Create Scraping Job
curl --request POST \
--url https://api.skop.dev/scrape/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"website": "https://example.com",
"prompt": "Find board meeting minutes from 2025",
"parameters": {
"single_page": false,
"timeout": 1800,
"confidence_threshold": 0.1,
"file_type": "document",
"max_file_size_mb": 100
}
}
'import requests
url = "https://api.skop.dev/scrape/"
payload = {
"website": "https://example.com",
"prompt": "Find board meeting minutes from 2025",
"parameters": {
"single_page": False,
"timeout": 1800,
"confidence_threshold": 0.1,
"file_type": "document",
"max_file_size_mb": 100
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
website: 'https://example.com',
prompt: 'Find board meeting minutes from 2025',
parameters: {
single_page: false,
timeout: 1800,
confidence_threshold: 0.1,
file_type: 'document',
max_file_size_mb: 100
}
})
};
fetch('https://api.skop.dev/scrape/', 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.skop.dev/scrape/",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'website' => 'https://example.com',
'prompt' => 'Find board meeting minutes from 2025',
'parameters' => [
'single_page' => false,
'timeout' => 1800,
'confidence_threshold' => 0.1,
'file_type' => 'document',
'max_file_size_mb' => 100
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.skop.dev/scrape/"
payload := strings.NewReader("{\n \"website\": \"https://example.com\",\n \"prompt\": \"Find board meeting minutes from 2025\",\n \"parameters\": {\n \"single_page\": false,\n \"timeout\": 1800,\n \"confidence_threshold\": 0.1,\n \"file_type\": \"document\",\n \"max_file_size_mb\": 100\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
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.skop.dev/scrape/")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"website\": \"https://example.com\",\n \"prompt\": \"Find board meeting minutes from 2025\",\n \"parameters\": {\n \"single_page\": false,\n \"timeout\": 1800,\n \"confidence_threshold\": 0.1,\n \"file_type\": \"document\",\n \"max_file_size_mb\": 100\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.skop.dev/scrape/")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"website\": \"https://example.com\",\n \"prompt\": \"Find board meeting minutes from 2025\",\n \"parameters\": {\n \"single_page\": false,\n \"timeout\": 1800,\n \"confidence_threshold\": 0.1,\n \"file_type\": \"document\",\n \"max_file_size_mb\": 100\n }\n}"
response = http.request(request)
puts response.read_body{
"job_id": "job_4fc79a89797e",
"status": "pending",
"message": "Job created successfully and queued for processing",
"estimated_completion": "2023-11-07T05:31:56Z",
"created_at": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}API Endpoints
Create Scraping Job
Start a new document scraping job with a website URL and natural language prompt
POST
/
scrape
/
Create Scraping Job
curl --request POST \
--url https://api.skop.dev/scrape/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"website": "https://example.com",
"prompt": "Find board meeting minutes from 2025",
"parameters": {
"single_page": false,
"timeout": 1800,
"confidence_threshold": 0.1,
"file_type": "document",
"max_file_size_mb": 100
}
}
'import requests
url = "https://api.skop.dev/scrape/"
payload = {
"website": "https://example.com",
"prompt": "Find board meeting minutes from 2025",
"parameters": {
"single_page": False,
"timeout": 1800,
"confidence_threshold": 0.1,
"file_type": "document",
"max_file_size_mb": 100
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
website: 'https://example.com',
prompt: 'Find board meeting minutes from 2025',
parameters: {
single_page: false,
timeout: 1800,
confidence_threshold: 0.1,
file_type: 'document',
max_file_size_mb: 100
}
})
};
fetch('https://api.skop.dev/scrape/', 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.skop.dev/scrape/",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'website' => 'https://example.com',
'prompt' => 'Find board meeting minutes from 2025',
'parameters' => [
'single_page' => false,
'timeout' => 1800,
'confidence_threshold' => 0.1,
'file_type' => 'document',
'max_file_size_mb' => 100
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.skop.dev/scrape/"
payload := strings.NewReader("{\n \"website\": \"https://example.com\",\n \"prompt\": \"Find board meeting minutes from 2025\",\n \"parameters\": {\n \"single_page\": false,\n \"timeout\": 1800,\n \"confidence_threshold\": 0.1,\n \"file_type\": \"document\",\n \"max_file_size_mb\": 100\n }\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
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.skop.dev/scrape/")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"website\": \"https://example.com\",\n \"prompt\": \"Find board meeting minutes from 2025\",\n \"parameters\": {\n \"single_page\": false,\n \"timeout\": 1800,\n \"confidence_threshold\": 0.1,\n \"file_type\": \"document\",\n \"max_file_size_mb\": 100\n }\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.skop.dev/scrape/")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"website\": \"https://example.com\",\n \"prompt\": \"Find board meeting minutes from 2025\",\n \"parameters\": {\n \"single_page\": false,\n \"timeout\": 1800,\n \"confidence_threshold\": 0.1,\n \"file_type\": \"document\",\n \"max_file_size_mb\": 100\n }\n}"
response = http.request(request)
puts response.read_body{
"job_id": "job_4fc79a89797e",
"status": "pending",
"message": "Job created successfully and queued for processing",
"estimated_completion": "2023-11-07T05:31:56Z",
"created_at": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}{
"error": true,
"message": "<string>",
"status_code": 123,
"path": "<string>",
"timestamp": "2023-11-07T05:31:56Z"
}Creates a new document scraping job that runs asynchronously in the background.
Request Body
{
"website": "https://example.com",
"prompt": "Find all board meeting minutes from 2025",
"parameters": {
"single_page": false,
"timeout": 1800,
"confidence_threshold": 0.7,
"file_type": "document",
"max_file_size_mb": 100
}
}
Required Fields
| Field | Type | Description |
|---|---|---|
website | string | Starting URL to scrape (must be valid HTTP/HTTPS URL) |
prompt | string | Description of documents to find (10-500 characters) |
Parameters Object
| Field | Type | Default | Description |
|---|---|---|---|
single_page | boolean | true | Only scrape the provided URL (no navigation) |
timeout | integer | 1800 | Max time in seconds (60-3600) |
confidence_threshold | float | 0.1 | Min AI confidence score (0.0-1.0) |
file_type | string | "document" | Type of files to extract |
max_file_size_mb | integer | 100 | Max file size in MB (1-500) |
Example Request
const response = await fetch('https://api.skop.dev/scrape/', {
method: 'POST',
headers: {
'Authorization': 'Bearer sk-your-api-key',
'Content-Type': 'application/json'
},
body: JSON.stringify({
website: 'https://example.com',
prompt: 'Find meeting minutes for 2025',
parameters: {
single_page: true,
timeout: 1800,
confidence_threshold: 0.7,
file_type: 'document',
max_file_size_mb: 100
}
})
})
const job = await response.json()
Response (201 Created)
{
"job_id": "job_4fc79a89797e",
"status": "pending",
"message": "Job created successfully and queued for processing",
"estimated_completion": "2025-07-24T21:00:00Z",
"created_at": "2025-07-24T20:50:00Z"
}
Response Fields
| Field | Type | Description |
|---|---|---|
job_id | string | Unique identifier for the created job |
status | string | Initial job status (always pending) |
message | string | Success message |
estimated_completion | string | ISO 8601 estimated completion time |
created_at | string | ISO 8601 job creation timestamp |
Error Responses
| Status | Error Code | Description |
|---|---|---|
400 | validation_error | Invalid request parameters |
402 | insufficient_credits | Not enough credits |
429 | concurrency_limit_exceeded | Too many concurrent jobs |
503 | service_unavailable | Required services not configured |
Authorizations
API key in format 'sk-xxxxxxxxxxxxx' or 'sk_xxxxxxxxxxxxx'
Body
application/json
Response
Job created successfully
Unique identifier for the created job
Pattern:
^job_[a-z0-9]+$Example:
"job_4fc79a89797e"
Initial job status (always 'pending')
Available options:
pending Success message
Example:
"Job created successfully and queued for processing"
ISO 8601 estimated completion time
ISO 8601 job creation timestamp
⌘I