header-check.py

#!/usr/bin/env python
from bs4 import BeautifulSoup
import sys

filename = sys.argv[1]

with open(filename) as fp:
    soup = BeautifulSoup(fp, 'html.parser')

def has_tag(name):
    return soup.find(name) is not None

if has_tag('h1') and has_tag('h2') and has_tag('h3') and has_tag('h4') and has_tag('h5') and has_tag('h6'):
    print(f"{filename}: found all header tags")

if len(soup.find_all('h1')) > 1:
    print(f'{filename}: found multiple <h1>')

# Check that there is no <h3> descending from <h2>, or
# other such invalidly nested HTML.
for parent_index in range(1, 6):
    for child_index in range(1, parent_index+1):
        for parent in soup.find_all(f'h{parent_index}'):
            if parent.find(f'h{child_index}') is not None:
                print(f'{filename}: found h{parent_index} > h{child_index}')
                sys.exit(1)