs - Use s3 for Amazon S3 and gs for Google Cloud Platform. Leave blank to enable Push/Pull delivery.
storage_url	Optional	Repository URL: s3://Your.Bucket.Name/your/object/name/prefix/ - Output will be saved to TASK_ID.json Leave blank to enable Push/Pull delivery.
callback_url	Optional	A url to callback once the data is delivered. The WebAPI will send a POST request to the callback_url with the task details once the task is complete (this “notification” will not include the requested data).

All URLs in a batch request receive the same parameters (country, locale, parse, repository, etc.)

Setting GCS/AWS access permissions

GCS Repository Configuration

In order to use Google Cloud Storage as your destination repository, please add Nimble’s system user as a principal to the relevant bucket. To do so, navigate to the “bucket details” page in your GCP console, and click on “Permission” in the submenu.

Next, past our system user [email protected] into the “New Principals” box, select Storage Object Creator as the role, and click save.

That’s all! At this point, Nimble will be able to upload files to your chosen GCS bucket.

S3 repository configuration

In order to use S3 as your destination repository, please give Nimble’s service user permission to upload files to the relevant S3 bucket. Paste the following JSON into the “Bucket Policy” (found under “Permissions”) in the AWS console.

Follow these steps:

1. Go to the “Permissions” tab on the bucket’s dashboard:

2. Scroll down to “Bucket policy” and press edit:

3. Paste the following bucket policy configuration into your bucket:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "Statement1",
            "Effect": "Allow",
            "Principal": {
                "AWS": "arn:aws:iam::744254827463:user/webit-uploader"
            },
            "Action": [
                "s3:PutObject",
                "s3:PutObjectACL"
            ],
            "Resource": "arn:aws:s3:::YOUR_BUCKET_NAME/*"
        },
        {
            "Sid": "Statement2",
            "Effect": "Allow",
            "Principal": {
                "AWS": "arn:aws:iam::744254827463:user/webit-uploader"
            },
            "Action": "s3:GetBucketLocation",
            "Resource": "arn:aws:s3:::YOUR_BUCKET_NAME"
        }
    ]
}

Important: Remember to replace “YOUR_BUCKET_NAME” with your actual bucket name.

Here is what the bucket policy should look like:

4. Scroll down and press “Save changes”

S3 Encrypted Buckets

If your S3 bucket is encrypted using an AWS Key Management Service (KMS) key, additional permissions to those outlined above are also needed. Specifically, Nimble's service user will need to be given permission to encrypt and decrypt objects using a KMS key. To do this, follow the steps below:

1. Sign in to the AWS Management Console and open the AWS Key Management Service (KMS) console.

   
2. In the navigation pane, choose "Customer managed keys".

   
3. Select the KMS key you want to modify.

   
4. Choose the "Key policy" tab, then "Switch to policy view".

   
5. Click "Edit".

   
6. Add the following statement to the existing policy JSON, ensuring it's inside the Statement array:

{
	"Version": "2012-10-17",
	"Id": "example-key-policy",
	"Statement": [
		// ... your pre-existing statements ...
		{
			"Sid": "Allow Nimble APIs account",
			"Effect": "Allow",
			"Principal": {
				"AWS": "arn:aws:iam::744254827463:user/webit-uploader"
			},
			"Action": [
				"kms:Encrypt",
				"kms:Decrypt",
				"kms:ReEncrypt*",
				"kms:GenerateDataKey*",
				"kms:DescribeKey"
			],
			"Resource": "*"
		},
	]
}

7. Click "Save changes" to update the key policy.

   

That's it! You've now given Nimble APIs permission to encrypt and decrypt objects, enabling access to encrypted buckets.

Please add Nimble's system/service user to your GCS or S3 bucket to ensure that data can be delivered successfully.

Responses

Initial Response

Batch requests operate asynchronously, and treat each request as a separate task. The result of each task is stored in a file, and a notification is sent to the provided callback any time an individual task is completed.

{
    "batch_id": "7a07a96d-c402-4d98-a17f-4ecb390d11a3",
    "batch_size": 3,
    "tasks": [
        {
            "batch_id": "7a07a96d-c402-4d98-a17f-4ecb390d11a3",
            "id": "2e508d43-8b02-4fc0-96c7-0968ab454a0c",
            "state": "pending",
            "output_url": "s3://Your.Repository.Path/2e508d43-8b02-4fc0-96c7-0968ab454a0c.json",
            "callback_url": "https://your.callback.url/path",
            "status_url": "https://api.webit.live/api/v1/tasks/2e508d43-8b02-4fc0-96c7-0968ab454a0c",
            "created_at": "2022-07-24T08:09:23.205Z",
            "modified_at": "2022-07-24T08:09:23.205Z",
            "input": {
            ...
        },
        {
            "batch_id": "7a07a96d-c402-4d98-a17f-4ecb390d11a3",
            "id": "63cc3bd5-01b4-4787-90a2-f382b9960c77",
            "state": "pending",
            ...
        },
        {
            "batch_id": "7a07a96d-c402-4d98-a17f-4ecb390d11a3",
            "id": "4cb39bbf-5580-4c50-8ed4-4a7905e2ec52",
            "state": "pending",
            ...
        }
    ]
}

Checking batch progress and status

POST https://api.webit.live/api/v1/batches/<batch_id>/progress

Like asynchronous tasks, the status of a batch is available for 24 hours.

cURL

curl -X GET 'https://api.webit.live/api/v1/batches/<batch_id>/progress' \
--header 'Authorization: Basic <credential string>'

Python

import requests

batch_id = "<batch_id>"
url = f"https://api.webit.live/api/v1/batches/{batch_id}/progress"
headers = {
    'Authorization': 'Basic <credential string>'
}

response = requests.get(url, headers=headers)

print(response.status_code)
print(response.json())

Node.js

const axios = require('axios');

const batchId = "<batch_id>";
const url = `https://api.webit.live/api/v1/batches/${batchId}/progress`;
const headers = {
  'Authorization': 'Basic <credential string>'
};

axios.get(url, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error(error);
  });

Go

package main

import (
	"fmt"
	"net/http"
)

func main() {
	batchID := "<batch_id>"
	url := fmt.Sprintf("https://api.webit.live/api/v1/batches/%s/progress", batchID)
	headers := map[string]string{
		"Authorization": "Basic <credential string>",
	}

	req, err := http.NewRequest("GET", url, nil)
	if err != nil {
		fmt.Println(err)
		return
	}

	for key, value := range headers {
		req.Header.Set(key, value)
	}

	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		fmt.Println(err)
		return
	}
	defer resp.Body.Close()

	fmt.Println(resp.StatusCode)
	// Read the response body if needed
	// body, err := ioutil.ReadAll(resp.Body)
	// fmt.Println(string(body))
}

Response

The progress of a batch is reported in percentages.

{
    "status": "success",
    "completed": false,
    "progress": 0.333333
}

Once a batch is finished, its progress will be reported as “1”.

{
    "status": "success",
    "completed": true,
    "progress": 1
}

Retrieving Batch Summary

Once a batch has finished, it’s possible to return a summary of the completed tasks, by using the following endpoint:

GET https://api.webit.live/api/v1/batches/<batch_id>

For example:

cURL

curl -X GET 'https://api.webit.live/api/v1/batches/7a07a96d-c402-4d98-a17f-4ecb390d11a3' \
--header 'Authorization: Basic <credential string>'

Python

import requests

batch_id = "7a07a96d-c402-4d98-a17f-4ecb390d11a3"
url = f"https://api.webit.live/api/v1/batches/{batch_id}"
headers = {
    'Authorization': 'Basic <credential string>'
}

response = requests.get(url, headers=headers)

print(response.status_code)
print(response.json())

Node.js

const axios = require('axios');

const batchId = "7a07a96d-c402-4d98-a17f-4ecb390d11a3";
const url = `https://api.webit.live/api/v1/batches/${batchId}`;
const headers = {
  'Authorization': 'Basic <credential string>'
};

axios.get(url, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error(error);
  });

Go

package main

import (
	"fmt"
	"net/http"
)

func main() {
	batchID := "7a07a96d-c402-4d98-a17f-4ecb390d11a3"
	url := fmt.Sprintf("https://api.webit.live/api/v1/batches/%s", batchID)
	headers := map[string]string{
		"Authorization": "Basic <credential string>",
	}

	req, err := http.NewRequest("GET", url, nil)
	if err != nil {
		fmt.Println(err)
		return
	}

	for key, value := range headers {
		req.Header.Set(key, value)
	}

	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		fmt.Println(err)
		return
	}
	defer resp.Body.Close()

	fmt.Println(resp.StatusCode)
	// Read the response body if needed
	// body, err := ioutil.ReadAll(resp.Body)
	// fmt.Println(string(body))
}

The response object lists the status of the overall batch, as well as the individual tasks and their details:

Response

{
    "status": "success",
    "tasks": [
        {
            "batch_id": "7a07a96d-c402-4d98-a17f-4ecb390d11a3",
            "id": "2e508d43-8b02-4fc0-96c7-0968ab454a0c",
            "state": "success",
            "query_time": "2023-01-01T12:00:00.007Z",
            "output_url": "s3://Your.Repository.Path/2e508d43-8b02-4fc0-96c7-0968ab454a0c.json",
            "callback_url": "https://your.callback.url/path",
            "status_url": "https://[base_url]/api/v1/tasks/2e508d43-8b02-4fc0-96c7-0968ab454a0c",
            "created_at": "2022-07-24T08:09:23.205Z",
            "modified_at": "2022-07-24T08:10:27.244Z",
            "input": {
        ...
            }
        },
        {
            "batch_id": "7a07a96d-c402-4d98-a17f-4ecb390d11a3",
            "id": "63cc3bd5-01b4-4787-90a2-f382b9960c77",
            "state": "success",
            "query_time": "2023-01-01T12:00:00.007Z",
            "output_url": "s3://Your.Repository.Path/63cc3bd5-01b4-4787-90a2-f382b9960c77.json",
            "callback_url": "https://your.callback.url/path",
            "status_url": "https://[base_url]/api/v1/tasks/63cc3bd5-01b4-4787-90a2-f382b9960c77",
            "created_at": "2022-07-24T08:09:23.205Z",
            "modified_at": "2022-07-24T08:10:27.973Z",
            "input": {
        ...
            }
         },
        {
            "batch_id": "7a07a96d-c402-4d98-a17f-4ecb390d11a3",
            "id": "4cb39bbf-5580-4c50-8ed4-4a7905e2ec52",
            "state": "success",
            "query_time": "2023-01-01T12:00:00.007Z",
            "output_url": "s3://Your.Repository.Path/4cb39bbf-5580-4c50-8ed4-4a7905e2ec52.json",
            "callback_url": "https://your.callback.url/path",
            "status_url": "https://[base_url]/api/v1/tasks/4cb39bbf-5580-4c50-8ed4-4a7905e2ec52",
            "created_at": "2022-07-24T08:09:23.205Z",
            "modified_at": "2022-07-24T08:10:30.292Z",
            "input": {
        ...
            }
        }
    ],
    "completed": true,
    "progress": 1
}

500 Error

{
        "status": "error",
        "task_id": "<task_id>",
        "msg": "can't download the query response - please try again"
}

400 Input Error

{
        "status": "failed",
        "msg": error
}

Previously, batch requests used a url field to pass multiple URLs for collection. That syntax is now deprecated, and batch requests should be updated to use the new requestssyntax defined above.

Response codes

Status	Description
200	OK
400	The requested resource could not be reached
401	Unauthorized/invalid credental string
500	Internal service error
501	An error was encountered by the proxy service