# Anno 117: Pax Romana Documentation Structured API-like documentation of all game elements in Anno 117: Pax Romana. ## Workflow ### 1. Scrape pages **From anno.land:** ```bash # Scrape 1 page (default) venv/bin/python python/scraper_anno_world.py # Scrape multiple pages venv/bin/python python/scraper_anno_world.py -n 10 # Scrape all remaining pages venv/bin/python python/scraper_anno_world.py -n 9999 ``` **From IGN wiki:** ```bash # Scrape 1 page (default) venv/bin/python python/scraper_ign.py # Scrape multiple pages venv/bin/python python/scraper_ign.py -n 10 ``` This scrapes unchecked URLs from `scraping.md` (anno.land) or `scraping_ign.md` (IGN), saves JSON to `scraped_data/`, and adds them to `processed.md` as pending. ### 2. Process scraped data into docs/ Use this prompt with Claude Code to process pending JSON files into documentation: ``` Process 1566 pending JSON files from processed.md into docs/. OUTER LOOP (repeat until X files total are done): 1. Read processed.md, find next 5 pending files (marked `- [ ]`) 2. Mark each in-progress: `- [ ]` to `- [~]` INNER LOOP (process batch of 10 in parallel): 3. Spawn 10 Task sub-agents in ONE message (subagent_type="general-purpose", run_in_background=true), one per file: "Process scraped_data/{filename} into docs/: - Read the JSON - Translate: Liberti, Plebejer=Plebeians, Equites, Patrizier=Patricians, Wanderer=Waders, Schmiede=Smiths, Älteste=Elders, Mercatoren=Mercators, Edelmänner=Nobles - Target: anno-117-buildings_* → docs/buildings/, anno-117-goods_* → docs/goods/, anno-117-specialists* → docs/specialists/, anno-117-skills_* → docs/skills/ - Merge if exists, create if not (use existing docs/ as format examples) - Update category _index.md if needed - Mark done: `- [~] {filename}` to `- [x] {filename}` in processed.md" 4. Use TaskOutput to wait for all 5 agents to complete END INNER LOOP 5. Count completed files, continue OUTER LOOP until X total done END OUTER LOOP ``` Replace X with desired total (e.g., 20). --- ## File Structure - `scraping.md` - anno.land URLs to scrape (checkboxes track progress) - `scraping_ign.md` - IGN wiki URLs to scrape (checkboxes track progress) - `processed.md` - JSON files pending/processed into docs/ - `scraped_data/` - Raw scraped JSON files - `docs/` - Structured documentation (see CLAUDE.md for structure) - `python/scraper_anno_world.py` - anno.land web scraper - `python/scraper_ign.py` - IGN wiki web scraper ## Data Flow ``` anno.land pages IGN wiki pages ↓ ↓ (scraper_anno_world.py) (scraper_ign.py) ↓ ↓ └──────────┬─────────────┘ ↓ scraped_data/*.json ↓ (Claude sub-agents) ↓ docs/**/*.md ```