from bs4 import BeautifulSoup
import re
from typing import Optional, Dict, List
import cssutils
from html import unescape
class HTMLBeautifier:
"""A comprehensive HTML beautifier and layout fixer"""
def __init__(self):
cssutils.log.setLevel(50) # Suppress cssutils warnings
def beautify(self, html_content: str,
indent_chars: int = 4,
fix_attributes: bool = True,
sort_attributes: bool = False,
remove_empty_tags: bool = True,
fix_self_closing: bool = True,
normalize_whitespace: bool = True,
add_doctype: bool = True) -> str:
"""
Beautify HTML with various layout fixes
Args:
html_content: Raw HTML string
indent_chars: Number of spaces for indentation
fix_attributes: Fix attribute quotes and spacing
sort_attributes: Sort attributes alphabetically
remove_empty_tags: Remove empty tags like
fix_self_closing: Fix self-closing tags
normalize_whitespace: Normalize whitespace in text
add_doctype: Add HTML5 doctype if missing
Returns:
Beautified HTML string
"""
# Parse HTML
soup = BeautifulSoup(html_content, 'html.parser')
# Fix doctype
if add_doctype and not self._has_doctype(html_content):
html_content = '\n' + str(soup)
soup = BeautifulSoup(html_content, 'html.parser')
# Fix structural issues
if fix_self_closing:
self._fix_self_closing_tags(soup)
if remove_empty_tags:
self._remove_empty_tags(soup)
if normalize_whitespace:
self._normalize_whitespace(soup)
if fix_attributes:
self._fix_attributes(soup, sort_attributes)
# Pretty print
pretty_html = soup.prettify(formatter="html")
# Additional formatting improvements
pretty_html = self._additional_formatting(pretty_html, indent_chars)
return pretty_html
def _has_doctype(self, html: str) -> bool:
"""Check if HTML has doctype declaration"""
return bool(re.search(r' 1:
sorted_attrs = sorted(tag.attrs.items())
tag.attrs.clear()
tag.attrs.update(sorted_attrs)
def _additional_formatting(self, html: str, indent_chars: int) -> str:
"""Apply additional formatting improvements"""
lines = html.split('\n')
formatted_lines = []
for line in lines:
# Remove trailing whitespace
line = line.rstrip()
# Ensure proper indentation
if line.strip():
# Count current indentation
current_indent = len(line) - len(line.lstrip())
# Normalize indentation to spaces
line = ' ' * current_indent + line.lstrip()
formatted_lines.append(line)
elif formatted_lines and formatted_lines[-1]: # Avoid multiple blank lines
formatted_lines.append('')
# Remove consecutive blank lines
result = []
prev_empty = False
for line in formatted_lines:
is_empty = len(line.strip()) == 0
if not (is_empty and prev_empty):
result.append(line)
prev_empty = is_empty
return '\n'.join(result)
def minify(self, html_content: str) -> str:
"""Minify HTML by removing unnecessary whitespace"""
soup = BeautifulSoup(html_content, 'html.parser')
# Remove comments
for comment in soup.find_all(string=lambda text: isinstance(text, str) and text.strip().startswith('