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 | failed | — | 2026-03-29 10:55:23 | — | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s). |
| discovery_fetch_validation | failed | 2026-03-29 10:51:49 | 2026-03-29 10:55:23 | 3 min 33 s | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s). |
| metadata_alt | completed | 2026-03-29 10:51:49 | 2026-03-29 10:55:22 | 3 min 33 s | — |
| reviews | completed | 2026-03-29 10:52:20 | 2026-03-29 10:55:23 | 3 min 2 s | — |
| taxonomy_enrichment_alt | failed | — | 2026-03-29 10:55:23 | — | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s). |
A futtatás hibával zárult — részletek a stage táblázatban.
{
"execution_id": "41e5d749-46e4-42c5-a37b-cb7bd1570bf6",
"input_url": "https://apponyi.eu/",
"state_filename": "20260329_105148_apponyi_eu.json",
"created_at": "2026-03-29T10:51:48.657721",
"updated_at": "2026-03-29T10:55:23.567286",
"stages": {
"metadata_alt": {
"stage_name": "metadata_alt",
"status": "completed",
"started_at": "2026-03-29T10:51:49.264575",
"completed_at": "2026-03-29T10:55:22.857552",
"result": {
"metadata": {
"company_name": "Apponyi Magánklinika",
"description": "Az Apponyi Magánklinika Kaposváron működő magánegészségügyi intézmény, amely 1992 óta folytat magánrendelést és 1998. május 1-jén nyitotta meg jelen épületét. A klinika kialakulását páciensei kezdeményezése indította el, az épületet Lőrincz Ferenc Ybl-díjas építész tervei alapján építették. Az intézmény folyamatosan bővíti személyi és műszaki kapacitásait; a legutóbbi fejlesztések között ultrahang diagnosztika és terheléses EKG rendszer is szerepel. A klinika szolgáltatásait több orvos közösen biztosítja az irodaházi jellegű rendelői környezetben, törekedve a korszerű, minőségi betegellátásra. A rendelés koordinátora Rucz Károly dr., a klinika kiemelten figyel a páciensek jogaira és az adatvédelemre.",
"arlista_url": "https://www.apponyi.eu/arak",
"varos": "Kaposvár",
"iranyitoszam": "7400",
"utca": "Gróf Apponyi Albert u. 41.",
"telefonszam": "N/A",
"email": "klinika@somogy.hu",
"website": "https://apponyi.eu/"
},
"llm_usage": {
"prompt_tokens": 40559,
"completion_tokens": 969,
"total_tokens": 41528,
"cost": 0.01075295
}
},
"error": null,
"metadata": {}
},
"discovery_fetch_validation": {
"stage_name": "discovery_fetch_validation",
"status": "failed",
"started_at": "2026-03-29T10:51:49.448012",
"completed_at": "2026-03-29T10:55:23.220699",
"result": null,
"error": "Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).",
"metadata": {}
},
"reviews": {
"stage_name": "reviews",
"status": "completed",
"started_at": "2026-03-29T10:52:20.270485",
"completed_at": "2026-03-29T10:55:23.043546",
"result": {
"reviews": {
"company_name": "Apponyi Magánklinika",
"total_reviews": 3,
"average_rating": 5,
"reviews": [
{
"author": "Zsolt Szeness",
"rating": 5,
"text": "Dr. Apponyi Dániel ügyvéd úr, segítségével gördülékenyen és könnyen zárult a volt munkáltatómmal való, munkaügyi jogvita, peren kívüli megegyezéssel.",
"date": null
}
],
"source": "google-maps-scraper",
"postal_code": "",
"city": "",
"street": "",
"phone": ""
}
},
"error": null,
"metadata": {}
},
"data_extraction": {
"stage_name": "data_extraction",
"status": "failed",
"started_at": null,
"completed_at": "2026-03-29T10:55:23.393851",
"result": null,
"error": "Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).",
"metadata": {}
},
"taxonomy_enrichment_alt": {
"stage_name": "taxonomy_enrichment_alt",
"status": "failed",
"started_at": null,
"completed_at": "2026-03-29T10:55:23.567272",
"result": null,
"error": "Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).",
"metadata": {}
}
},
"overall_status": "failed",
"current_stage": "taxonomy_enrichment_alt",
"resume_from_stage": null,
"llm_usage_summary": null
}
Forrás: data/logs — név szerint illeszkedő .log fájlok (API/orchestrator: 41e5d749-46e4-42c5-a37b-cb7bd1570bf6_*.log, CLI: pipeline_41e5d749_*.log).
data/logs/41e5d749-46e4-42c5-a37b-cb7bd1570bf6_20260329_105149.log
2026-03-29 10:51:49 | INFO | prefect.pipeline.parallel | Starting parallel pipeline execution 41e5d749-46e4-42c5-a37b-cb7bd1570bf6 for URL: https://apponyi.eu/
2026-03-29 10:51:49 | INFO | src.stages.stage_2_discovery_async | Starting discovery-fetch-validation (async) for URL: https://apponyi.eu/
2026-03-29 10:51:49 | INFO | src.stages.stage_2_discovery_async | Async discovery config: fetch=curl, output=html, prediction=http://docker-host:8000/predict
2026-03-29 10:51:49 | INFO | src.stages.stage_2_discovery_async | Async crawl starting: https://apponyi.eu/ (max_depth=2, max_concurrent=10)
2026-03-29 10:51:49 | INFO | src.stages.stage_1_metadata_alt | Starting alternative metadata extraction stage
2026-03-29 10:51:49 | INFO | src.stages.stage_1_metadata_alt | Querying metadata for: https://apponyi.eu/
2026-03-29 10:51:49 | INFO | src.stages.stage_1_metadata_alt | Downloading main URL: https://apponyi.eu/
2026-03-29 10:51:49 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 0): https://apponyi.eu/
2026-03-29 10:51:49 | INFO | src.stages.stage_2_discovery_async | Crawl finished: 2 URLs in 0.2s (success=1, errors=0)
2026-03-29 10:51:49 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted 985 characters from main URL
2026-03-29 10:51:49 | INFO | src.stages.stage_1_metadata_alt | Searching for contact pages using OpenSerp
2026-03-29 10:51:49 | INFO | src.stages.stage_1_metadata_alt | Trying OpenSerp API: http://openserp:7000/mega/search with params: {'text': 'cím kapcsolat telefonszám', 'site': 'apponyi.eu', 'limit': '3', 'lang': 'HU'}
2026-03-29 10:51:50 | INFO | src.stages.stage_2_discovery_async | Crawl produced 0 URLs from BERT (threshold and above), fetching all
2026-03-29 10:51:50 | ERROR | src.stages.stage_2_discovery_async | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).
2026-03-29 10:51:50 | INFO | src.stages.stage_2_discovery_async | Attempting fallback: original URL with trafilatura+markdown
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Successfully connected to OpenSerp at http://openserp:7000/mega/search
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | OpenSerp returned 2 results
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Result 1: Adatvédelmi nyilatkozat - Kaposvár - https://www.apponyi.eu/adatvedelmi-nyilatkozat
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Result 2: PDF HONLAPRA - Apponyi - https://www.apponyi.eu/GINOP-3.2.2-8-2-4-16-2019-01873.pdf
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 1/3: https://www.apponyi.eu/adatvedelmi-nyilatkozat
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 17041 characters from contact page 1
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 2/3: https://www.apponyi.eu/GINOP-3.2.2-8-2-4-16-2019-01873.pdf
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 243645 characters from contact page 2
2026-03-29 10:52:11 | INFO | src.stages.stage_1_metadata_alt | Calling OpenRouter for metadata extraction (model=openai/gpt-5-mini)
2026-03-29 10:52:19 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted metadata for: Apponyi Magánklinika
2026-03-29 10:52:19 | INFO | src.stages.stage_1_metadata_alt | Alternative metadata extraction stage completed
2026-03-29 10:52:20 | INFO | src.stages.stage_4_reviews | Starting reviews scraping stage
2026-03-29 10:52:20 | INFO | src.stages.stage_4_reviews | Found metadata directly: company_name=Apponyi Magánklinika, varos=Kaposvár
2026-03-29 10:52:20 | INFO | src.stages.stage_4_reviews | input_path: /tmp/tmp2q7gdymr
2026-03-29 10:52:20 | INFO | src.stages.stage_4_reviews | output_path: /tmp/tmp_23cidu3
2026-03-29 10:52:20 | INFO | src.stages.stage_4_reviews | Running google-maps-scraper (attempt 1/3)
2026-03-29 10:53:56 | INFO | src.stages.stage_4_reviews | google-maps-scraper completed successfully on attempt 1
2026-03-29 10:53:56 | INFO | src.stages.stage_4_reviews | Input fájl mentve: data/review/20260329_105356_apponyi_magánklinika_url_input.txt
2026-03-29 10:53:56 | INFO | src.stages.stage_4_reviews | Output fájl mentve: data/review/20260329_105356_apponyi_magánklinika_url_output.json
2026-03-29 10:53:56 | INFO | src.stages.stage_4_reviews | Reviews scraping completed. Found 1 reviews
2026-03-29 10:53:56 | INFO | prefect.pipeline.parallel | Branch 1 (metadata_alt -> reviews) completed successfully
2026-03-29 10:53:56 | ERROR | prefect.pipeline.parallel | Branch 2 failed: Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).
2026-03-29 10:55:22 | INFO | src.stages.stage_4_reviews | google-maps-scraper completed successfully on attempt 1
2026-03-29 10:55:22 | INFO | src.stages.stage_4_reviews | Input fájl mentve: data/review/20260329_105522_apponyi_magánklinika_url_input.txt
2026-03-29 10:55:22 | INFO | src.stages.stage_4_reviews | Output fájl mentve: data/review/20260329_105522_apponyi_magánklinika_url_output.json
2026-03-29 10:55:22 | INFO | src.stages.stage_4_reviews | Reviews scraping completed. Found 1 reviews
2026-03-29 10:55:23 | INFO | prefect.pipeline.parallel | Branch 1 (metadata_alt -> reviews) completed successfully
2026-03-29 10:55:23 | ERROR | prefect.pipeline.parallel | Branch 2 failed: Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).