Extract the WHATWG HTML attribute index table and count Boolean attributes

count-html-boolean-attributes.sh

#!/usr/bin/env bash

# Count Boolean attributes in the WHATWG HTML attribute index
#
# License: CC0 / Public Domain
# https://creativecommons.org/publicdomain/zero/1.0/
# You may use, modify, and redistribute this script without restriction.
#
# Source table:
# https://html.spec.whatwg.org/multipage/indices.html#attributes-1
#
# Requirements:
#   Python 3
#   beautifulsoup4
#   lxml
#
# This script:
#   1. Downloads the WHATWG attribute index page
#   2. Extracts the table with id="attributes-1"
#   3. Writes the table to CSV for verification
#   4. Counts how many attributes are Boolean

curl -L -o /tmp/indices.html https://html.spec.whatwg.org/multipage/indices.html

python3 <<'PY'
from bs4 import BeautifulSoup

# Parse the downloaded HTML
with open("/tmp/indices.html", "r", encoding="utf-8") as f:
    soup = BeautifulSoup(f, "lxml")

# Locate the attribute index table
table = soup.find("table", id="attributes-1")

boolean_count = 0

# Export table to CSV for verification
with open("/tmp/attributes-1.csv", "w", encoding="utf-8") as out:
    for row in table.find_all("tr"):
        cells = [c.get_text(" ", strip=True) for c in row.find_all(["th","td"])]
        if cells:
            out.write(",".join('"' + c.replace('"','""') + '"' for c in cells) + "\n")

            # Value column is the 4th column
            if len(cells) >= 4 and "boolean" in cells[3].lower():
                boolean_count += 1

print("Boolean attributes:", boolean_count)
print("CSV exported to: /tmp/attributes-1.csv")
PY