Build a clean research library from any website sitemap and save it as markdown files in Google Drive. Ideal for content teams that need quick audits, topic research, or backups without manual copy and paste.

Here is how it works. You start the run manually. A sitemap URL is set, then a web request pulls the XML and converts it to JSON. The list of pages is split out, optional filters keep only the pages you care about, and a limit controls how many links to process per run. Each URL is fetched through a readable page endpoint, a small code step extracts the title and markdown, and each page is stored as a text file in Google Drive. A wait step can slow the loop to respect rate limits.

Setup is simple. You only need a Google Drive connection in n8n Cloud, a valid sitemap URL, and a folder to store files. Expect faster content reviews, organized files named by page title, and less time spent copying text from the browser. Great for SEO snapshots, competitor scans, and internal documentation backups.

• Manual start for full control of when scraping runs
• Set node defines the sitemap URL you want to capture
• HTTP request downloads the sitemap XML
• XML to JSON converts the sitemap into a usable list
• Split out creates one item per page URL from urlset.url
• Filter node keeps only topics or paths you care about
• Limit node caps how many pages process in a single run
• Batch loop fetches each page via a readable endpoint
• Code step extracts the title and markdown for storage
• Google Drive creates a text file named with URL and title
• Wait step adds a pause to manage pacing or rate limits

• Reduce manual copy and paste from hours to minutes
• Automate up to 90 percent of collection work from a sitemap
• Handle 20 pages per run by default and scale higher by raising the limit
• Improve consistency by pulling every page from the sitemap structure
• Keep content organized in Google Drive with clear file names

1. Import the template into n8n: Create a new workflow in n8n > Click the three dots menu > Select 'Import from File' > Choose the downloaded JSON file.
2. You'll need accounts with Google Drive. See the Tools Required section above for links to create accounts with these services.
3. In n8n Cloud, open Credentials > New > Choose Google Drive. If unsure, double click the Google Drive node and in the Credential to connect with dropdown, click Create new credential and follow the on screen steps to sign in with OAuth2.
4. Open the Google Drive node. Select your Google Drive credential. Choose the target folder or leave root to save files at the top level.
5. Open the Set Website URL node and replace the sample sitemap link with the sitemap you want to capture.
6. Run the Get List of Website URLs node in isolation. Confirm you get a 200 response and XML content.
7. Check the Convert to JSON and Create List of Website URLs nodes. Verify each item has a loc field with a full page URL.
8. Update the Filter By Topics or Pages node with your keywords or paths to include. If you need everything, disable or clear the conditions.
9. Adjust the Limit node to control how many pages run per test. Start with 20 to keep it safe for the target site.
10. Open the Wait node and set a small delay if you see rate limits or Drive throttling. This helps avoid errors during loops.
11. Click Test workflow to run end to end. Watch items pass through the loop and confirm new markdown files appear in your Google Drive with the expected names.
12. If files are empty, check the code node output. If the sitemap structure differs, update the Split Out field path or the selector used in the code step.