Facebook Ads Library to Google Sheets, insights logged
Your competitor launches three new ads and you only notice a week later. Or you do notice, but the “research” lives in screenshots, random Slack messages, and a sheet nobody trusts. It’s messy.
Paid media managers feel it first. A marketing lead trying to guide creative direction feels it too. And if you run a small agency, you’ve probably rebuilt the same “competitor swipe file” five times. This Ads Library Sheets automation turns that chaos into a repeatable system.
You submit a keyword, the workflow pulls matching ads from Facebook Ads Library, analyzes the creative (image and video), and logs consistent notes into Google Sheets. Below is how it works, what you get, and what to watch for.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Facebook Ads Library to Google Sheets, insights logged
flowchart LR
subgraph sg0["On form submission Flow"]
direction LR
n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/form.svg' width='40' height='40' /></div><br/>On form submission"]
n1["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Scrape Ads"]
n2@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Switch", pos: "b", h: 48 }
n3@{ icon: "mdi:robot", form: "rounded", label: "OpenAI", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Extract from File", pos: "b", h: 48 }
n5["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Gemini Video Decode"]
n6["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Download Video"]
n7@{ icon: "mdi:swap-vertical", form: "rounded", label: "Final Image Values", pos: "b", h: 48 }
n8@{ icon: "mdi:swap-vertical", form: "rounded", label: "Final Video Values", pos: "b", h: 48 }
n9["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/merge.svg' width='40' height='40' /></div><br/>Merge"]
n10@{ icon: "mdi:database", form: "rounded", label: "Save", pos: "b", h: 48 }
n11@{ icon: "mdi:swap-vertical", form: "rounded", label: "Loop Over Items", pos: "b", h: 48 }
n12@{ icon: "mdi:cog", form: "rounded", label: "Wait", pos: "b", h: 48 }
n12 --> n5
n9 --> n10
n3 --> n7
n2 --> n6
n2 --> n3
n1 --> n2
n6 --> n4
n11 --> n8
n11 --> n12
n4 --> n11
n7 --> n9
n8 --> n9
n0 --> n1
n5 --> n11
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n0 trigger
class n3 ai
class n2 decision
class n10 database
class n1,n5,n6 api
classDef customIcon fill:none,stroke:none
class n0,n1,n5,n6,n9 customIcon
The Problem: Competitor ad research is slow and inconsistent
Competitor research should be a quick habit. In reality, it becomes a half-day project: open Ads Library, search a few keywords, click into ads, copy links, grab screenshots, then try to write “insights” that make sense later. Next week you do it again, but you describe things differently, miss the same details, and can’t compare anything cleanly. Worse, video ads are painful because you can’t skim them. You either watch the whole thing or ignore it, which is how good ideas slip through.
It adds up fast. Here’s where the process usually breaks down.
- You lose time re-finding ads because the original link or page ID wasn’t captured consistently.
- Notes vary by person and mood, so “what worked” is hard to spot later in a spreadsheet.
- Video ads rarely get analyzed properly, which means you miss hooks, offers, and spoken CTAs.
- Teams end up with a swipe file that looks full, but isn’t searchable or reusable.
The Solution: Keyword-based Ads Library logging with AI summaries
This workflow starts with a simple keyword submission through a form. n8n then retrieves matching listings from Facebook Ads Library (via an HTTP request setup, typically powered by a scraping provider like Apify). Each ad is routed based on what it contains: image creatives go one way, video creatives go another. For images, an AI model describes what’s on screen and pulls out visible text so you don’t rely on subjective notes. For videos, the workflow downloads the asset, breaks it into frames, and sends those frames for analysis so you get a usable description of visuals and any spoken content. Finally, everything is compiled into a clean, consistent row format and stored in Google Sheets for quick filtering and team reuse.
The workflow begins when someone submits a keyword. Then it collects ads, splits them by media type, and generates structured creative notes. The finished output lands in your Google Sheet, ready for sorting by brand, hook, CTA, or landing page.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you track 5 competitor brands and you research 3 keywords every week. Manually, it’s easy to spend about 20 minutes per keyword just collecting links, screenshots, and rough notes, which is roughly 3 hours a week. With this workflow: you submit the keyword in under a minute, wait for processing (often around 10–15 minutes depending on videos), and your Google Sheet fills in with structured insights. You still review and decide what matters, but you stop doing the busywork.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Google Sheets for storing and sharing the research log.
- Apify to retrieve Ads Library listings reliably.
- OpenAI API key (get it from the OpenAI dashboard API keys page).
- Gemini API credentials (get them from Google AI Studio).
Skill level: Intermediate. You’ll connect accounts, paste API keys, and confirm your Sheet columns match the workflow fields.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A keyword submission triggers the run. Someone on your team submits a keyword through the built-in form trigger (you can also adapt it to a webhook or Telegram message later).
Ads are retrieved and routed. n8n pulls matching Ads Library listings, then routes each result based on the creative type so images and videos get handled properly.
AI generates consistent creative notes. Images are analyzed to describe what’s shown and what text appears. Videos are fetched, parsed, decoded into frames in batches, and analyzed so you get an understandable summary instead of “watch it and guess.” A Wait node is used so processing stays stable when a provider needs a moment.
Everything lands in Google Sheets. The image and video outputs are merged, fields are cleaned up, and the workflow stores each ad as a structured row your team can filter, tag, and reuse.
You can easily modify the keywords source to come from Gmail, a CRM, or a Slack request based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Form Trigger
This workflow begins when a user submits the n8n form. You’ll set the form input to capture the competitor or campaign details needed to fetch ad listings.
- Add and open Form Submission Trigger.
- Configure the form fields to capture the competitor name, ad platform, or search criteria you want to analyze.
- Save the node to generate a shareable form URL for submissions.
Step 2: Retrieve and Route Ad Listings
Next, the workflow fetches ads and routes them by format so images and videos can be processed separately.
- Open Retrieve Ad Listings and set the request details to the ad listing API you use.
- Connect Form Submission Trigger to Retrieve Ad Listings so form inputs drive the API call.
- Open Route by Ad Type and configure the switch conditions to separate image and video ads.
- Confirm the execution flow: Retrieve Ad Listings → Route by Ad Type.
- Route by Ad Type outputs to both Fetch Video Asset and AI Image Analysis in parallel.
Step 3: Set Up Image Analysis with AI
The image path analyzes ad creatives and prepares structured results for reporting.
- Open AI Image Analysis and configure the prompt or model settings for extracting insights from images.
- Credential Required: Connect your OpenAI credentials in AI Image Analysis.
- Open Assemble Image Output and map the AI results into clean fields for downstream storage.
- Verify the path: AI Image Analysis → Assemble Image Output → Combine Media Results.
Step 4: Process Video Ads and Batch Frames
The video path fetches video assets, parses media, decodes frames, and assembles results in batches.
- Open Fetch Video Asset and configure the HTTP request to download the video file using data from Route by Ad Type.
- Open Parse Video File to extract video metadata or file structure needed for frame decoding.
- Open Decode Video Frames and configure the request to your frame decoding service or endpoint.
- Open Iterate Media Batches and set the batch size appropriate for your frame processing limits.
- Iterate Media Batches outputs to both Assemble Video Output and Pause for Processing in parallel.
- Open Pause for Processing if you need a delay between batch processing cycles.
- Open Assemble Video Output and map the processed frame results into structured output fields.
Step 5: Combine and Store Results
Both image and video outputs are merged and written to Google Sheets for reporting.
- Open Combine Media Results and confirm it merges input from Assemble Image Output and Assemble Video Output.
- Open Store in Sheets and select the spreadsheet and worksheet for storing results.
- Credential Required: Connect your Google Sheets credentials in Store in Sheets.
- Confirm the final flow: Combine Media Results → Store in Sheets.
Step 6: Test and Activate Your Workflow
Run a full test to ensure both image and video paths produce results and that data is written to your sheet.
- Click Execute Workflow and submit a test entry through Form Submission Trigger.
- Verify that Retrieve Ad Listings returns ad data and that Route by Ad Type correctly branches.
- Confirm that AI Image Analysis and the video path complete and that Store in Sheets records a new row.
- Once successful, toggle the workflow to Active for production use.
Common Gotchas
- Google Sheets credentials can expire or need specific permissions. If things break, check the connected Google account inside n8n’s Credentials page first.
- If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.
Frequently Asked Questions
About 20 minutes if you already have your API keys.
No. You connect accounts and paste a few credentials. The rest is mostly mapping fields into Google Sheets.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in API costs for Apify, OpenAI, and Gemini, which vary based on how many ads and videos you process.
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
Yes, and it’s a common upgrade. You can swap the Form Submission Trigger for a Webhook, Gmail trigger, or Telegram trigger, then pass the message text into the same “retrieve listings” step. Many teams also add a second Google Sheet tab for “keywords requested” so you can track who asked for what. If you want scoring, you can extend the AI prompts to output a rating and a short test recommendation.
Usually it’s an expired Google authorization or the wrong Google account connected in n8n. Reconnect the Google Sheets credential, then confirm the spreadsheet is shared with that account. Also check that the target sheet and tab name still match what the workflow expects. If you recently changed columns, you may need to remap fields so writes don’t fail.
A typical small-team setup can comfortably log a few hundred ads per week, and self-hosting removes execution caps, but video-heavy runs will be limited by your AI and scraping quotas.
Often, yes, because this workflow isn’t a simple “2-step Zap.” You’ve got branching by media type, batching, and waits, plus file handling for videos, which is where many no-code tools get expensive or brittle. n8n also gives you a real self-hosting option, which matters when you start running this daily. That said, if you only want “keyword in, row out” with no video analysis, Zapier or Make can be faster to set up. Talk to an automation expert if you want help choosing.
Once this is in place, competitor research stops being a side quest. You get a living Google Sheet that stays clean, searchable, and actually useful.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.
