All files / scripts extract-news-metadata.ts

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
/**
 * Extract News Article Metadata to JSON Database
 *
 * Parses all news article HTML files and extracts Schema.org JSON-LD
 * metadata into a single data/news-articles.json file.
 *
 * Usage: node --experimental-strip-types scripts/extract-news-metadata.ts
 *
 * @module scripts/extract-news-metadata
 */
 
import { readFileSync, writeFileSync, readdirSync, mkdirSync } from 'fs';
import { join, dirname } from 'path';
import { fileURLToPath } from 'url';
 
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
const ROOT = join(__dirname, '..');
 
interface ArticleMetadata {
  slug: string;
  file: string;
  lang: string;
  headline: string;
  description: string;
  datePublished: string;
  dateModified: string;
  articleSection: string;
  wordCount: number;
  inLanguage: string;
  keywords: string;
  image: string;
  url: string;
}
 
interface NewsDatabase {
  version: string;
  generatedAt: string;
  totalArticles: number;
  uniqueSlugs: number;
  languages: string[];
  articles: ArticleMetadata[];
}
 
interface JsonLdArticle {
  '@type'?: string;
  headline?: string;
  description?: string;
  datePublished?: string;
  dateModified?: string;
  articleSection?: string;
  wordCount?: number;
  inLanguage?: string;
  keywords?: string;
  mainEntityOfPage?: { '@id'?: string };
  url?: string;
}
 
function extractMetadata(): void {
  const newsDir = join(ROOT, 'news');
  const files = readdirSync(newsDir)
    .filter((f: string) => f.endsWith('.html') && !f.startsWith('index'));
 
  const articles: ArticleMetadata[] = [];
 
  for (const file of files) {
    const content = readFileSync(join(newsDir, file), 'utf-8');
 
    // Extract JSON-LD blocks
    const jsonLdRegex = /<script type="application\/ld\+json">([\s\S]*?)<\/script>/g;
    let match: RegExpExecArray | null;
    let articleData: JsonLdArticle | null = null;
 
    while ((match = jsonLdRegex.exec(content)) !== null) {
      try {
        const parsed = JSON.parse(match[1]!) as JsonLdArticle;
        if (parsed['@type'] === 'NewsArticle') {
          articleData = parsed;
          break;
        }
      } catch {
        // Skip malformed JSON-LD
      }
    }
 
    if (!articleData) {
      console.warn(`WARN: No NewsArticle JSON-LD in ${file}`);
      continue;
    }
 
    // Extract Open Graph image
    const ogImageMatch = content.match(/property="og:image" content="([^"]+)"/);
    const ogImage: string = ogImageMatch?.[1] ?? '';
 
    // Extract language from filename
    const langMatch = file.match(/-([a-z]{2})\.html$/);
    const lang: string = langMatch?.[1] ?? 'en';
 
    // Extract slug (filename without language suffix)
    const slug = file.replace(/-[a-z]{2}\.html$/, '');
 
    articles.push({
      slug,
      file,
      lang,
      headline: articleData.headline ?? '',
      description: articleData.description ?? '',
      datePublished: articleData.datePublished ?? '',
      dateModified: articleData.dateModified ?? '',
      articleSection: articleData.articleSection ?? '',
      wordCount: articleData.wordCount || (() => {
        const stripped = content.replace(/<[^>]+>/g, ' ');
        return stripped.split(/\s+/).filter((w: string) => w.length > 0).length;
      })(),
      inLanguage: articleData.inLanguage ?? lang as string,
      keywords: articleData.keywords ?? '',
      image: ogImage as string,
      url: articleData.mainEntityOfPage?.['@id'] ?? '',
    });
  }
 
  // Sort by date descending, then by language
  articles.sort((a, b) => {
    const dateCompare = b.datePublished.localeCompare(a.datePublished);
    if (dateCompare !== 0) return dateCompare;
    return a.lang.localeCompare(b.lang);
  });
 
  const db: NewsDatabase = {
    version: '1.0.0',
    generatedAt: new Date().toISOString(),
    totalArticles: articles.length,
    uniqueSlugs: [...new Set(articles.map((a) => a.slug))].length,
    languages: [...new Set(articles.map((a) => a.lang))].sort(),
    articles,
  };
 
  mkdirSync(join(ROOT, 'data'), { recursive: true });
  writeFileSync(join(ROOT, 'data', 'news-articles.json'), JSON.stringify(db, null, 2));
 
  console.log('Generated data/news-articles.json:');
  console.log('  Total articles:', db.totalArticles);
  console.log('  Unique slugs:', db.uniqueSlugs);
  console.log('  Languages:', db.languages.join(', '));
  console.log('  File size:', (JSON.stringify(db).length / 1024).toFixed(1), 'KB');
}
 
extractMetadata();