Get website datasource details
curl --request GET \
--url http://localhost:8080/crawl/{id} \
--header 'Authorization: Bearer <token>'import requests
url = "http://localhost:8080/crawl/{id}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('http://localhost:8080/crawl/{id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_PORT => "8080",
CURLOPT_URL => "http://localhost:8080/crawl/{id}",
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 := "http://localhost:8080/crawl/{id}"
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("http://localhost:8080/crawl/{id}")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("http://localhost:8080/crawl/{id}")
http = Net::HTTP.new(url.host, url.port)
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"url": "<string>",
"display_name": "<string>",
"status": "<string>",
"page_limit": 123,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 123,
"restricted_to_channels": [
"web"
],
"last_crawl_started_at": "2023-11-07T05:31:56Z",
"last_crawl_completed_at": "2023-11-07T05:31:56Z",
"error_message": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"auth_configured": true,
"auth_type": "basic",
"page_stats": {
"total": 123,
"synced": 123,
"pending": 123,
"error": 123,
"excluded": 123
},
"active_crawl_job": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "<string>",
"total_pages": 123,
"completed_pages": 123,
"new_pages": 123,
"updated_pages": 123,
"removed_pages": 123,
"unchanged_pages": 123,
"started_at": "2023-11-07T05:31:56Z"
}
}{
"statusCode": 123,
"message": "<string>",
"error": "<string>"
}Crawl
Get website datasource details
Get website datasource details — Retrieve a website datasource with page statistics and active crawl job information.
GET
/
crawl
/
{id}
Get website datasource details
curl --request GET \
--url http://localhost:8080/crawl/{id} \
--header 'Authorization: Bearer <token>'import requests
url = "http://localhost:8080/crawl/{id}"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('http://localhost:8080/crawl/{id}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_PORT => "8080",
CURLOPT_URL => "http://localhost:8080/crawl/{id}",
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 $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "http://localhost:8080/crawl/{id}"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("http://localhost:8080/crawl/{id}")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("http://localhost:8080/crawl/{id}")
http = Net::HTTP.new(url.host, url.port)
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"url": "<string>",
"display_name": "<string>",
"status": "<string>",
"page_limit": 123,
"exclude_paths": [
"<string>"
],
"include_paths": [
"<string>"
],
"crawl_interval_hours": 123,
"restricted_to_channels": [
"web"
],
"last_crawl_started_at": "2023-11-07T05:31:56Z",
"last_crawl_completed_at": "2023-11-07T05:31:56Z",
"error_message": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"auth_configured": true,
"auth_type": "basic",
"page_stats": {
"total": 123,
"synced": 123,
"pending": 123,
"error": 123,
"excluded": 123
},
"active_crawl_job": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"status": "<string>",
"total_pages": 123,
"completed_pages": 123,
"new_pages": 123,
"updated_pages": 123,
"removed_pages": 123,
"unchanged_pages": 123,
"started_at": "2023-11-07T05:31:56Z"
}
}{
"statusCode": 123,
"message": "<string>",
"error": "<string>"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
The website datasource ID
Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Response
Default Response
Pattern:
^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$Channels this datasource is restricted to. Empty = available on all channels.
Available options:
web, email, phone_voice, slack, sms, whatsapp, instagram, messenger, api, web_voice, twitter, twitter_mentions, app_review, internal Whether optional Firecrawl site auth is configured. Secrets are never returned.
Configured auth type, or null when auth is not set.
Available options:
basic, bearer, cookie, headers Show child attributes
Show child attributes
Show child attributes
Show child attributes
Was this page helpful?