Add Tasks

curl --request POST \
  --url https://api.lobstr.io/v1/tasks \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>'

import requests

url = "https://api.lobstr.io/v1/tasks"

headers = {
    "Authorization": "<authorization>",
    "Content-Type": "<content-type>"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<authorization>', 'Content-Type': '<content-type>'}
};

fetch('https://api.lobstr.io/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.lobstr.io/v1/tasks",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: <content-type>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.lobstr.io/v1/tasks"

	req, _ := http.NewRequest("POST", url, nil)

	req.Header.Add("Authorization", "<authorization>")
	req.Header.Add("Content-Type", "<content-type>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.lobstr.io/v1/tasks")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "<content-type>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.lobstr.io/v1/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = '<content-type>'

response = http.request(request)
puts response.read_body

POST

tasks

Add Tasks

curl --request POST \
  --url https://api.lobstr.io/v1/tasks \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>'

import requests

url = "https://api.lobstr.io/v1/tasks"

headers = {
    "Authorization": "<authorization>",
    "Content-Type": "<content-type>"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<authorization>', 'Content-Type': '<content-type>'}
};

fetch('https://api.lobstr.io/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.lobstr.io/v1/tasks",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: <content-type>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.lobstr.io/v1/tasks"

	req, _ := http.NewRequest("POST", url, nil)

	req.Header.Add("Authorization", "<authorization>")
	req.Header.Add("Content-Type", "<content-type>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.lobstr.io/v1/tasks")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "<content-type>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.lobstr.io/v1/tasks")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = '<content-type>'

response = http.request(request)
puts response.read_body

Add Pages Jaunes (French Yellow Pages) search URLs to your squid for scraping business directory listings. The scraper extracts company information including contact details, addresses, business registration numbers (SIRET/SIREN), and social media profiles from France’s largest business directory.

Headers

string

required

Your API authentication token. Value: Token YOUR_API_KEY

string

required

Request body format. Value: application/json

Task Format

Each task should contain a URL from a Pages Jaunes search results page. Search for businesses by category and location on the website, then use those search URLs as tasks.

Supported URL Formats

The scraper supports Pages Jaunes search URLs:

Pages Jaunes URLs use department codes (e.g., ‘paris-75’ for Paris). Apply location filters on the website to get properly formatted URLs.

Search by specific business categories (boulanger, plombier, restaurant) to get targeted results for your industry research.

Code Examples

curl -X POST "https://api.lobstr.io/v1/tasks" \
  -H "Authorization: Token YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "squid": "YOUR_SQUID_HASH",
    "tasks": [
      {
        "url": "https://www.pagesjaunes.fr/annuaire/paris-75/boulanger"
      }
    ]
  }'

import requests

API_KEY = "YOUR_API_KEY"
BASE_URL = "https://api.lobstr.io/v1"
headers = {"Authorization": f"Token {API_KEY}"}

squid_id = "YOUR_SQUID_HASH"

# Add Pages Jaunes search URLs as tasks
response = requests.post(f"{BASE_URL}/tasks",
    headers=headers,
    json={
        "squid": squid_id,
        "tasks": [
            {"url": "https://www.pagesjaunes.fr/annuaire/paris-75/boulanger"},
            {"url": "https://www.pagesjaunes.fr/annuaire/lyon-69/plombier"}
        ]
    }
)

data = response.json()
print(f"Added {len(data['tasks'])} tasks")
print(f"Duplicates skipped: {data['duplicated_count']}")

for task in data["tasks"]:
    print(f"  Task ID: {task['id']}")
    print(f"  URL: {task['params']['url']}")

Response

200

{
  "duplicated_count": 0,
  "tasks": [
    {
      "id": "82367f24d9450b2222080eed91662968",
      "created_at": "2025-07-17T09:06:47.287893",
      "is_active": true,
      "params": {
        "url": "https://www.pagesjaunes.fr/annuaire/paris-75/boulanger"
      },
      "module": 115,
      "object": "task"
    }
  ]
}

Get Results Update Settings

​Headers

​Task Format

​Supported URL Formats

​Code Examples

​Response

Headers

Task Format

Supported URL Formats

Code Examples

Response