n8n Workflow: Merge RSS Feeds & Hugging Face Data to CSV

Merge Hugging Face + RSS marketing data into a clean CSV—every three days

This n8n workflow automatically collects marketing data from two public Hugging Face datasets and four marketing RSS feeds, standardizes and quality-checks the combined records, and outputs a cleaned CSV plus a JSON quality report. No credentials required.

What this workflow does

• Runs on a schedule (every three days) to refresh your marketing dataset automatically.
• Loads configuration (Hugging Face dataset names, row window, and RSS feed URLs) from a dedicated configuration step.
• Fetches rows from two Hugging Face datasets (ad copy and campaign performance), maps each source into a shared schema, and records per-source availability.
• Reads the latest items from four RSS feeds, then strips HTML from titles and summaries before mapping them into the same shared schema (and tolerates individual feed failures).
• Merges and normalizes all sources, converts dates to YYYY-MM-DD, removes duplicates, and drops records missing essential fields.
• Flags incomplete records with clear quality reasons.
• Outputs files: a cleaned CSV and a JSON report with per-source health, counts of removed records, and completeness metrics.

Use cases

• Keep a centralized marketing dataset in CSV form by combining Hugging Face ad/campaign data with content updates from RSS.
• Quality-monitor your ingestion pipeline using the JSON report (source health, removed record counts, completeness).
• Reduce manual work for SaaS ops teams that need periodic refreshes of standardized marketing records.

Technical details

• Category: n8n automation workflow
• Nodes/tech stack: set, code, merge, sticky note, http request, rss feed read
• Configurable: dataset names, row offset/length, and RSS feed URLs
• Credentialless: uses public Hugging Face datasets and public RSS URLs

Setup: Import the workflow, optionally update configuration values, run once, download the generated CSV/JSON from the output steps, then enable the three-day schedule.