Turn any web page into structured insights for marketing research. The flow pulls a page through Bright Data, strips it to clean text, and uses AI to extract topics, sentiment, and trends by location and category. Teams use it to scan news or sites and get ready to use data without manual reading.

On click, the workflow sets your target URL and zone, then calls Bright Data Web Unlocker to fetch the page. A markdown to text chain cleans the content so it has no scripts or links. Two AI extractors, powered by Google Gemini, return topic models with sentiment and a second view of trends grouped by place and category. Results are posted to a webhook endpoint for alerts and saved to files for downstream use. This creates a repeatable pipeline that produces structured outputs from messy pages.

Update the URL and zone, add your API keys, and replace the sample webhook links. Expect research time to drop while consistency goes up because the schema is fixed. Use it for content research, brand monitoring, competitive scans, and editorial planning where fast, structured insights matter.

• Manual run to fetch any target page on demand
• Bright Data Web Unlocker request to reliably load the page
• Markdown to text conversion that removes links, scripts, and styling
• Google Gemini models drive topic analysis and custom sentiment
• Second extractor returns trends grouped by location and category
• Webhook notifications send plain text, sentiment, and trend results
• Function nodes package results into binary files
• Write to disk nodes store topic and trend outputs for reuse

• Reduce manual research from hours to minutes per page
• Automate up to 80% of topic tagging and sentiment scoring
• Improve data consistency by using a fixed output schema
• Connect data capture, AI analysis, and alerts in one flow
• Save results as files for quick handoff to BI or data teams

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 Bright Data, Google Gemini and Webhook.site. See the Tools Required section above for links to create accounts with these services.
3. In the n8n credentials manager, create a Bright Data HTTP Header Auth credential. If you are unsure, double click the Bright Data HTTP Request node, choose 'Credential to connect with' > 'Create new credential', then add an Authorization header with your API key as instructed on the Bright Data API page.
4. Create a Google Gemini credential. Double click each Gemini model node, choose 'Credential to connect with' > 'Create new credential', then paste your API key from the Google AI Studio API page.
5. Open the Set URL and Bright Data Zone node and enter your target page URL and your Bright Data zone name.
6. Replace the sample Webhook.site URLs in all three HTTP Request nodes that send notifications with your own Webhook.site URL or your real endpoint.
7. Click Execute or Test workflow to run it. Watch the Perform Bright Data Web Request node to confirm you get a 200 response and a data payload.
8. Check the Markdown to Textual Data Extractor output. You should see clean text with no links or scripts. If empty, verify the target page and Bright Data credentials.
9. Review the two information extractor nodes. Confirm you receive structured fields for topics, sentiment, and trends by location and category.
10. Open the write to disk nodes and confirm the file paths work in your environment. If files do not appear, set a valid directory path and run again.
11. If webhooks do not receive data, copy a fresh URL from Webhook.site and paste it into each notification node, then test again.