#!/usr/bin/env python3 """ Etsy Archive Auditor Scans /Users/tonyclaw/Documents/Etsy Designs/04-Archive/ and generates a quality report flagging listings with missing files or weak metadata. Output: /Users/tonyclaw/.openclaw/workspace/drafts/etsy/archive-audit-{date}.md """ import os import sys import re import glob from datetime import datetime from pathlib import Path ARCHIVE_DIR = Path("/Users/tonyclaw/Documents/Etsy Designs/04-Archive") OUTPUT_DIR = Path("/Users/tonyclaw/.openclaw/workspace/drafts/etsy") DATE_STR = datetime.now().strftime("%Y-%m-%d") OUTPUT_FILE = OUTPUT_DIR / f"archive-audit-{DATE_STR}.md" # Folders that are not product listings — skip them META_FOLDERS = { "listed", "rejected", "source-pngs", "archive", "whats-included", "cleanup-20260210", "cleanup-20260211", "cleanup-20260212", } MIN_TITLE_LEN = 40 MIN_TAGS_COUNT = 13 SVG_KEYWORDS = ["svg", "SVG"] # Common niche keywords — if NONE are present, flag as weak NICHE_KEYWORDS = [ "hunting", "christmas", "halloween", "faith", "christian", "cross", "easter", "military", "patriot", "eagle", "floral", "wedding", "deer", "dog", "cat", "horse", "flower", "bird", "baby", "mom", "dad", "teacher", "nurse", "football", "baseball", "basketball", "fishing", "camping", "skull", "anchor", "nautical", "western", "farmhouse", ] # ─── Severity buckets ───────────────────────────────────────────────────────── critical = [] # missing required files warnings = [] # weak title issues infos = [] # tag/improvement suggestions stats = { "total": 0, "critical": 0, "warning": 0, "info": 0, "clean": 0, } def parse_listing(listing_path: Path) -> dict: """Parse a -listing.txt file and extract TITLE and TAGS.""" data = {"title": None, "tags": []} try: text = listing_path.read_text(encoding="utf-8", errors="replace") # TITLE m = re.search(r"^TITLE:\s*(.+)$", text, re.MULTILINE) if m: data["title"] = m.group(1).strip() # TAGS — grab the line(s) after "TAGS:" until blank line or PRICE: m_tags = re.search(r"^TAGS:\s*\n(.*?)(?:\n\n|\nPRICE:|\Z)", text, re.MULTILINE | re.DOTALL) if m_tags: raw = m_tags.group(1).strip() # Skip if raw is empty or looks like it's the next section if raw and not raw.startswith("PRICE:") and not raw.startswith("==="): data["tags"] = [t.strip() for t in raw.split(",") if t.strip()] else: data["tags"] = [] except Exception as e: data["parse_error"] = str(e) return data def audit_folder(folder: Path) -> dict: """Audit a single archive folder, return dict with issues.""" issues = {"critical": [], "warning": [], "info": []} files = {f.name for f in folder.iterdir() if f.is_file()} # ── Required file checks ────────────────────────────────────────────────── has_car = any(f.endswith("-car.jpg") for f in files) has_zip = any(f.endswith(".zip") for f in files) # listing.txt might be named anything with -listing.txt listing_files = [folder / f for f in files if f.endswith("-listing.txt")] has_listing = len(listing_files) > 0 if not has_car: issues["critical"].append("Missing `*-car.jpg` mockup") if not has_listing: issues["critical"].append("Missing `*-listing.txt` file") if not has_zip: issues["critical"].append("Missing ZIP file") # ── Metadata quality checks ─────────────────────────────────────────────── if has_listing: meta = parse_listing(listing_files[0]) title = meta.get("title", "") tags = meta.get("tags", []) # Title: too short if title and len(title) < MIN_TITLE_LEN: issues["warning"].append( f"Title too short ({len(title)} chars, min {MIN_TITLE_LEN}): `{title}`" ) # Title: missing SVG keyword if title and not any(kw in title for kw in SVG_KEYWORDS): issues["warning"].append( f"Title missing SVG keyword: `{title}`" ) # Title: missing niche keyword if title: title_lower = title.lower() has_niche = any(kw in title_lower for kw in NICHE_KEYWORDS) if not has_niche: issues["info"].append( f"Title may be missing a niche keyword (check manually): `{title}`" ) # Tags: missing or too few if not tags: issues["critical"].append("TAGS field is empty or missing in listing.txt") elif len(tags) < MIN_TAGS_COUNT: issues["warning"].append( f"Only {len(tags)} tags (need {MIN_TAGS_COUNT}): {', '.join(tags)}" ) else: # Exactly 13+ is fine; note if more than 13 if len(tags) > 13: issues["info"].append( f"Has {len(tags)} tags — Etsy allows max 13; extra tags ignored" ) if "parse_error" in meta: issues["warning"].append(f"Could not parse listing.txt: {meta['parse_error']}") return issues def main(): OUTPUT_DIR.mkdir(parents=True, exist_ok=True) all_folders = sorted([f for f in ARCHIVE_DIR.iterdir() if f.is_dir()]) # Skip known meta/utility folders that aren't product listings folders = [ f for f in all_folders if f.name not in META_FOLDERS and not f.name.startswith("cleanup-") ] skipped = len(all_folders) - len(folders) stats["total"] = len(folders) for folder in folders: issues = audit_folder(folder) folder_critical = issues["critical"] folder_warnings = issues["warning"] folder_infos = issues["info"] if folder_critical: critical.append((folder.name, folder_critical, folder_warnings, folder_infos)) stats["critical"] += 1 elif folder_warnings: warnings.append((folder.name, [], folder_warnings, folder_infos)) stats["warning"] += 1 elif folder_infos: infos.append((folder.name, [], [], folder_infos)) stats["info"] += 1 else: stats["clean"] += 1 # ── Build report ───────────────────────────────────────────────────────── lines = [ f"# Etsy Archive Audit — {DATE_STR}", "", f"**Archive:** `{ARCHIVE_DIR}` ", f"**Generated:** {datetime.now().strftime('%Y-%m-%d %H:%M %Z')} ", "", "---", "", "## Summary", "", f"| Stat | Count |", f"|------|-------|", f"| Total listings audited | {stats['total']} |", f"| 🔴 CRITICAL | {stats['critical']} |", f"| 🟡 WARNING | {stats['warning']} |", f"| 🔵 INFO | {stats['info']} |", f"| ✅ Clean | {stats['clean']} |", f"| ⏭️ Skipped (meta) | {skipped} |", "", "---", "", ] # ── CRITICAL ───────────────────────────────────────────────────────────── if critical: lines.append("## 🔴 CRITICAL — Missing Required Files") lines.append("") for name, crits, warns, infs in critical: lines.append(f"### `{name}`") for c in crits: lines.append(f"- ❌ **CRITICAL:** {c}") for w in warns: lines.append(f"- ⚠️ WARNING: {w}") for i in infs: lines.append(f"- ℹ️ INFO: {i}") lines.append("") # ── WARNING ─────────────────────────────────────────────────────────────── if warnings: lines.append("## 🟡 WARNING — Metadata Issues") lines.append("") for name, crits, warns, infs in warnings: lines.append(f"### `{name}`") for w in warns: lines.append(f"- ⚠️ WARNING: {w}") for i in infs: lines.append(f"- ℹ️ INFO: {i}") lines.append("") # ── INFO ────────────────────────────────────────────────────────────────── if infos: lines.append("## 🔵 INFO — Improvement Suggestions") lines.append("") for name, crits, warns, infs in infos: lines.append(f"### `{name}`") for i in infs: lines.append(f"- ℹ️ INFO: {i}") lines.append("") if not critical and not warnings and not infos: lines.append("## ✅ All Clean!") lines.append("") lines.append("No issues found across all archive listings.") lines.append("") lines.append("---") lines.append("") lines.append("*Generated by etsy-archive-audit.py*") report = "\n".join(lines) OUTPUT_FILE.write_text(report, encoding="utf-8") print(f"Report saved: {OUTPUT_FILE}") # Summary for cron delivery print(f"\n=== AUDIT SUMMARY ===") print(f"Total: {stats['total']} | Critical: {stats['critical']} | Warning: {stats['warning']} | Info: {stats['info']} | Clean: {stats['clean']}") # Exit code: 1 if any issues found (so cron job can conditionally notify) has_issues = stats["critical"] > 0 or stats["warning"] > 0 or stats["info"] > 0 return has_issues if __name__ == "__main__": has_issues = main() sys.exit(1 if has_issues else 0) # TONY-APPROVED: 2026-03-01 | sha:d547464a