A séma az aktuális config alapján rajzolódik; egy régebbi futtatás más orchestrátorral készülhetett. BPMN-szerű jelölés: zöld kör = kezdőesemény, kék + rombusz = párhuzamos fork/join, lekerekített téglalap = task (szín = státusz), dupla piros kör = befejezés. Egér a task fölött: részletek (státusz, időpontok, hiba).
| Stage | Státusz | Indult | Befejezve | Időtartam | Hiba |
|---|---|---|---|---|---|
| data_extraction | completed | 2026-03-28 17:04:22 | 2026-03-28 17:08:00 | 3 min 37 s | — |
| discovery_fetch_validation | completed | 2026-03-28 17:04:13 | 2026-03-28 17:07:59 | 3 min 46 s | — |
| metadata_alt | completed | 2026-03-28 17:04:13 | 2026-03-28 17:07:59 | 3 min 46 s | — |
| reviews | completed | 2026-03-28 17:04:56 | 2026-03-28 17:07:59 | 3 min 2 s | — |
| taxonomy_enrichment_alt | completed | 2026-03-28 17:04:23 | 2026-03-28 17:08:00 | 3 min 36 s | — |
| Szolgáltatás | Ár | Kategória | a / v |
|---|---|---|---|
| Szemészeti szakorvosi vizsgálat | 20000 | Szemészet | Szemészet / 0.7464370912082655 |
| Szemészeti kontroll | 15000 | Szemészet | Szemészet / 0.6850837979320755 |
| Receptfelírás | 3000 | Szemészet | Szemészet / 0.6169972400865555 |
| OCT vizsgálat | 5000 | Szemészet | Szemészet / 0.7774161437575036 |
{
"execution_id": "b9524474-24cd-4b12-aaf5-f67e50e6aab5",
"input_url": "https://starlens.hu/",
"state_filename": "20260328_170412_starlens_hu.json",
"created_at": "2026-03-28T17:04:12.843652",
"updated_at": "2026-03-28T17:08:00.598304",
"stages": {
"metadata_alt": {
"stage_name": "metadata_alt",
"status": "completed",
"started_at": "2026-03-28T17:04:13.301934",
"completed_at": "2026-03-28T17:07:59.549065",
"result": {
"metadata": {
"company_name": "Starlens magán szemészeti rendelő Nagykőrös",
"description": "A Star-Lens (Starlens) magán szemészeti szakrendelő 2024-ben alakult azzal a céllal, hogy a legmodernebb szemészeti ellátást biztosítsa pácienseinek. Rendelőnk korszerű műszerekkel és technológiával dolgozik a pontos diagnózis és a leghatékonyabb kezelés érdekében. Szakorvosaink, köztük Dr. Tinka Tímea Réka és Dr. Böcskei Zsolt, kiemelkedő tapasztalattal végzik a vizsgálatokat. Célunk a személyre szabott, magas színvonalú ellátás nyújtása a jobb látásélmény és életminőség biztosítására. Rendelőnk Nagykőrösön, könnyen megközelíthető helyen várja a pácienseket, és részletes tájékoztatást, vizsgálati illetve díj információkat is közzétesz weboldalán.",
"arlista_url": "https://starlens.hu/szemeszeti-vizsgalatok-dija",
"varos": "Nagykőrös",
"iranyitoszam": "2750",
"utca": "Biczó Géza u. 2.",
"telefonszam": "+36 70 537 1310",
"email": "N/A",
"website": "https://starlens.hu/"
},
"llm_usage": {
"prompt_tokens": 8778,
"completion_tokens": 1363,
"total_tokens": 10141,
"cost": 0.0033365
}
},
"error": null,
"metadata": {}
},
"discovery_fetch_validation": {
"stage_name": "discovery_fetch_validation",
"status": "completed",
"started_at": "2026-03-28T17:04:13.490676",
"completed_at": "2026-03-28T17:07:59.958307",
"result": {
"pages": [
{
"source_url": "https://starlens.hu/szemeszeti-vizsgalatok-dija",
"discovered_url": "https://starlens.hu/szemeszeti-vizsgalatok-dija",
"input_strategy": "async_crawl_bert",
"fetch_strategy": "curl",
"output_strategy": "html",
"strategy": "async_crawl_bert,curl,html",
"original_url": "https://starlens.hu/",
"validation_passed": true,
"ft_count": 4,
"score": 0.9993219375610352,
"attempts": 1
}
],
"original_url": "https://starlens.hu/",
"strategy": "async_crawl_bert,curl,html"
},
"error": null,
"metadata": {}
},
"data_extraction": {
"stage_name": "data_extraction",
"status": "completed",
"started_at": "2026-03-28T17:04:22.176254",
"completed_at": "2026-03-28T17:08:00.160525",
"result": {
"number_of_price_items": 4,
"price_items": [
{
"s": "Szemészeti szakorvosi vizsgálat",
"p": 20000,
"c": "Szemészet",
"a": "Szemészet",
"v": 0.7464370912082655
},
{
"s": "Szemészeti kontroll",
"p": 15000,
"c": "Szemészet",
"a": "Szemészet",
"v": 0.6850837979320755
},
{
"s": "Receptfelírás",
"p": 3000,
"c": "Szemészet",
"a": "Szemészet",
"v": 0.6169972400865555
},
{
"s": "OCT vizsgálat",
"p": 5000,
"c": "Szemészet",
"a": "Szemészet",
"v": 0.7774161437575036
}
],
"llm_usage": {
"prompt_tokens": 1338,
"completion_tokens": 122,
"total_tokens": 1460,
"cost": 0.00036864
}
},
"error": null,
"metadata": {}
},
"taxonomy_enrichment_alt": {
"stage_name": "taxonomy_enrichment_alt",
"status": "completed",
"started_at": "2026-03-28T17:04:23.949882",
"completed_at": "2026-03-28T17:08:00.383050",
"result": {
"summary": {
"provider": "openrouter",
"embedding_model": "openai/text-embedding-3-large",
"items_total": 4,
"items_processed": 4,
"avg_best_similarity": 0.7064835682460999,
"min_best_similarity": 0.6169972400865555,
"max_best_similarity": 0.7774161437575036,
"cache_hit": true,
"cache_file": "data/taxonomy_embeddings/openrouter_openai_text_embedding_3_large.json"
},
"predictions": [
{
"idx": 0,
"s": "Szemészeti szakorvosi vizsgálat",
"c": "Szemészet",
"best_a": "Szemészet",
"best_similarity": 0.7464370912082655
},
{
"idx": 1,
"s": "Szemészeti kontroll",
"c": "Szemészet",
"best_a": "Szemészet",
"best_similarity": 0.6850837979320755
},
{
"idx": 2,
"s": "Receptfelírás",
"c": "Szemészet",
"best_a": "Szemészet",
"best_similarity": 0.6169972400865555
},
{
"idx": 3,
"s": "OCT vizsgálat",
"c": "Szemészet",
"best_a": "Szemészet",
"best_similarity": 0.7774161437575036
}
],
"llm_usage": {
"prompt_tokens": 50,
"completion_tokens": 0,
"total_tokens": 50,
"cost": 6.5e-6
}
},
"error": null,
"metadata": {}
},
"reviews": {
"stage_name": "reviews",
"status": "completed",
"started_at": "2026-03-28T17:04:56.883227",
"completed_at": "2026-03-28T17:07:59.754600",
"result": {
"reviews": {
"company_name": "Starlens magán szemészeti rendelő Nagykőrös",
"total_reviews": 0,
"average_rating": null,
"reviews": [],
"source": "google-maps-scraper",
"postal_code": "1056",
"city": "Budapest",
"street": "Irányi u. 1",
"phone": "(06 1) 318 2418"
}
},
"error": null,
"metadata": {}
}
},
"overall_status": "completed",
"current_stage": "taxonomy_enrichment_alt",
"resume_from_stage": null,
"llm_usage_summary": {
"prompt_tokens": 10166,
"completion_tokens": 1485,
"total_tokens": 11651,
"cost": 0.00371164
}
}
Forrás: data/logs — név szerint illeszkedő .log fájlok (API/orchestrator: b9524474-24cd-4b12-aaf5-f67e50e6aab5_*.log, CLI: pipeline_b9524474_*.log).
data/logs/b9524474-24cd-4b12-aaf5-f67e50e6aab5_20260328_170413.log
2026-03-28 17:04:13 | INFO | prefect.pipeline.parallel | Starting parallel pipeline execution b9524474-24cd-4b12-aaf5-f67e50e6aab5 for URL: https://starlens.hu/
2026-03-28 17:04:13 | INFO | src.stages.stage_1_metadata_alt | Starting alternative metadata extraction stage
2026-03-28 17:04:13 | INFO | src.stages.stage_1_metadata_alt | Querying metadata for: https://starlens.hu/
2026-03-28 17:04:13 | INFO | src.stages.stage_2_discovery_async | Starting discovery-fetch-validation (async) for URL: https://starlens.hu/
2026-03-28 17:04:13 | INFO | src.stages.stage_2_discovery_async | Async discovery config: fetch=curl, output=html, prediction=http://docker-host:8000/predict
2026-03-28 17:04:13 | INFO | src.stages.stage_2_discovery_async | Async crawl starting: https://starlens.hu/ (max_depth=2, max_concurrent=10)
2026-03-28 17:04:13 | INFO | src.stages.stage_1_metadata_alt | Downloading main URL: https://starlens.hu/
2026-03-28 17:04:13 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 0): https://starlens.hu/
2026-03-28 17:04:13 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted 692 characters from main URL
2026-03-28 17:04:13 | INFO | src.stages.stage_1_metadata_alt | Searching for contact pages using OpenSerp
2026-03-28 17:04:13 | INFO | src.stages.stage_1_metadata_alt | Trying OpenSerp API: http://openserp:7000/mega/search with params: {'text': 'cím kapcsolat telefonszám', 'site': 'starlens.hu', 'limit': '3', 'lang': 'HU'}
2026-03-28 17:04:14 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/sutiszabalyzat
2026-03-28 17:04:14 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/adatvedelem
2026-03-28 17:04:14 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/megkozelites
2026-03-28 17:04:14 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/szemeszeti-vizsgalatok-dija
2026-03-28 17:04:14 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/szemeszeti-vizsgalatok
2026-03-28 17:04:16 | INFO | src.stages.stage_2_discovery_async | Crawl finished: 21 URLs in 3.4s (success=6, errors=2)
2026-03-28 17:04:21 | INFO | src.stages.stage_2_discovery_async | Crawl produced 1 URLs from BERT (threshold and above), fetching all
2026-03-28 17:04:21 | INFO | src.stages.stage_2_discovery_async | [URL 1/1] Fetching (BERT prob=1.00): https://starlens.hu/szemeszeti-vizsgalatok-dija
2026-03-28 17:04:21 | INFO | src.stages.stage_2_discovery_async | [URL 1/1] OK (BERT prob=1.00)
2026-03-28 17:04:21 | INFO | src.stages.stage_2_discovery_async | Discovery (async) completed with 1 page(s)
2026-03-28 17:04:21 | INFO | src.stages.stage_2_discovery_async | Detailed logs saved to: data/logs/b9524474-24cd-4b12-aaf5-f67e50e6aab5_20260328_170413.log
2026-03-28 17:04:22 | INFO | src.stages.stage_3_data_extraction | Data extraction: 1 page(s) to process
2026-03-28 17:04:23 | INFO | src.stages.stage_3_data_extraction | Extracted 4 price items from page 1
2026-03-28 17:04:23 | INFO | src.stages.stage_3_data_extraction | Data extraction stage completed: 4 total price items from 1 page(s)
2026-03-28 17:04:23 | INFO | src.stages.stage_5_taxonomy_enrichment_alt | Starting taxonomy enrichment alt stage (embeddings)
2026-03-28 17:04:24 | INFO | src.stages.stage_5_taxonomy_enrichment_alt | taxonomy_enrichment_alt: loaded cached label embeddings from data/taxonomy_embeddings/openrouter_openai_text_embedding_3_large.json
2026-03-28 17:04:24 | INFO | src.stages.stage_5_taxonomy_enrichment_alt | taxonomy_enrichment_alt summary: processed=4 avg=0.7065 min=0.6170 max=0.7774 cache_hit=True model=openai/text-embedding-3-large provider=openrouter
2026-03-28 17:04:24 | INFO | src.stages.stage_5_taxonomy_enrichment_alt | taxonomy_enrichment_alt weakest_matches: [{'idx': 2, 's': 'Receptfelírás', 'c': 'Szemészet', 'best_a': 'Szemészet', 'best_similarity': 0.6169972400865555}, {'idx': 1, 's': 'Szemészeti kontroll', 'c': 'Szemészet', 'best_a': 'Szemészet', 'best_similarity': 0.6850837979320755}, {'idx': 0, 's': 'Szemészeti szakorvosi vizsgálat', 'c': 'Szemészet', 'best_a': 'Szemészet', 'best_similarity': 0.7464370912082655}]
2026-03-28 17:04:24 | INFO | src.stages.stage_5_taxonomy_enrichment_alt | taxonomy_enrichment_alt stage completed
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Successfully connected to OpenSerp at http://openserp:7000/mega/search
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | OpenSerp returned 3 results
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Result 1: Starlens magán szemészeti rendelő Nagykőrös - https://starlens.hu/
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Result 2: Adatvédelem - Starlens magán szemészeti rendelő Nagykőrös - https://starlens.hu/adatvedelem
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Result 3: Szemészeti vizsgálatok - starlens.hu - https://starlens.hu/szemeszeti-vizsgalatok
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 1/3: https://starlens.hu/
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 2439 characters from contact page 1
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 2/3: https://starlens.hu/adatvedelem
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 17195 characters from contact page 2
2026-03-28 17:04:35 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 3/3: https://starlens.hu/szemeszeti-vizsgalatok
2026-03-28 17:04:36 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 2956 characters from contact page 3
2026-03-28 17:04:36 | INFO | src.stages.stage_1_metadata_alt | Calling OpenRouter for metadata extraction (model=openai/gpt-5-mini)
2026-03-28 17:04:56 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted metadata for: Starlens magán szemészeti rendelő Nagykőrös
2026-03-28 17:04:56 | INFO | src.stages.stage_1_metadata_alt | Alternative metadata extraction stage completed
2026-03-28 17:04:56 | INFO | src.stages.stage_4_reviews | Starting reviews scraping stage
2026-03-28 17:04:56 | INFO | src.stages.stage_4_reviews | Found metadata directly: company_name=Starlens magán szemészeti rendelő Nagykőrös, varos=Nagykőrös
2026-03-28 17:04:56 | INFO | src.stages.stage_4_reviews | input_path: /tmp/tmp866fl9m3
2026-03-28 17:04:56 | INFO | src.stages.stage_4_reviews | output_path: /tmp/tmpew5h8ee1
2026-03-28 17:04:56 | INFO | src.stages.stage_4_reviews | Running google-maps-scraper (attempt 1/3)
2026-03-28 17:05:18 | INFO | prefect.pipeline.parallel | Starting parallel pipeline execution 1008151b-1f64-425d-8a0d-01934eb5ea94 for URL: https://www.borokaegeszseghaz.hu/
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Starting discovery-fetch-validation (async) for URL: https://www.borokaegeszseghaz.hu/
2026-03-28 17:05:18 | INFO | src.stages.stage_1_metadata_alt | Starting alternative metadata extraction stage
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Async discovery config: fetch=curl, output=html, prediction=http://docker-host:8000/predict
2026-03-28 17:05:18 | INFO | src.stages.stage_1_metadata_alt | Querying metadata for: https://www.borokaegeszseghaz.hu/
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Async crawl starting: https://www.borokaegeszseghaz.hu/ (max_depth=2, max_concurrent=10)
2026-03-28 17:05:18 | INFO | src.stages.stage_1_metadata_alt | Downloading main URL: https://www.borokaegeszseghaz.hu/
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 0): https://www.borokaegeszseghaz.hu/
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://www.borokaegeszseghaz.hu/hirek
2026-03-28 17:05:18 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted 2154 characters from main URL
2026-03-28 17:05:18 | INFO | src.stages.stage_1_metadata_alt | Searching for contact pages using OpenSerp
2026-03-28 17:05:18 | INFO | src.stages.stage_1_metadata_alt | Trying OpenSerp API: http://openserp:7000/mega/search with params: {'text': 'cím kapcsolat telefonszám', 'site': 'borokaegeszseghaz.hu', 'limit': '3', 'lang': 'HU'}
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://www.borokaegeszseghaz.hu/arlista
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://www.borokaegeszseghaz.hu/elerhetoseg
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://www.borokaegeszseghaz.hu/rendelesi-idok
2026-03-28 17:05:18 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://www.borokaegeszseghaz.hu/elojegyzes
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/aldott-husveti-unnepeket-kivanunk
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://www.borokaegeszseghaz.hu/rolunk
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://www.borokaegeszseghaz.hu/kollegak
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/unnepi-nyitvatartas
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/figyelemfelhivas-1
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/figyelemfelhivas-0
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/ajandekozzon-egeszseget-boroka-egeszsegkartyaval
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/rendelesvaltozas
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/figyelemfelhivas
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/kerjuk-erkezzenek-10-perccel-korabban
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/idopontfoglalas-1100-tol-1800-ig-lehetseges
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/prosztatacentrum
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/teriteses-szuroprogramjaink
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/riport-dr-orosz-orsolyaval-az-rtl-klub-reggeli-cimu-musoraban
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/egyenre-szabott-manager-szures
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/sztopka-anna-kortars-festomuvesz-kiallitasa
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/bemer-terapia
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/hirek?page=0
2026-03-28 17:05:19 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/hirek?page=1
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/csomos-istvan
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-andrassy-ilona
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-barkovics-maria-angella
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-hella-zoltan
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-gonczi-nora
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-gyorffy-laszlo
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-kaszas-annamaria
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-herczegh-istvan
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-molnar-csaba
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-satori-maria
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-orosz-orsolya
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-sebestyen-gyongyi-maria
2026-03-28 17:05:20 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-siroki-xenia
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-szabo-melinda
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-szabady-monika
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-szabo-monika
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-szemeredi-peter
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-vagacs-tibor
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-szekely-gabriella
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/dr-varhegyi-aniko
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/duliskovich-ilona
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 2): https://www.borokaegeszseghaz.hu/orvosaink/leman-szilvia
2026-03-28 17:05:21 | INFO | src.stages.stage_2_discovery_async | Crawl finished: 47 URLs in 3.2s (success=47, errors=0)
2026-03-28 17:05:34 | INFO | src.stages.stage_2_discovery_async | Crawl produced 0 URLs from BERT (threshold and above), fetching all
2026-03-28 17:05:34 | ERROR | src.stages.stage_2_discovery_async | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).
2026-03-28 17:05:34 | INFO | src.stages.stage_2_discovery_async | Attempting fallback: original URL with trafilatura+markdown
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Successfully connected to OpenSerp at http://openserp:7000/mega/search
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | OpenSerp returned 5 results
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Result 1: Dr. Andrássy Ilona | Boróka Egészségház - https://www.borokaegeszseghaz.hu/orvosaink/dr-andrassy-ilona
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Result 2: Kapcsolat - https://www.borokaegeszseghaz.hu/kapcsolat
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Result 3: PDF BOMM Kft. Adószám Lt - borokaegeszseghaz.hu - https://www.borokaegeszseghaz.hu/sites/default/files/20260130%20BOMM%20Kft%20m.pdf
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 1/3: https://www.borokaegeszseghaz.hu/orvosaink/dr-andrassy-ilona
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 2643 characters from contact page 1
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 2/3: https://www.borokaegeszseghaz.hu/kapcsolat
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 1338 characters from contact page 2
2026-03-28 17:05:39 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 3/3: https://www.borokaegeszseghaz.hu/sites/default/files/20260130%20BOMM%20Kft%20m.pdf
2026-03-28 17:05:40 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 260742 characters from contact page 3
2026-03-28 17:05:40 | INFO | src.stages.stage_1_metadata_alt | Calling OpenRouter for metadata extraction (model=openai/gpt-5-mini)
2026-03-28 17:05:55 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted metadata for: Boróka Egészségház
2026-03-28 17:05:55 | INFO | src.stages.stage_1_metadata_alt | Alternative metadata extraction stage completed
2026-03-28 17:05:55 | INFO | src.stages.stage_4_reviews | Starting reviews scraping stage
2026-03-28 17:05:55 | INFO | src.stages.stage_4_reviews | Found metadata directly: company_name=Boróka Egészségház, varos=Gödöllő
2026-03-28 17:05:55 | INFO | src.stages.stage_4_reviews | input_path: /tmp/tmpjn39b0c5
2026-03-28 17:05:55 | INFO | src.stages.stage_4_reviews | output_path: /tmp/tmpt7jthsx2
2026-03-28 17:05:55 | INFO | src.stages.stage_4_reviews | Running google-maps-scraper (attempt 1/3)
2026-03-28 17:06:23 | INFO | src.stages.stage_4_reviews | google-maps-scraper: early exit (reviews found in output for URL) on attempt 1
2026-03-28 17:06:23 | INFO | src.stages.stage_4_reviews | Input fájl mentve: data/review/20260328_170623_boróka_egészségház_url_input.txt
2026-03-28 17:06:23 | INFO | src.stages.stage_4_reviews | Output fájl mentve: data/review/20260328_170623_boróka_egészségház_url_output.json
2026-03-28 17:06:23 | INFO | src.stages.stage_4_reviews | Reviews scraping completed. Found 8 reviews
2026-03-28 17:06:23 | INFO | prefect.pipeline.parallel | Branch 1 (metadata_alt -> reviews) completed successfully
2026-03-28 17:06:23 | ERROR | prefect.pipeline.parallel | Branch 2 failed: Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).
2026-03-28 17:07:59 | INFO | src.stages.stage_4_reviews | google-maps-scraper completed successfully on attempt 1
2026-03-28 17:07:59 | INFO | src.stages.stage_4_reviews | Input fájl mentve: data/review/20260328_170759_starlens_magán_szemészeti_rendelő_nagykőrös_url_input.txt
2026-03-28 17:07:59 | INFO | src.stages.stage_4_reviews | Output fájl mentve: data/review/20260328_170759_starlens_magán_szemészeti_rendelő_nagykőrös_url_output.json
2026-03-28 17:07:59 | INFO | src.stages.stage_4_reviews | Reviews scraping completed. Found 0 reviews
2026-03-28 17:07:59 | INFO | prefect.pipeline.parallel | Branch 1 (metadata_alt -> reviews) completed successfully
2026-03-28 17:08:00 | INFO | prefect.pipeline.parallel | Branch 2 (discovery -> data_extraction -> taxonomy_enrichment_alt) completed successfully
2026-03-28 17:08:00 | INFO | prefect.pipeline.parallel | Pipeline execution b9524474-24cd-4b12-aaf5-f67e50e6aab5 completed