惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - Franky
云风的 BLOG
云风的 BLOG
人人都是产品经理
人人都是产品经理
博客园 - 叶小钗
Engineering at Meta
Engineering at Meta
Vercel News
Vercel News
Y
Y Combinator Blog
B
Blog
Microsoft Azure Blog
Microsoft Azure Blog
C
Check Point Blog
M
MIT News - Artificial intelligence
Jina AI
Jina AI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Apple Machine Learning Research
Apple Machine Learning Research
Hugging Face - Blog
Hugging Face - Blog
阮一峰的网络日志
阮一峰的网络日志
罗磊的独立博客
Stack Overflow Blog
Stack Overflow Blog
F
Fortinet All Blogs
博客园 - 司徒正美
I
InfoQ
Google DeepMind News
Google DeepMind News
GbyAI
GbyAI
U
Unit 42

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
How I Built a Programmatic SEO Pipeline with n8n + Claude...
Paul Maxime DOSSOU · 2026-06-21 · via DEV Community

Paul Maxime DOSSOU

A few months ago, a client asked me to rank on 150+ local search queries across 5 cities — with a budget that wouldn't cover a single traditional agency retainer.

Instead of writing 150 articles manually, I built a pipeline. Here's exactly how it works.

The problem with traditional SEO at scale

Creating geo-targeted content manually is slow, expensive, and inconsistent. You need a writer who understands SEO structure, knows the local context, and can maintain quality across hundreds of pages.

I replaced that process with a system: n8n + Claude API + WordPress REST API.

The architecture

Google Sheets (input)
→ n8n workflow
→ Claude API (content generation)
→ WordPress REST API (publish)
→ Next.js revalidation (ISR)
Three tools. One trigger. Zero manual publishing.

Step 1 — The input sheet

Each row in Google Sheets defines one page:

city service target_keyword population competitors
Cotonou n8n automation consultant n8n cotonou 800000 ...
Abidjan automatisation automatisation processus abidjan 4M ...
n8n reads this sheet on a schedule (or on-demand via webhook).

Step 2 — The n8n workflow

The core workflow has 6 nodes:

Google Sheets trigger — reads unprocessed rows (status = "pending")
HTTP Request — calls Claude API with a structured prompt
JSON parser — extracts title, slug, content, excerpt, tags
WordPress REST API — creates the post as draft
Google Sheets update — marks row as "published" with the post URL
Next.js revalidation — calls /api/revalidate to clear ISR cache
The Claude prompt is the critical piece. Here's a simplified version:

You are an SEO content expert. Write a complete article for:

  • Service: {{service}}
  • City: {{city}}
  • Target keyword: {{target_keyword}}
  • Word count: 2000+ words
  • Language: French

Required structure:

  1. intro-block (50 words max, direct answer)
  2. 4 stats (local market data)
  3. 8+ H2 sections with rich content
  4. Comparison table
  5. FAQ (8-10 questions, accordion format)
  6. CTA block linking to /contact

Return valid JSON: { title, slug, excerpt, content, tags[], read_time }
Step 3 — The WordPress REST API call

// n8n HTTP Request node
POST https://your-site.com/wp-json/wp/v2/posts
Authorization: Bearer {{wp_token}}

{
"title": "{{title}}",
"slug": "{{slug}}",
"content": "{{content}}",
"status": "publish",
"categories": [{{category_id}}],
"meta": {
"excerpt": "{{excerpt}}"
}
}
Step 4 — Next.js ISR revalidation

If you're running Next.js in front of WordPress (or a custom backend), you need to bust the cache after publishing:

// app/api/revalidate/route.ts
import { revalidatePath } from 'next/cache';
import { NextRequest, NextResponse } from 'next/server';

export async function POST(req: NextRequest) {
const { slug } = await req.json();
const secret = req.headers.get('x-revalidate-secret');

if (secret !== process.env.REVALIDATE_SECRET) {
return NextResponse.json({ error: 'Unauthorized' }, { status: 401 });
}

revalidatePath(/blog/${slug});
return NextResponse.json({ revalidated: true });
}
n8n calls this endpoint after each publish. The page is live and indexed within minutes.

Results

200+ geo-targeted pages deployed in 3 days
Average 2,100 words per page, consistent structure
Zero duplicate content issues (city + service combinations are unique)
First rankings appearing within 3 weeks on low-competition queries
The pipeline runs unattended. I trigger it manually for client reviews, but it could run fully automated on a cron.

What I learned

Prompt engineering is the bottleneck. Getting Claude to output valid JSON with correct HTML structure every single time took more iteration than the n8n workflow itself. Add a validation node that checks the JSON before publishing — don't skip this.

WordPress REST API rate limits exist. If you're deploying 200 pages in one run, add a Wait node between requests (2-3 seconds). Otherwise you'll hit 429s.

ISR cache busting matters. Without it, your newly published pages serve stale "404 not found" content for hours. Always wire the revalidation call into the workflow.

The bigger picture

I build these kinds of systems for clients — SEO pipelines, automation workflows, AI integrations. If you're a dev who's curious about the business side of this, or an entrepreneur who wants to understand what's possible: this is what modern digital agencies actually do when they stop charging by the hour for manual work.

I document more of this on my site: paulmaximedossou.com

Audits are free. DMs are open.

Paul Maxime Dossou — Founder of EkoMedia. I build automation systems, SEO pipelines, and AI integrations for businesses in France and West Africa.