Scrapeless + Google Sheets: SEO topics to drafts
Your content calendar shouldn’t depend on gut feel, scattered notes, and a half-finished keyword spreadsheet. But that’s how “SEO research” usually looks: a few tools open, 30 tabs of competitor posts, and a doc that never becomes a publishable draft.
This is where Scrapeless SEO automation pays off. Content managers feel the pain first, honestly, but growth leads and agency teams get stuck in the same loop. You will go from “we should write something about X” to prioritized topics and draft-ready articles stored in your database.
This workflow uses Scrapeless, Google Sheets, and AI to find trending keywords, study the top results, and generate drafts you can review and publish. Here’s what it does, what you need, and what to watch out for.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Scrapeless + Google Sheets: SEO topics to drafts
flowchart LR
subgraph sg0["Manual Run Flow"]
direction LR
n0@{ icon: "mdi:play-circle", form: "rounded", label: "Manual Run Trigger", pos: "b", h: 48 }
n1@{ icon: "mdi:swap-vertical", form: "rounded", label: "Assign Seed Terms", pos: "b", h: 48 }
n2@{ icon: "mdi:cog", form: "rounded", label: "Fetch Trend Topics", pos: "b", h: 48 }
n3@{ icon: "mdi:swap-vertical", form: "rounded", label: "Expand Related Queries", pos: "b", h: 48 }
n4@{ icon: "mdi:cog", form: "rounded", label: "Retrieve Trend Heat", pos: "b", h: 48 }
n5@{ icon: "mdi:robot", form: "rounded", label: "Trend Analysis Agent", pos: "b", h: 48 }
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/code.svg' width='40' height='40' /></div><br/>Prioritize Output Sorter"]
n7@{ icon: "mdi:database", form: "rounded", label: "Upsert Sheet Record", pos: "b", h: 48 }
n8@{ icon: "mdi:robot", form: "rounded", label: "Structured Result Parser", pos: "b", h: 48 }
n9@{ icon: "mdi:brain", form: "rounded", label: "Anthropic Chat Engine", pos: "b", h: 48 }
n10@{ icon: "mdi:database", form: "rounded", label: "Fetch Sheet Rows", pos: "b", h: 48 }
n11@{ icon: "mdi:swap-vertical", form: "rounded", label: "Distribute Level Items", pos: "b", h: 48 }
n12@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Exclude Low Priority Topics", pos: "b", h: 48 }
n13@{ icon: "mdi:cog", form: "rounded", label: "Run Google Search", pos: "b", h: 48 }
n14@{ icon: "mdi:swap-vertical", form: "rounded", label: "Select Top Competitor Links", pos: "b", h: 48 }
n15@{ icon: "mdi:swap-vertical", form: "rounded", label: "Split Competitor Results", pos: "b", h: 48 }
n16@{ icon: "mdi:cog", form: "rounded", label: "Crawl Competitor Pages", pos: "b", h: 48 }
n17@{ icon: "mdi:swap-vertical", form: "rounded", label: "Map Competitor Markdown", pos: "b", h: 48 }
n18@{ icon: "mdi:cog", form: "rounded", label: "Aggregate Markdown", pos: "b", h: 48 }
n19@{ icon: "mdi:robot", form: "rounded", label: "Senior Content Writer", pos: "b", h: 48 }
n20["<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/code.svg' width='40' height='40' /></div><br/>Parse AI Article JSON"]
n21["<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/supabase.svg' width='40' height='40' /></div><br/>Insert Supabase Row"]
n22@{ icon: "mdi:brain", form: "rounded", label: "Anthropic Writer Model", pos: "b", h: 48 }
n20 --> n21
n6 --> n7
n16 --> n17
n5 --> n6
n18 --> n19
n3 --> n4
n11 --> n12
n15 --> n16
n13 --> n14
n2 --> n3
n1 --> n2
n10 --> n11
n9 -.-> n5
n22 -.-> n19
n8 -.-> n5
n19 --> n20
n4 --> n5
n14 --> n15
n17 --> n18
n0 --> n1
n0 --> n10
n12 --> n13
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 n5,n8,n19 ai
class n9,n22 aiModel
class n12 decision
class n7,n10 database
class n6,n20 code
classDef customIcon fill:none,stroke:none
class n6,n20,n21 customIcon
The Problem: SEO Topics Don’t Turn Into Drafts
Keyword research is easy to start and hard to finish. You pull “related queries,” copy a few into a sheet, then you’re supposed to decide what matters, check who already ranks, extract what they covered, and turn it into a brief or draft. That “supposed to” part is where weeks disappear. Meanwhile, your site keeps publishing safe topics that don’t move traffic, or you chase a trend too late because nobody had time to validate it.
It adds up fast. And the cost isn’t just time. It’s momentum.
- Most teams spend about 2 hours to validate a single topic once you include SERP checks, competitor reading, and note cleanup.
- Prioritization becomes political, so low-effort ideas win over high-potential long-tail opportunities.
- Competitor research is inconsistent because everyone “skims” differently, which leads to drafts with obvious gaps.
- Your sheet becomes a graveyard of keywords with no clear next action, so publishing slows down right when it should speed up.
The Solution: Trend-Driven Topics, Auto-Prioritized, Drafted
This workflow turns a seed keyword into a repeatable pipeline: discover what’s trending, decide what’s worth writing, research what already ranks, then generate an SEO draft you can actually review. You start by entering a seed term (like “project management” or a product category). Scrapeless pulls related queries from Google Trends and collects interest-over-time signals. An AI agent then reviews those signals, labels each keyword by priority (P0–P3), and logs the “what” and “why” into Google Sheets.
From there, the workflow picks only the higher-priority topics (P0–P2), runs a Google Search via Scrapeless/Deep SerpAPI, and grabs the top organic competitor pages. Scrapeless crawls each page and extracts clean Markdown, so your AI writer isn’t guessing based on titles alone. Finally, the “Senior Content Writer” agent generates a complete SEO article draft (title, slug, meta description, strategy summary, and a structured body). The finished output is saved to Supabase, ready for review or API-based publishing.
The workflow starts when you trigger it in n8n and provide (or update) your seed keyword. Next, it discovers and scores trend-based long-tail keywords, then enriches the best ones with competitor content. Finally, AI produces draft articles and stores them in Supabase while Google Sheets keeps your prioritized topic list tidy.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you publish 4 SEO posts per week for an international site. Manually, if you spend about 2 hours per topic on trends + competitor reading, that’s roughly 8 hours before writing even starts. With this workflow, you trigger the run, wait for research and drafting to finish, then review what’s stored in Supabase. Setup time is a one-time 30–60 minutes, and weekly “topic to draft” time usually drops to about an hour of review and edits.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Scrapeless for trends, SERP, and crawling.
- Google Sheets to store and manage topic priorities.
- Supabase to store drafts and structured article JSON.
- LLM credentials (get it from OpenAI or Anthropic console).
Skill level: Intermediate. You’ll connect a few APIs, map fields, and test runs with small batches.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
You trigger the run and set your seed terms. The workflow starts from a manual trigger, then the “Assign Seed Terms” step defines the niche you want to build topical authority around.
Trends are collected and scored. Scrapeless pulls related queries and interest-over-time data, then an AI agent reviews the signals and labels each keyword with a priority (P0–P3) so you’re not guessing.
Only the best topics get full competitor research. The workflow filters out low-priority items, runs a Google Search, selects top competitor links, then crawls those pages and converts them into clean Markdown your writer model can use.
Drafts are generated and saved. The “Senior Content Writer” agent produces a structured article package (title, slug, meta, strategy summary, body blocks), then the workflow parses the JSON and inserts it into Supabase for review and publishing.
You can easily modify the priority thresholds to expand or narrow what gets drafted based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Manual Trigger
Start the workflow with a manual execution so you can validate outputs before scheduling or deploying.
- Add Manual Run Trigger as the starting node.
- Note that Manual Run Trigger outputs to both Assign Seed Terms and Fetch Sheet Rows in parallel.
Step 2: Connect Google Sheets
Configure the Google Sheets nodes to store trend insights and fetch existing topic rows for competitor research.
- Open Upsert Sheet Record and set Operation to
appendOrUpdate. - Set Document to
[YOUR_ID]and Sheet to[YOUR_ID]in Upsert Sheet Record. - Map fields in Upsert Sheet Record: Level →
{{ $json.recommended_priority }}, Reason →{{ $json.data_interpretation }}, Seed Keywords →{{ $('Assign Seed Terms').item.json.seedKeyword }}, Related Keywords →{{ $json.keyword }}. - Open Fetch Sheet Rows and set Document to
[YOUR_ID]and Sheet to[YOUR_ID]. - Credential Required: Connect your googleSheetsOAuth2Api credentials to Upsert Sheet Record and Fetch Sheet Rows.
Step 3: Set Up Trend Discovery and Prioritization
This branch generates trend-based keyword priorities and writes them to the sheet.
- In Assign Seed Terms, set seedKeyword to
Project Management. - Configure Fetch Trend Topics with Operation
googleTrends, Data Typerelated_queries, GeoUS, and Query{{ $json.seedKeyword }}. - Set Expand Related Queries to split Field to Split Out
related_queries.top. - Configure Retrieve Trend Heat with Operation
googleTrends, GeoUS, and Query{{ $json.query }}. - In Trend Analysis Agent, keep Text as
=The following are the keywords for the topic:` {{ $json.parameters.q }}` trends data： ``` {{ $json.interest_over_time.toJsonString() }} ```and ensure Has Output Parser is enabled. - Review Structured Result Parser and keep the JSON schema example as provided.
- Keep Prioritize Output Sorter code unchanged to sort by
P0–P3levels. - Credential Required: Connect your scrapelessApi credentials to Fetch Trend Topics and Retrieve Trend Heat.
- Credential Required: Connect your anthropicApi credentials to Anthropic Chat Engine.
- Note: Structured Result Parser is a sub-node for Trend Analysis Agent. Add credentials to Anthropic Chat Engine, not the parser.
Step 4: Configure Competitor Research and Content Aggregation
This branch filters priority topics, searches competitors, crawls pages, and aggregates markdown content.
- In Distribute Level Items, set Field to Split Out to
Leveland Include toallOtherFields. - Configure Exclude Low Priority Topics with a condition: Level
{{ $json.Level }}notContainsP3. - Set Run Google Search query to
{{ $json['Related Keywords'] }}. - In Select Top Competitor Links, set organic_results to
{{ $json.organic_results.slice(0,3) }}. - Configure Split Competitor Results to split Field to Split Out
organic_results. - Set Crawl Competitor Pages with Resource
crawler, Operationcrawl, and URL{{ $json.link }}. - In Map Competitor Markdown, set markdown to
{{ $json[0].markdown }}. - Configure Aggregate Markdown to aggregate the markdown field.
- Credential Required: Connect your scrapelessApi credentials to Run Google Search and Crawl Competitor Pages.
Step 5: Configure AI Writing, Parsing, and Storage
Generate a full SEO article from aggregated markdown and store it in Supabase.
- In Senior Content Writer, keep the structured prompt and JSON output format intact.
- Ensure Anthropic Writer Model is connected as the language model for Senior Content Writer.
- Leave Parse AI Article JSON code unchanged to clean and parse the model output.
- In Insert Supabase Row, set Table to
seo_articlesand map fields: title →{{ $json.title }}, meta_description →{{ $json.meta_description }}, body →{{ $json.body }}, slug →{{ $json.slug }}. - Credential Required: Connect your anthropicApi credentials to Anthropic Writer Model.
- Credential Required: Connect your supabaseApi credentials to Insert Supabase Row.
Step 6: Test and Activate Your Workflow
Run the workflow end-to-end to verify sheet updates, competitor crawling, AI output, and database storage.
- Click Execute Workflow from Manual Run Trigger to test all branches.
- Confirm that Upsert Sheet Record writes prioritized keywords to your Google Sheet.
- Verify that Aggregate Markdown outputs an array of competitor content before Senior Content Writer runs.
- Check Insert Supabase Row for a new record in
seo_articleswith populated fields. - When the test succeeds, toggle the workflow to Active for production use.
Common Gotchas
- Scrapeless credentials can expire or your plan may block certain endpoints. If things break, check your Scrapeless dashboard usage and API key status 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 30–60 minutes once your API keys are ready.
No. You’ll mostly connect accounts, paste API keys, and adjust a few fields like your seed keyword and priority rules.
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 Scrapeless usage plus LLM API costs for drafting.
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 tweak for international SEO. You can run separate seed terms per locale, then pass a country/language parameter into the Scrapeless trend and search requests. Most teams also adjust the AI prompts in the “Trend Analysis Agent” and “Senior Content Writer” steps so the output matches local intent and spelling conventions. If you want to keep one master backlog, add a locale column in Google Sheets and include it in the Supabase record.
Usually it’s an invalid or expired API key, or the endpoint you’re calling isn’t enabled for your plan. Regenerate the key in Scrapeless, update it in n8n, then re-run a single keyword to confirm it works. If it fails only on larger batches, it can be rate limiting; slow the workflow down or reduce how many keywords you process per run.
If you self-host n8n there’s no execution cap, so the limit is mostly your server size and your Scrapeless/LLM quotas. On n8n Cloud, it depends on your plan’s monthly executions. Practically, many teams process 20–50 keywords per run, then generate drafts only for P0–P2 to control crawl and model costs.
Often, yes. This kind of pipeline needs filtering, branching, structured parsing, and multi-step research loops, and n8n handles that without you paying extra for every path. Self-hosting is also a big deal if you want unlimited runs or you’re using community nodes that don’t work on managed platforms. Zapier or Make can still be fine for simple “send this row to that tool” automations, but they get awkward once you add crawling and agent-based drafting. If you’re unsure, Talk to an automation expert and map it to your volume.
Once this is running, your backlog stops being a wish list and starts being a production line. The workflow handles the repetitive research and drafting so you can spend your time on review, differentiation, and publishing.
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.
