Collect product details from many web pages and store clean results in Google Sheets. Ideal for marketing teams and ecommerce analysts who need fast product research, price checks, and catalog enrichment without manual copy and paste.

The run starts on a manual click. It reads a list of URLs from a tracking sheet in Google Sheets, then processes them in batches. Each URL is sent to a web scraping API to fetch the page HTML. A code step removes extra tags and noise. The cleaned HTML goes to an AI model through OpenRouter with a strict schema so fields like name, price, rating, reviews, and description come back in a consistent JSON format. The results are split into items and appended to a results sheet. The loop continues until all URLs are done.

Plan for two Google Sheets tabs, one for URLs and one for results. You will need a Bright Data API token and an OpenRouter API key. Expect faster research, fewer errors, and a steady data format that is ready for analysis. Common uses include competitor tracking, marketplace scans, and building product lists for campaigns or feeds.

• Reads URL lists from a Google Sheets tab for simple queue management
• Processes links in batches to control load and avoid timeouts
• Calls a web scraping API with an auth token to fetch page HTML
• Cleans raw HTML in a code step to remove scripts, styles, and noise
• Uses an AI model via OpenRouter to extract product fields from the cleaned HTML
• Enforces a structured JSON output with a defined schema
• Appends results to a separate Google Sheets tab for reporting and analysis

• Reduce manual work from 5 hours to 20 minutes for a typical product list
• Streamline product research by about 80 percent with one click runs
• Improve data quality by 90 percent using a strict JSON schema
• Handle 10 times more pages without extra staff
• Connect Google Sheets, Bright Data, and OpenRouter in one flow

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 Sheets, Bright Data and OpenRouter. See the Tools Required section above for links to create accounts with these services.
3. Prepare your Google Sheet: create one tab for tracking URLs with a column named url and a second tab for results with columns for name, price, rating, reviews, and description.
4. In n8n, open the Google Sheets nodes. In the Credential to connect with dropdown, click Create new credential, then follow the on screen instructions to sign in with Google and grant access.
5. Find your Google Sheets document ID and the tab names or GIDs. Enter these values in the get urls to scrape and add results nodes so they point to the correct sheet and tabs.
6. Create a Bright Data API token in your Bright Data dashboard. In n8n Cloud, go to Settings or Variables and add an environment variable named BRIGHTDATA_TOKEN with your token value. You can also paste the token directly in the HTTP header if testing.
7. Open the HTTP Request node and confirm the Authorization header uses {{BRIGHTDATA_TOKEN}} and that the body has zone, url, and format set to raw.
8. Create an OpenRouter API key in your OpenRouter account. In the OpenRouter Chat Model node, choose Create new credential and enter the key. Keep the model as a supported option.
9. Open the extract data node and review the prompt. Make sure the requested fields match the columns you plan to store. Adjust field names only if you also update the results mapping.
10. Check the Structured Output Parser node schema. Confirm it defines the fields you want like name, description, rating, reviews, and price.
11. Click Execute workflow to run a small test. Confirm that the scrap url node returns HTML, the clean html node returns cleanedHtml, and the extract data node outputs JSON with the expected fields.
12. If you get a 401 or 403 on the HTTP Request, recheck your Bright Data token and zone. If Google Sheets fails to write, verify you selected the right spreadsheet and that your Google account has edit access.