This repository has been archived on 2023-02-26. You can view files and clone it, but cannot push or open issues or pull requests.
langue-phundrak-com/web/dart/parse_sitemap.dart

39 lines
1.1 KiB
Dart
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import 'dart:html' show HttpRequest;
import 'package:html/parser.dart' show parse;
// Get the sitemap content
Future<String> getSitemap() async {
const path = 'sitemap.html';
try {
return await HttpRequest.getString(path);
} catch (e) {
print('Couldnt open $path');
}
return 'Error';
}
// This function returns a Map which contains all links to languages detected
// from the sitemap.
Future<Map<String, String>> parseSitemap() async {
var links = <String, String>{};
await getSitemap().then((String content) {
final sitemap = parse(content).getElementsByClassName('org-ul')[0].children;
for (var elem in sitemap) {
// TODO: make this recursive so prefixes in nested folders can be added to
// each other
if (elem.innerHtml.startsWith('<a')) {
elem = elem.firstChild;
final text = elem.firstChild.text;
final url = elem.attributes['href'];
if (!url.contains('index')) {
links[url] = text;
}
} else {
print('Sitemap folder:\n${elem.innerHtml}');
}
}
});
return links;
}