feat: add script to audit guides.csv URLs for WCAG 2.1 AA issues with pa11y and output filtered report

Co-authored-by: aider (o3) <aider@aider.chat>

check_wcag.py

@@ -0,0 +1,119 @@
+#!/usr/bin/env python3
+"""
+Check each guide URL in guides.csv for WCAG 2.1 AA accessibility
+issues using the pa11y CLI and report results.
+
+The script:
+1. Reads guides.csv in the current directory.
+2. Runs `pa11y` for each URL with the WCAG2AA standard, requesting JSON.
+3. Collects the issues for every guide.
+4. Removes any issue codes that appear in *every* guide.
+5. Prints the filtered results to the console and writes them to
+   output.txt.
+
+Prerequisites:
+    npm install -g pa11y
+
+Usage:
+    python check_wcag.py
+"""
+from __future__ import annotations
+
+import csv
+import json
+import subprocess
+import sys
+from pathlib import Path
+from typing import Dict, List, Set
+
+GUIDES_CSV = Path(__file__).with_name("guides.csv")
+OUTPUT_FILE = Path("output.txt")
+
+
+def run_pa11y(url: str) -> List[dict]:
+    """
+    Run pa11y on a URL and return the parsed JSON list of issues.
+
+    Returns an empty list if pa11y fails.
+    """
+    try:
+        result = subprocess.run(
+            ["pa11y", url, "--standard", "WCAG2AA", "--reporter", "json"],
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        if result.returncode != 0:
+            print(f"[WARN] pa11y returned code {result.returncode} for {url}", file=sys.stderr)
+            return []
+        return json.loads(result.stdout)
+    except FileNotFoundError:
+        print("Error: pa11y not found. Install it with `npm install -g pa11y`.", file=sys.stderr)
+        sys.exit(1)
+    except json.JSONDecodeError:
+        print(f"[WARN] Could not parse pa11y JSON output for {url}", file=sys.stderr)
+        return []
+
+
+def read_guides(csv_path: Path) -> List[Dict[str, str]]:
+    """Load all guides from the CSV into a list of dicts."""
+    with csv_path.open(newline="", encoding="utf-8-sig") as fh:
+        reader = csv.DictReader(fh)
+        return list(reader)
+
+
+def compute_common_codes(issues_by_guide: Dict[str, List[dict]]) -> Set[str]:
+    """Return the set of issue codes that appear in every guide."""
+    all_codes_iter = (
+        {issue["code"] for issue in issues} for issues in issues_by_guide.values()
+    )
+    common_codes: Set[str] | None = None
+    for codes in all_codes_iter:
+        if common_codes is None:
+            common_codes = codes
+        else:
+            common_codes &= codes
+    return common_codes or set()
+
+
+def format_issue(issue: dict) -> str:
+    """Return a human-readable one-line representation of a pa11y issue."""
+    selector = issue.get("selector", "").strip() or "N/A"
+    return f"[{issue['type']}] {issue['code']}: {issue['message']}  (selector: {selector})"
+
+
+def main() -> None:
+    guides = read_guides(GUIDES_CSV)
+    issues_by_guide: Dict[str, List[dict]] = {}
+
+    print("Auditing guides with pa11y…\n")
+    for guide in guides:
+        name = guide["Name"]
+        url = guide["URL"]
+        print(f"• {name} — {url}")
+        issues = run_pa11y(url)
+        issues_by_guide[name] = issues
+
+    common_codes = compute_common_codes(issues_by_guide)
+
+    lines_out: List[str] = []
+    lines_out.append("\nAccessibility report (WCAG 2.1 AA)")
+    lines_out.append("=" * 40)
+
+    for name, issues in issues_by_guide.items():
+        filtered = [i for i in issues if i["code"] not in common_codes]
+        lines_out.append(f"\nGuide: {name}")
+        if not filtered:
+            lines_out.append("  ✔ No unique issues found.")
+            continue
+        for issue in filtered:
+            lines_out.append(f"  • {format_issue(issue)}")
+
+    report_text = "\n".join(lines_out)
+    print("\n" + report_text)
+    OUTPUT_FILE.write_text(report_text, encoding="utf-8")
+    print(f"\nReport written to {OUTPUT_FILE.resolve()}")
+
+
+if __name__ == "__main__":
+    main()