How to Remove HTML tags from String in Flutter/Dart

import 'package:flutter/material.dart';

void main() {
  runApp(const MaterialApp(home: ModernHtmlStripperDemo()));
}

/// Production utility for stripping HTML markup, scripts, styles, and unescaping entities.
class HtmlStripper {
  static final RegExp _scriptBlock = RegExp(
    r'<script[^>]*>[\s\S]*?<\/script>',
    caseSensitive: false,
  );
  static final RegExp _styleBlock = RegExp(
    r'<style[^>]*>[\s\S]*?<\/style>',
    caseSensitive: false,
  );
  static final RegExp _htmlTag = RegExp(r'<[^>]+>');
  static final RegExp _multiWhitespace = RegExp(r'[ \t]+');
  static final RegExp _multiNewline = RegExp(r'\n\s*\n');

  /// Common HTML entity unescape table.
  static final Map<String, String> _entities = {
    ' ': ' ',
    '&': '&',
    '<': '<',
    '>': '>',
    '"': '"',
    ''': "'",
    '&apos;': "'",
    '©': '©',
    '®': '®',
    '—': '—',
    '–': '–',
  };

  /// Strips all HTML markup, script/style blocks, and converts HTML entities to plain text.
  static String strip(String html) {
    if (html.isEmpty) return '';

    // 1. Remove dangerous or non-content blocks (scripts, styles)
    var text = html.replaceAll(_scriptBlock, '');
    text = text.replaceAll(_styleBlock, '');

    // 2. Replace block breaks (<br>, </p>, </div>, </li>, </h1>..</h6>) with newlines
    text = text.replaceAll(RegExp(r'<br\s*\/?>', caseSensitive: false), '\n');
    text = text.replaceAll(
      RegExp(r'<\/(p|div|li|h[1-6]|tr)>', caseSensitive: false),
      '\n',
    );

    // 3. Remove all remaining tags
    text = text.replaceAll(_htmlTag, '');

    // 4. Unescape standard HTML entities
    _entities.forEach((entity, replacement) {
      text = text.replaceAll(entity, replacement);
    });

    // 5. Decode numeric entities (e.g. A or A)
    text = text.replaceAllMapped(RegExp(r'&#(x?[0-9a-fA-F]+);'), (m) {
      final codeStr = m.group(1)!;
      try {
        final code = codeStr.startsWith('x') || codeStr.startsWith('X')
            ? int.parse(codeStr.substring(1), radix: 16)
            : int.parse(codeStr);
        return String.fromCharCode(code);
      } catch (_) {
        return m.group(0)!;
      }
    });

    // 6. Normalize whitespace
    text = text.replaceAll(_multiWhitespace, ' ');
    text = text.replaceAll(_multiNewline, '\n\n');

    return text.trim();
  }
}

class ModernHtmlStripperDemo extends StatefulWidget {
  const ModernHtmlStripperDemo({super.key});

  @override
  State<ModernHtmlStripperDemo> createState() => _ModernHtmlStripperDemoState();
}

class _ModernHtmlStripperDemoState extends State<ModernHtmlStripperDemo> {
  final TextEditingController _inputController = TextEditingController();
  String _strippedText = '';

  static const _sampleHtml =
      '<h2>Flutter & Dart</h2>'
      '<p>Learn how to <b>strip HTML tags</b> safely without heavy dependencies.</p>'
      '<p>Visit <a href="https://flutterdocs.dev">FlutterDocs</a> © 2026.</p>';

  @override
  void initState() {
    super.initState();
    _inputController.text = _sampleHtml;
    _strip();
  }

  @override
  void dispose() {
    _inputController.dispose();
    super.dispose();
  }

  void _strip() {
    setState(() {
      _strippedText = HtmlStripper.strip(_inputController.text);
    });
  }

  @override
  Widget build(BuildContext context) {
    final theme = Theme.of(context);

    return Scaffold(
      appBar: AppBar(title: const Text('HTML Stripper & Entity Decoder')),
      body: SingleChildScrollView(
        padding: const EdgeInsets.all(20.0),
        child: Column(
          crossAxisAlignment: CrossAxisAlignment.stretch,
          children: [
            Text('HTML Source Input:', style: theme.textTheme.titleMedium),
            const SizedBox(height: 8),
            TextField(
              controller: _inputController,
              maxLines: 5,
              decoration: const InputDecoration(
                border: OutlineInputBorder(),
                hintText: 'Enter HTML snippet...',
              ),
              onChanged: (_) => _strip(),
            ),
            const SizedBox(height: 20),
            Text('Plain Text Output:', style: theme.textTheme.titleMedium),
            const SizedBox(height: 8),
            Card(
              elevation: 0,
              color: theme.colorScheme.surfaceContainerHighest,
              child: Padding(
                padding: const EdgeInsets.all(16.0),
                child: SelectableText(
                  _strippedText,
                  key: const Key('stripped-text-output'),
                  style: theme.textTheme.bodyLarge,
                ),
              ),
            ),
          ],
        ),
      ),
    );
  }
}