Get crawler job
curl --request GET \
--url https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId} \
--header 'Authorization: Bearer <token>'import requests
url = "https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}', 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://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($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://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"success": true,
"message": "<string>",
"data": {
"id": "<string>",
"workspaceId": "<string>",
"primaryUrl": "<string>",
"urls": [
"<string>"
],
"crawl": true,
"crawlOptions": {
"maxPages": 250,
"urlMatchers": [
"<string>"
],
"unMatchers": [
"<string>"
],
"stayOnDomain": true
},
"useProxy": true,
"deep": true,
"refreshRate": "<string>",
"toAgentId": "<string>",
"toAgentIds": [
"<string>"
],
"done": true,
"failed": true,
"isCancelled": true,
"message": "<string>",
"resultError": "<string>",
"createdAt": "<string>",
"ts": 123,
"currentPageIndex": 123,
"scrapedPagesNum": 123,
"failedPagesNum": 123,
"pageLimit": 123,
"creditsPerPage": 123,
"estimatedCredits": 123,
"activeScrapeUrl": "<string>",
"crawlerJobId": "<string>",
"scrapedUrls": [
"<string>"
],
"scrapedHashes": [
"<string>"
],
"pendingCandidateUrls": [
"<string>"
],
"processedCrawlUrls": [
"<string>"
],
"failedCrawlUrls": [
"<string>"
],
"webhookFinalizedAt": "<string>",
"processingMode": "<string>",
"crawlerSubmittedAt": "<string>",
"crawlerWebhookUrl": "<string>",
"crawlerSubmissionEndpoint": "<string>",
"webhook": {
"url": "<string>",
"events": [],
"hasSecret": true,
"hasBearerToken": true,
"headerKeys": [
"<string>"
]
}
}
}{
"message": "<string>",
"code": "<string>",
"issues": [
{
"message": "<string>"
}
]
}Crawler
Get Crawler Job
Gets a single crawler job by id using the V3 API.
GET
/
workspaces
/
{workspaceId}
/
crawler
/
jobs
/
{jobId}
Get crawler job
curl --request GET \
--url https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId} \
--header 'Authorization: Bearer <token>'import requests
url = "https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}', 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://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($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://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://eu-gcp-api.vg-stuff.com/v3/workspaces/{workspaceId}/crawler/jobs/{jobId}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"success": true,
"message": "<string>",
"data": {
"id": "<string>",
"workspaceId": "<string>",
"primaryUrl": "<string>",
"urls": [
"<string>"
],
"crawl": true,
"crawlOptions": {
"maxPages": 250,
"urlMatchers": [
"<string>"
],
"unMatchers": [
"<string>"
],
"stayOnDomain": true
},
"useProxy": true,
"deep": true,
"refreshRate": "<string>",
"toAgentId": "<string>",
"toAgentIds": [
"<string>"
],
"done": true,
"failed": true,
"isCancelled": true,
"message": "<string>",
"resultError": "<string>",
"createdAt": "<string>",
"ts": 123,
"currentPageIndex": 123,
"scrapedPagesNum": 123,
"failedPagesNum": 123,
"pageLimit": 123,
"creditsPerPage": 123,
"estimatedCredits": 123,
"activeScrapeUrl": "<string>",
"crawlerJobId": "<string>",
"scrapedUrls": [
"<string>"
],
"scrapedHashes": [
"<string>"
],
"pendingCandidateUrls": [
"<string>"
],
"processedCrawlUrls": [
"<string>"
],
"failedCrawlUrls": [
"<string>"
],
"webhookFinalizedAt": "<string>",
"processingMode": "<string>",
"crawlerSubmittedAt": "<string>",
"crawlerWebhookUrl": "<string>",
"crawlerSubmissionEndpoint": "<string>",
"webhook": {
"url": "<string>",
"events": [],
"hasSecret": true,
"hasBearerToken": true,
"headerKeys": [
"<string>"
]
}
}
}{
"message": "<string>",
"code": "<string>",
"issues": [
{
"message": "<string>"
}
]
}Overview
Returns one crawler job with its current processing state, scraped URL tracking, and webhook metadata.Crawler jobs cannot be updated after submission. This endpoint is read-only.
Typical Use Cases
- Polling job progress
- Reading final job status
- Inspecting webhook delivery configuration
- Reviewing discovered and processed URLs
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
⌘I
