Get Scrape Status
curl --request GET \
--url https://api.example.com/scrape/{jobScrapeId}import requests
url = "https://api.example.com/scrape/{jobScrapeId}"
response = requests.get(url)
print(response.text)const options = {method: 'GET'};
fetch('https://api.example.com/scrape/{jobScrapeId}', 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.example.com/scrape/{jobScrapeId}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
]);
$response = curl_exec($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.example.com/scrape/{jobScrapeId}"
req, _ := http.NewRequest("GET", url, nil)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.example.com/scrape/{jobScrapeId}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/scrape/{jobScrapeId}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
response = http.request(request)
puts response.read_body{
"data": "<string>",
"timestamp": "<string>",
"status": "<string>",
"metrics": "<string>"
}Web Scraping
Get Scrape Status
Retrieve the status of a specific scraping job
GET
/
scrape
/
{jobScrapeId}
Get Scrape Status
curl --request GET \
--url https://api.example.com/scrape/{jobScrapeId}import requests
url = "https://api.example.com/scrape/{jobScrapeId}"
response = requests.get(url)
print(response.text)const options = {method: 'GET'};
fetch('https://api.example.com/scrape/{jobScrapeId}', 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.example.com/scrape/{jobScrapeId}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
]);
$response = curl_exec($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.example.com/scrape/{jobScrapeId}"
req, _ := http.NewRequest("GET", url, nil)
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.example.com/scrape/{jobScrapeId}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.example.com/scrape/{jobScrapeId}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
response = http.request(request)
puts response.read_body{
"data": "<string>",
"timestamp": "<string>",
"status": "<string>",
"metrics": "<string>"
}Overview
The/scrape/{jobScrapeId} endpoint retrieves the status and details of a specific scraping job. This is useful for monitoring long-running or asynchronous scraping operations.
Parameters
string
required
The unique identifier of the scraping job
Example Request
curl -X GET "https://api.scrapengine.io/api/v1/scrape/job_12345_abcde" \
-H "Authorization: Bearer YOUR_API_KEY"
const response = await fetch(
"https://api.scrapengine.io/api/v1/scrape/job_12345_abcde",
{
method: "GET",
headers: {
Authorization: "Bearer YOUR_API_KEY",
},
}
);
const data = await response.json();
console.log(data);
import requests
url = "https://api.scrapengine.io/api/v1/scrape/job_12345_abcde"
headers = {
"Authorization": "Bearer YOUR_API_KEY"
}
response = requests.get(url, headers=headers)
data = response.json()
print(data)
Response
Success Response (200)
string
Session data or status information
string
Timestamp of the response in ISO 8601 format
string
Status of the operation (e.g., “success”, “processing”, “failed”)
string
Performance metrics and timing information
{
"data": "session",
"timestamp": "2024-01-15T10:30:00.000Z",
"status": "success",
"metrics": "100ms"
}
Error Responses
| Status | Description |
|---|---|
401 | Unauthorized - Invalid or missing API key |
404 | Job not found - The specified job ID does not exist |
Use Cases
- Job monitoring: Check the status of asynchronous scraping jobs
- Progress tracking: Monitor long-running scraping operations
- Debugging: Investigate failed or stuck scraping jobs
- Analytics: Collect performance metrics for scraping operations
Was this page helpful?