2c51513851
Reset local main to gitea/master (new source of truth) and restored local-only files: web scrapers, admin dashboard, ChromaDB integration, debug scripts, and utility libraries that aren't tracked in Gitea. Gitea master adds: discovermass, buscarmisas-network, hk-parishes, bohosluzby, kerknet, gottesdienstzeiten, miserend importers, ClaimRequest model, forward geocoding, heartbeat healthcheck. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
46 lines
1.3 KiB
TypeScript
46 lines
1.3 KiB
TypeScript
#!/usr/bin/env tsx
|
|
/**
|
|
* Check the full section text for German church to understand office hours pattern
|
|
*/
|
|
|
|
import { GenericScraper } from '../../src/scrapers/strategies/generic';
|
|
|
|
async function checkGerman() {
|
|
const scraper = new GenericScraper();
|
|
await scraper.init();
|
|
scraper.setCountry('DE');
|
|
|
|
const result = await scraper.scrape('https://www.alterpeter.de/');
|
|
|
|
if (result.rawHtml) {
|
|
const text = result.rawHtml
|
|
.replace(/<script[^>]*>[\s\S]*?<\/script>/gi, '')
|
|
.replace(/<style[^>]*>[\s\S]*?<\/style>/gi, '')
|
|
.replace(/<[^>]+>/g, ' ')
|
|
.replace(/\s+/g, ' ')
|
|
.toLowerCase();
|
|
|
|
// Find Monday section
|
|
const montagIndex = text.indexOf('montag');
|
|
if (montagIndex !== -1) {
|
|
const montagContext = text.substring(montagIndex, montagIndex + 200);
|
|
console.log('=== Monday (Montag) context ===');
|
|
console.log(montagContext);
|
|
console.log('');
|
|
}
|
|
|
|
// Find Sunday section
|
|
const sonntagIndex = text.indexOf('sonntag');
|
|
if (sonntagIndex !== -1) {
|
|
const sonntagContext = text.substring(sonntagIndex, sonntagIndex + 300);
|
|
console.log('=== Sunday (Sonntag) context ===');
|
|
console.log(sonntagContext);
|
|
console.log('');
|
|
}
|
|
}
|
|
|
|
await scraper.close();
|
|
}
|
|
|
|
checkGerman().catch(console.error);
|