# Google SERP + trends and recommendations with Bright Data: n8n workflow

> Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Gemini.

Source: https://millionrounds.com/workflow/google-serp-trends-and-recommendations-with-bright-data (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [AI assistants](https://millionrounds.com/workflows?category=AI+assistants#library)

# Google SERP + trends and recommendations with Bright Data

Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Gemini. 20 steps, 1 loop or waits: a working afternoon to understand properly.

Medium Calls a model: Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgoogle-serp-trends-and-recommendations-with-bright-data)

**20 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**1** Loop or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 1 Model 9 Logic 5 Service 5

The steps in the order they run, from what starts it.

- 1 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 2 **Google Gemini Chat Model for Google Search** Lm Chat Google Gemini *Model*
- 3 **Structured Output Parser for Google Search** Output Parser Structured *Model*
- 4 **Google Gemini Chat Model for Trend Data** Lm Chat Google Gemini *Model*
- 5 **Google Gemini Chat Model for Recommendation** Lm Chat Google Gemini *Model*
- 6 **Structured Output Parser for Recommendation** Output Parser Structured *Model*
- 7 **Structured Output Parser for Trend Data** Output Parser Structured *Model*
- 8 **Set input fields** Set *Logic*
- 9 **Google Search Data Extractor** Chain Llm *Model*
- 10 **Trends Data Extractor** Chain Llm *Model*
- 11 **Recommendation Data Extractor** Chain Llm *Model*
- 12 **Perform Bright Data Web Request** Http Request *Service*
- 13 **Code** Code *Logic*
- 14 **Code for Trends** Code *Logic*
- 15 **Code for Recommendations** Code *Logic*
- 16 **Loop Over Items** Split In Batches *Logic*
- 17 **Convert to File for Trends** Convert To File *Service*
- 18 **Convert to File for Recommendations** Convert To File *Service*
- 19 **Write the trends csv file to disk** Read Write File *Service*
- 20 **Write the recommendations csv file to disk** Read Write File *Service*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 20, 1 loop or waits
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Gemini

## Questions

What does it need to run?

An n8n account, and a key for Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 20 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 20 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgoogle-serp-trends-and-recommendations-with-bright-data)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also ai assistants, with the same services where possible, closest in size first.

- [**Automate GitHub PR linting with Gemini** 20 steps · calls a model](https://millionrounds.com/workflow/automate-github-pr-linting-with-gemini)
- [**Automated AI media creation with MagicHour AI and OpenAI** 20 steps · calls a model](https://millionrounds.com/workflow/automated-ai-media-creation-with-magichour-ai-and-openai)
- [**Automatic jest test generation for GitHub PRs with OpenAI** 20 steps · calls a model · GitHub](https://millionrounds.com/workflow/automatic-jest-test-generation-for-github-prs-with-openai)
- [**Combine answers from OpenAI, Anthropic, Gemini** 20 steps · calls a model](https://millionrounds.com/workflow/combine-answers-from-openai-anthropic-gemini)
- [**Create a RAG system with Paul Essays and Milvus** 20 steps · calls a model](https://millionrounds.com/workflow/create-a-rag-system-with-paul-essays-and-milvus)
- [**Create a knowledge base chatbot with Google Drive and OpenAI** 20 steps · calls a model · Google Drive, in-memory vectors](https://millionrounds.com/workflow/create-a-knowledge-base-chatbot-with-google-drive-and-openai)