Source Syncs and Imports
List Crawl Preview Pages
Lists the pages a crawl preview found, with the page_id to pass to Import Selected Pages. Page content is not returned.
Pages are ordered by page_id, not by their place on the site. While the preview is still crawling, the list is partial.
For the preview-and-import flow, see Import Website Pages.
GET
/
knowledge-fs
/
spaces
/
{knowledge_base_id}
/
source-workflows
/
{run_id}
/
pages
List Crawl Preview Pages
curl --request GET \
--url https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages \
--header 'Authorization: Bearer <token>'import requests
url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages', 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_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages",
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://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages"
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://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages")
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{
"data": [
{
"description": "How invoices, plans, and payment methods work.",
"etag": null,
"page_id": "0b6e9a1f3c5d7e9f1a3b5c7d9e1f3a5b7c9d1e3f5a7b9c1d3e5f7a9b1c3d5e7f",
"source_url": "https://docs.example.com/guides/billing",
"title": "Billing | Docs site"
},
{
"description": null,
"etag": null,
"page_id": "5e0f9a6c2b8d4e1f7a3c9b5d1e7f3a9c5b1d7e3f9a5c1b7d3e9f5a1c7b3d9e5f",
"source_url": "https://docs.example.com/pricing",
"title": "Pricing | Docs site"
}
],
"next_cursor": null
}Authorizations
Every request authenticates with an API key: Authorization: Bearer {API_KEY}. App endpoints take an app API key; knowledge endpoints take a knowledge base API key (Get Started).
Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP 401 (unauthorized).
Path Parameters
Knowledge base ID: the last segment of the Service API endpoint shown in the knowledge base's API Access dialog (…/knowledge-fs/spaces/<knowledge base ID>), and the segment after /datasets/new/ in the address bar.
Run ID of a crawl preview: id from Preview Website Crawl, List Source Runs, or Get Source Run.
Query Parameters
Cursor from the previous page's next_cursor.
Required string length:
1 - 4096Pages per response.
Required range:
1 <= x <= 200Was this page helpful?
⌘I
List Crawl Preview Pages
curl --request GET \
--url https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages \
--header 'Authorization: Bearer <token>'import requests
url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages', 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_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages",
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://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages"
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://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages")
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{
"data": [
{
"description": "How invoices, plans, and payment methods work.",
"etag": null,
"page_id": "0b6e9a1f3c5d7e9f1a3b5c7d9e1f3a5b7c9d1e3f5a7b9c1d3e5f7a9b1c3d5e7f",
"source_url": "https://docs.example.com/guides/billing",
"title": "Billing | Docs site"
},
{
"description": null,
"etag": null,
"page_id": "5e0f9a6c2b8d4e1f7a3c9b5d1e7f3a9c5b1d7e3f9a5c1b7d3e9f5a1c7b3d9e5f",
"source_url": "https://docs.example.com/pricing",
"title": "Pricing | Docs site"
}
],
"next_cursor": null
}