> ## Documentation Index
> Fetch the complete documentation index at: https://developers.leadwaycrm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Get all trained page links by knowledge base

```http theme={null}
GET https://services.leadconnectorhq.com/knowledge-bases/crawler
```

## Autorización

<ParamField header="Authorization" type="string" required>
  Bearer token generado desde el portal Leadway. Ver [Autenticación](/authentication).
</ParamField>

<ParamField header="Version" type="string" required default="2021-07-28">
  Versión de la API.
</ParamField>

## Query parameters

<ParamField query="knowledgeBaseId" type="string" required default="tDtDnQdgm2LXpyiqYvZ6">
  knowledge base ID as string
</ParamField>

<ParamField query="locationId" type="string" required default="tDtDnQdgm2LXpyiqYvZ6">
  account ID as string
</ParamField>

<ParamField query="page" type="number" default="1">
  Page number
</ParamField>

<ParamField query="pageLength" type="number" default="1">
  Records per page
</ParamField>

<ParamField query="query" type="string" default="www.example.com/">
  query to filter on url links
</ParamField>

## Respuestas

<Accordion title="200 - Trained page links retrieved successfully">
  <ResponseField name="count" type="number" required default="64">
    Total count of URLs in the knowledge base
  </ResponseField>

  <ResponseField name="urls" type="object[]" required>
    Array of crawled URLs with their details

    <Expandable title="cada item">
      <ResponseField name="id" type="string" required default="688c73a25275c513f5f3a7de">
        Unique identifier for the URL
      </ResponseField>

      <ResponseField name="url" type="string" required default="https://developer.mozilla.org/en-US/blog">
        The actual URL that was crawled
      </ResponseField>

      <ResponseField name="title" type="string" required default="MDN Blog">
        Title of the webpage
      </ResponseField>

      <ResponseField name="status" type="string" required default="Successful">
        Current processing status of the URL Posibles valores: 'Pending', 'Processing', 'Successful', 'Failed', 'Existing', 'Restricted', 'Cancelled', 'Aborted', 'Training'
      </ResponseField>

      <ResponseField name="locationId" type="string" required default="qIyivCmsuEOSnyoFYEej">
        Account ID associated with this URL
      </ResponseField>

      <ResponseField name="knowledgeBaseId" type="string" required default="Arc9QRauPKkSuMJO8D0m">
        Knowledge base ID this URL belongs to
      </ResponseField>

      <ResponseField name="content" type="string" required default="https://storage.googleapis.com/crm-conversations-ai-staging/conversationAI/2025/8/1/locations/qIyivCmsuEOSnyoFYEej/688c739c88c89f21ad30f63e-4IseusbZ3vDXMT8WNw9M.txt">
        URL to the stored content file
      </ResponseField>

      <ResponseField name="contentEditedByUser" type="boolean" required default="False">
        Whether the content was edited by user
      </ResponseField>

      <ResponseField name="updatedAt" type="string" required default="2025-08-01T07:58:29.858Z">
        Last updated timestamp
      </ResponseField>
    </Expandable>
  </ResponseField>

  ```json theme={null}
  {
    "count": 64,
    "urls": [
      {
        "id": "688c73a25275c513f5f3a7de",
        "url": "https://developer.mozilla.org/en-US/blog",
        "title": "MDN Blog",
        "status": "Successful",
        "locationId": "qIyivCmsuEOSnyoFYEej",
        "knowledgeBaseId": "Arc9QRauPKkSuMJO8D0m",
        "content": "https://storage.googleapis.com/crm-conversations-ai-staging/conversationAI/2025/8/1/locations/qIyivCmsuEOSnyoFYEej/688c739c88c89f21ad30f63e-4IseusbZ3vDXMT8WNw9M.txt",
        "contentEditedByUser": false,
        "updatedAt": "2025-08-01T07:58:29.858Z"
      }
    ]
  }
  ```
</Accordion>

<Accordion title="400 - Bad Request">
  <ResponseField name="statusCode" type="number" default="400" />

  <ResponseField name="message" type="string" default="Bad Request" />

  ```json theme={null}
  {
    "statusCode": 400,
    "message": "Bad Request"
  }
  ```
</Accordion>

<Accordion title="401 - Unauthorized">
  <ResponseField name="statusCode" type="number" default="401" />

  <ResponseField name="message" type="string" default="Invalid token: access token is invalid" />

  <ResponseField name="error" type="string" default="Unauthorized" />

  ```json theme={null}
  {
    "statusCode": 401,
    "message": "Invalid token: access token is invalid",
    "error": "Unauthorized"
  }
  ```
</Accordion>

<Accordion title="422 - Unprocessable Entity">
  <ResponseField name="statusCode" type="number" default="422" />

  <ResponseField name="message" type="string[]" />

  <ResponseField name="error" type="string" default="Unprocessable Entity" />

  ```json theme={null}
  {
    "statusCode": 422,
    "message": [
      "Unprocessable Entity"
    ],
    "error": "Unprocessable Entity"
  }
  ```
</Accordion>

<Accordion title="500 - Internal Server Error">
  <ResponseField name="statusCode" type="number" default="500" />

  <ResponseField name="message" type="string" default="Internal Server Error" />

  ```json theme={null}
  {
    "statusCode": 500,
    "message": "Internal Server Error"
  }
  ```
</Accordion>

## Ejemplo

<CodeGroup>
  ```bash cURL theme={null}
  curl -X GET 'https://services.leadconnectorhq.com/knowledge-bases/crawler' \
    -H 'Authorization: Bearer YOUR_TOKEN' \
    -H 'Version: 2021-07-28'
  ```

  ```javascript Node.js theme={null}
  const response = await fetch('https://services.leadconnectorhq.com/knowledge-bases/crawler', {
    method: 'GET',
    headers: {
      Authorization: `Bearer ${process.env.LEADWAY_TOKEN}`,
      Version: '2021-07-28',
    },
  });
  const data = await response.json();
  ```

  ```python Python theme={null}
  import os, requests
  response = requests.request(
      'GET',
      'https://services.leadconnectorhq.com/knowledge-bases/crawler',
      headers={
          'Authorization': f"Bearer {os.environ['LEADWAY_TOKEN']}",
          'Version': '2021-07-28',
      },
  )
  data = response.json()
  ```

  ```php PHP theme={null}
  <?php
  $ch = curl_init('https://services.leadconnectorhq.com/knowledge-bases/crawler');
  curl_setopt_array($ch, [
      CURLOPT_RETURNTRANSFER => true,
      CURLOPT_CUSTOMREQUEST => 'GET',
      CURLOPT_HTTPHEADER => [
          'Authorization: Bearer ' . getenv('LEADWAY_TOKEN'),
          'Version: 2021-07-28',
      ],
  ]);
  $data = json_decode(curl_exec($ch), true);
  ```
</CodeGroup>
