Seeking Developer for AI-Powered Automated Content Platform (Scraping, AI, WordPress Integration)
Budget: €1,500 – €3,000 EUR
? Seeking Developer for AI-Powered Automated Content Platform (Scraping, AI, WordPress Integration)
? Project Overview
We are looking for an experienced developer (or team) to help us build a fully automated, AI-driven content platform. The system will automate the process of collecting, processing, and publishing news and articles from selected sources. The goal is to create a scalable and high-quality content pipeline that handles everything from scraping to social media sharing with minimal manual input.
✅ High-Level Requirements:
Scrape articles from specific categories across multiple websites using Python-based tools.
Automate similarity checks between articles to combine similar ones into a single, cohesive article.
Use AI to translate and rewrite content while maintaining HTML structure.
Check for plagiarism and ensure original content using a plagiarism-checking tool.
Format and publish articles to a WordPress site using the REST API.
Create a central database (Google Sheets or Airtable) to track all scraped content.
Automate posting to social media (starting with X (Twitter), expanding to others later).
Include an approval workflow for manual oversight before publishing.
Optionally consider using an open-source LLM (e.g., DeepSeek) to reduce costs for similarity checks and translation.
✅ Key Features
✔️ Scrape only targeted categories (not full sites)
✔️ Automatic similarity check and merging
✔️ AI-based translation and rewriting
✔️ Plagiarism check with automated rephrasing
✔️ Centralized database tracking
✔️ Seamless WordPress publishing via REST API
✔️ Initial social media automation (Twitter)
✔️ Admin approval before publishing
✔️ Future scalability for other social platforms
? Tech Stack
We expect the following technologies to be used, but we’re open to suggestions:
Function
Tool/Tech
Scraping
Scrapy + Playwright
Database
Google Sheets / Airtable
Similarity Check
OpenAI embeddings (or DeepSeek)
Translation + Rewriting
ChatGPT API (or DeepSeek)
Plagiarism Check
Copyscape API
Publishing
WordPress REST API
Automation
Make (Integromat) or Python scripts
Approval Flow
Slack API
Social Sharing
Twitter API (others in future)
Image Processing
Python (Pillow)
? Additional Notes
We will provide all necessary API keys and any third-party platforms or services (e.g., OpenAI, Copyscape) will be paid for by us directly.
If any additional platform or software is required, we will cover the cost.
We are open to suggestions on how to improve efficiency or reduce costs (e.g., switching from OpenAI to open-source models).
? Next Steps
We would like to schedule a brief interview to further discuss the project details and scope.
? We have a very detailed brief prepared that outlines the full workflow, technical requirements, and automation strategy. This will be sh
? Project Overview
We are looking for an experienced developer (or team) to help us build a fully automated, AI-driven content platform. The system will automate the process of collecting, processing, and publishing news and articles from selected sources. The goal is to create a scalable and high-quality content pipeline that handles everything from scraping to social media sharing with minimal manual input.
✅ High-Level Requirements:
Scrape articles from specific categories across multiple websites using Python-based tools.
Automate similarity checks between articles to combine similar ones into a single, cohesive article.
Use AI to translate and rewrite content while maintaining HTML structure.
Check for plagiarism and ensure original content using a plagiarism-checking tool.
Format and publish articles to a WordPress site using the REST API.
Create a central database (Google Sheets or Airtable) to track all scraped content.
Automate posting to social media (starting with X (Twitter), expanding to others later).
Include an approval workflow for manual oversight before publishing.
Optionally consider using an open-source LLM (e.g., DeepSeek) to reduce costs for similarity checks and translation.
✅ Key Features
✔️ Scrape only targeted categories (not full sites)
✔️ Automatic similarity check and merging
✔️ AI-based translation and rewriting
✔️ Plagiarism check with automated rephrasing
✔️ Centralized database tracking
✔️ Seamless WordPress publishing via REST API
✔️ Initial social media automation (Twitter)
✔️ Admin approval before publishing
✔️ Future scalability for other social platforms
? Tech Stack
We expect the following technologies to be used, but we’re open to suggestions:
Function
Tool/Tech
Scraping
Scrapy + Playwright
Database
Google Sheets / Airtable
Similarity Check
OpenAI embeddings (or DeepSeek)
Translation + Rewriting
ChatGPT API (or DeepSeek)
Plagiarism Check
Copyscape API
Publishing
WordPress REST API
Automation
Make (Integromat) or Python scripts
Approval Flow
Slack API
Social Sharing
Twitter API (others in future)
Image Processing
Python (Pillow)
? Additional Notes
We will provide all necessary API keys and any third-party platforms or services (e.g., OpenAI, Copyscape) will be paid for by us directly.
If any additional platform or software is required, we will cover the cost.
We are open to suggestions on how to improve efficiency or reduce costs (e.g., switching from OpenAI to open-source models).
? Next Steps
We would like to schedule a brief interview to further discuss the project details and scope.
? We have a very detailed brief prepared that outlines the full workflow, technical requirements, and automation strategy. This will be sh