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>
54 lines
1.8 KiB
TypeScript
54 lines
1.8 KiB
TypeScript
#!/usr/bin/env tsx
|
|
/**
|
|
* Verify Paróquia da Paz schedules are correctly parsed
|
|
*/
|
|
|
|
import { GenericScraper } from '../../src/scrapers/strategies/generic';
|
|
|
|
async function verifyPazSchedules() {
|
|
const url = 'https://www.paroquiadapaz.org.br/';
|
|
console.log(`Verifying: ${url}\n`);
|
|
|
|
const scraper = new GenericScraper();
|
|
await scraper.init();
|
|
scraper.setCountry('BR');
|
|
|
|
const result = await scraper.scrape(url);
|
|
|
|
console.log(`✅ Success: ${result.success}`);
|
|
console.log(`📅 Schedules found: ${result.schedules.length}\n`);
|
|
|
|
// Group by day
|
|
const byDay: Record<number, typeof result.schedules> = {};
|
|
for (const sched of result.schedules) {
|
|
if (!byDay[sched.dayOfWeek]) byDay[sched.dayOfWeek] = [];
|
|
byDay[sched.dayOfWeek].push(sched);
|
|
}
|
|
|
|
const dayNames = ['Domingo', 'Segunda', 'Terça', 'Quarta', 'Quinta', 'Sexta', 'Sábado'];
|
|
|
|
console.log('═══════════════════════════════════════════════');
|
|
console.log('PARSED SCHEDULE:');
|
|
console.log('═══════════════════════════════════════════════\n');
|
|
|
|
Object.entries(byDay)
|
|
.sort(([a], [b]) => parseInt(a) - parseInt(b))
|
|
.forEach(([day, scheds]) => {
|
|
console.log(`${dayNames[parseInt(day)]}:`);
|
|
scheds.forEach(s => {
|
|
console.log(` ${s.time} - ${s.language} ${s.massType}`);
|
|
});
|
|
console.log('');
|
|
});
|
|
|
|
console.log('Expected schedule (from website):');
|
|
console.log('Segunda, Terça, Quarta, Sexta: 16:00 e 18:00');
|
|
console.log('Quinta: 16:00 e 19:00');
|
|
console.log('Sábado: 08:00, 16:00 e 18:00');
|
|
console.log('Domingo: 08:00, 11:00, 16:00, 18:00 e 20:00');
|
|
|
|
await scraper.close();
|
|
}
|
|
|
|
verifyPazSchedules().catch(console.error);
|