Web Crawler

Crawl public or internal websites directly in meinGPT and make them searchable

Set up in meinGPT

Open Settings → Data sources, click Add data source, and choose Web Crawler. Enter the Start URL and click Connect — every other field is optional and has a sensible default.

The web crawler runs as a Cloud data source; it needs no Outpost of your own, and this source type is not currently supported for that.

Basic settings

FieldDefaultDescription
Start URLThe URL the crawler starts from
Scraping MethodBasic (HTTP)Basic uses HTTP requests, Browser enables JavaScript rendering — needed for pages that load content via JS
Max Depth3How many clicks deep the crawler follows from the start URL
Max Pages1000Upper bound on the number of pages crawled

Login (optional)

For password-protected intranets: the crawler signs in once and stays signed in for the whole crawl.

FieldDescription
Login URLTarget URL of the login form — must use HTTPS
Username / PasswordCredentials for the login form

Advanced settings

FieldDefaultDescription
Include / Exclude PathsURL path regex patterns, one per line
Wait for SelectorBrowser mode only: CSS selector to wait for before extraction
Page Timeout30sTimeout per page
Request Delay1.0sWait time between requests
Concurrent Requests5Parallel crawl requests
Retry Attempts2Retries on failure
Output FormatMarkdownMarkdown, HTML, or Text
Main Content OnlyOnExtracts only the main content area, without navigation and footer
Max Age24hPages older than this threshold get re-crawled
Proxy Server / Username / PasswordFor crawls routed through a proxy
User AgentCustom User-Agent string

Synchronization

  • meinGPT crawls from the start URL and stores extracted content per discovered page.
  • Every data pool is checked by the sync scheduler every 15 minutes (see Sync interval); a page is only actually re-crawled once the configured max age (default 24 hours) has passed since it was last crawled.
  • Use path filters to keep crawl scope tight.
Was this page helpful?