Automate Website Summaries at Scale from Any Domain Using CaptureKit and n8n
If your job involves scraping content, summarizing pages, or collecting structured data across dozens of URLs every week, you already know it can feel like chasing flies with chopsticks. Time-consuming, repetitive, and just plain boring.
Here’s the good news you can automate all of it.
From pulling entire websites into structured summaries, to generating clean, readable overviews in minutes instead of hours.
This tutorial is for marketers, SEO professionals, content analysts, developers, and honestly, anyone who’s ever looked at a list of 200 URLs and thought, “There’s no way I’m doing that manually.”
Because with CaptureKit (part of the WebAPI Group) and n8n, you can build a workflow that does it all for you. Automatically. Every page on your website will be summarized and stored with just one starting URL.
No scripts, no manual parsing, no copy-pasting HTML.
Just smart automation that runs quietly while you get actual work done.
What You’ll Need to Get Started
A spreadsheet (Google Sheets or CSV)
CaptureKit’s Page Content API
CaptureKit’s AI Content API
n8n (Automation Tool)
This is how it will work
We will use CaptureKit’s Page Content API to extract clean page data, metadata, and links from any site.
Feed those pages into CaptureKit’s AI Content API to generate concise, context-aware summaries.
Automate the entire process inside n8n, so one workflow handles the whole chain pulling input from a spreadsheet and writing results back in real time.
And the best part?
At the end of this article, you’ll get a ready-to-use n8n blueprint. Just import it, add your spreadsheet link, plug in your CaptureKit key, and boom your automation is live.
This isn’t just another “look what we can do with APIs” thing. This is the kind of automation that clears your to-do list while you’re still sipping your morning coffee.
Let’s get started.
Step 1. Grab Your Capture Kit API
Sign up for CaptureKit. Once you’re in the dashboard, head over to the sidebar and click on API Keys. You’ll see your key sitting right there. Copy it and keep it somewhere safe, you’ll need for automation.
Step 2. Prepare spreadsheet
Now, let’s set up the spreadsheet.
In the first sheet named Domain, drop in your website link or a few of them if you want to batch it.
In the second sheet named Summaries, you’ll have two columns: one for URLs and one for Summaries. That’s where your automation will dump all the results once it runs. Simple, clean, done.
Step 3. Get Started With Automation Workflow on n8n
Once you’re logged into n8n, click “Workflows” in the left sidebar, then hit “+ New Workflow” in the top right corner.
A blank canvas will open, that's where we’ll start building your automation. Each step you add here is called a Node. You’ll connect these Nodes one after another, and together, they’ll form your full workflow.
Node 1: Schedule Trigger
The first Node you’ll add is the Schedule Trigger. This Node basically tells n8n when to run your automation. Whether that’s every hour, once a day, or every Monday at 9 a.m.
Node 2: Get New Rows
Next, add a Google Sheets Node - Get New Rows. This one will pull the domain name from your spreadsheet, the one we’ll use to extract all the pages.
Here’s how to set it up:
Credential: Choose your connected Google Sheets account.
Resource: Select Sheet Within Document.
Operation: Pick Get Row(s).
Document: Choose your spreadsheet (the one named Summarize All Pages of A Domain).
Sheet: Select Domain.
Once everything’s mapped, hit Execute Node at the top.
You’ll see your domain name appear on the right under Output that means n8n has successfully fetched it from your sheet.
Node 3: HTTP Request (Content API)
Now add an HTTP Request Node. This is where we make our first API call using CaptureKit’s Page Content API. To know more check out the documentation from here.
Here’s how to set it up:
Method: GET
Query Parameters:
access_key → your CaptureKit API key
- url →
{{ $json.Domain }}(this maps the domain pulled from your sheet) include_sitemap → true
Once you’re done, click Execute Node.
You’ll see the full list of pages from that domain appear on the right under Output. These URLs will later be added to your spreadsheet automatically.
Node 4: Split Out
This one takes all the links we got from the previous API response. Basically that long list of URLs inside data.sitemap.links and breaks them down into separate items that n8n can handle one by one.
Here’s what you set:
Here, simply drag the “links” field (shown in the output from the previous step) into the “Fields to Split Out” box - it should look like this: data.sitemap.links.
That’s it.
When you click Execute Node, you’ll see each URL listed individually in the output on the right.
We use this node because the HTTP Request Node returns all the links in a single batch, but we need each page URL as a separate entry for the next steps. So we can process and summarize them one at a time.
Node 5: Loop
This node processes each URL one by one, so every link from the Split Out Node runs through the next steps individually.
Connect it right after the Split Out Node.
We’ll loop this through the upcoming nodes as well, so each page goes through the full flow fetching, summarizing, and saving in sequence.
Node 6: HTTP Request
Now add another HTTP Request Node. This time for CaptureKit’s AI Content API.
You can check the full API reference here.
Here’s how to set it up:
Method: GET
Query Parameters:
access_key → your CaptureKit API key
url → In the URL value, drag and drop the field from the Loop Over Items output.
Then click Execute Node.
In the Output, you’ll see clean AI-generated summaries for each page, along with key info like categories, use cases, and features.
This data will later be written back to your spreadsheet automatically.
Node 7: Append Row in Sheet
This is the final node in your workflow, and we don’t need any more after this because this one writes everything back into your spreadsheet automatically.
Here’s how to set it up:
Credential: Your connected Google Sheets account
Resource: Sheet Within Document
Operation: Append Row
Document: Select your spreadsheet (Summarize All Pages of A Domain)
Sheet: Choose Summaries
Now, map the fields precisely:
For URL, drag and drop the field from Loop Over Items → data.sitemap.links
For Summary, drag and drop the field from HTTP Request1 → data.summary
Then click Execute Node.
You’ll see each page URL with its summary added to your spreadsheet and that’s the end of the automation.
Now, pick the Loop Over Items node and drag its output to the Append Row in Sheet node. (See the screenshot in node 5th “Loop Over Item” section)
This creates the final loop. It runs each URL through the full chain: fetching content, generating summaries, and writing results back to your spreadsheet automatically.
Once connected, your workflow will cycle through every page until all summaries are complete.
Step 4: Run the Workflow and Check Your Sheet
Click Execute Workflow at the top.
n8n will now run through the full process and pull the domain, extracting all URLs, summarizing each page, and writing the results back into your spreadsheet.
Once it’s done, open your Summaries sheet.
You’ll see every page URL listed neatly in the first column, and their AI-generated summaries right next to them, all done automatically.
Grab the Blueprints and Get Started
You don’t need to rebuild everything from scratch — we’ve got both blueprints ready for you.
👉 Spreadsheet Blueprint: Copy it here
👉n8n JSON Blueprint: Download it here
Just import the n8n JSON into your workspace, open the spreadsheet copy, add your CaptureKit API key, and connect your Google account.
Once that’s done, click Execute Workflow and your automation will start running instantly.
Every URL summarized. Every result is written neatly into your sheet without any manual work.
Conclusion:
And that’s it - your full automation to summarize every page on a website, built from scratch with CaptureKit and n8n.
No more opening endless tabs, no manual copy-pasting, no mind-numbing repetition.
You feed in a single domain, and the workflow does the rest — crawls the pages, generates clean summaries, and drops them neatly into your sheet.
If you haven’t tried it yet, this is the perfect time to sign up for CaptureKit and grab your API key.
You’ll be up and running in minutes, and once you see your first batch of summaries appear automatically, you’ll wonder why you didn’t automate this sooner.