musmem-locations

What problem does it solve?

This Skill helps researchers and historians quickly locate reliable dates, venues, and locations for bodybuilding contests by parsing both article narratives and scorecard data, then updating a centralized dataset.

Core Features & Use Cases

• Scrapes historic and modern contest articles to extract contest name, year, date, venue, and location, then merges results into contest_locations.json without overwriting existing data.
• Supports two data sources and workflows: article-based extraction from XML article files and scorecard-based extraction from scorecard listings, with conflict checks and deduplication.
• Use Case: a researcher wants to fill gaps for the Mr. America - AAU entries across 1940s–1970s and build a complete contest-history dataset.

Quick Start

Run prescreen_articles.py to scan all articles and generate a manifest, then run merge_locations.py to append new contest data to contest_locations.json.