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 | — | 2026-03-28 16:23:58 | — | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s). |
| discovery_fetch_validation | failed | 2026-03-28 16:20:20 | 2026-03-28 16:23:58 | 3 min 37 s | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s). |
| metadata_alt | completed | 2026-03-28 16:20:20 | 2026-03-28 16:23:58 | 3 min 37 s | — |
| reviews | completed | 2026-03-28 16:20:55 | 2026-03-28 16:23:58 | 3 min 2 s | — |
| taxonomy_enrichment_alt | failed | — | 2026-03-28 16:23:58 | — | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s). |
A futtatás hibával zárult — részletek a stage táblázatban.
{
"execution_id": "aebe1122-f2d0-4e29-8a13-8fb57fb7ee64",
"input_url": "https://starlens.hu/",
"state_filename": "20260328_162020_starlens_hu.json",
"created_at": "2026-03-28T16:20:20.127527",
"updated_at": "2026-03-28T16:23:58.539825",
"stages": {
"metadata_alt": {
"stage_name": "metadata_alt",
"status": "completed",
"started_at": "2026-03-28T16:20:20.544239",
"completed_at": "2026-03-28T16:23:58.052603",
"result": {
"metadata": {
"company_name": "Starlens magán szemészeti rendelő Nagykőrös",
"description": "A Starlens magán szemészeti rendelő 2024-ben jött létre azzal a céllal, hogy korszerű és személyre szabott szemészeti ellátást nyújtson pácienseinek. Rendelőnkben modern műszerekkel és fejlett technológiákkal dolgozunk a pontos diagnózis és hatékony kezelés érdekében. Csapatunkot tapasztalt szakorvosok alkotják, köztük Dr. Tinka Tímea Réka és Dr. Böcskei Zsolt. Kiemelt célunk a magas szakmai színvonal, a gondos betegellátás és a javuló látásélmény biztosítása. Várjuk szeretettel pácienseinket barátságos, biztonságos környezetben.",
"arlista_url": "/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": 7658,
"completion_tokens": 866,
"total_tokens": 8524,
"cost": 0.0036465
}
},
"error": null,
"metadata": {}
},
"discovery_fetch_validation": {
"stage_name": "discovery_fetch_validation",
"status": "failed",
"started_at": "2026-03-28T16:20:20.660244",
"completed_at": "2026-03-28T16:23:58.301146",
"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": "2026-03-28T16:20:55.442752",
"completed_at": "2026-03-28T16:23:58.172932",
"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": {}
},
"data_extraction": {
"stage_name": "data_extraction",
"status": "failed",
"started_at": null,
"completed_at": "2026-03-28T16:23:58.418390",
"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": "2026-03-28T16:23:58.539811",
"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: aebe1122-f2d0-4e29-8a13-8fb57fb7ee64_*.log, CLI: pipeline_aebe1122_*.log).
data/logs/aebe1122-f2d0-4e29-8a13-8fb57fb7ee64_20260328_162020.log
2026-03-28 16:20:20 | INFO | prefect.pipeline.parallel | Starting parallel pipeline execution aebe1122-f2d0-4e29-8a13-8fb57fb7ee64 for URL: https://starlens.hu/
2026-03-28 16:20:20 | INFO | src.stages.stage_1_metadata_alt | Starting alternative metadata extraction stage
2026-03-28 16:20:20 | INFO | src.stages.stage_1_metadata_alt | Querying metadata for: https://starlens.hu/
2026-03-28 16:20:20 | INFO | src.stages.stage_2_discovery_async | Starting discovery-fetch-validation (async) for URL: https://starlens.hu/
2026-03-28 16:20:20 | INFO | src.stages.stage_2_discovery_async | Async discovery config: fetch=curl, output=html, prediction=http://docker-host:8000/predict
2026-03-28 16:20:20 | INFO | src.stages.stage_2_discovery_async | Async crawl starting: https://starlens.hu/ (max_depth=2, max_concurrent=10)
2026-03-28 16:20:20 | INFO | src.stages.stage_1_metadata_alt | Downloading main URL: https://starlens.hu/
2026-03-28 16:20:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 0): https://starlens.hu/
2026-03-28 16:20:21 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted 692 characters from main URL
2026-03-28 16:20:21 | INFO | src.stages.stage_1_metadata_alt | Searching for contact pages using OpenSerp
2026-03-28 16:20:21 | 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 16:20:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/adatvedelem
2026-03-28 16:20:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/szemeszeti-vizsgalatok-dija
2026-03-28 16:20:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/megkozelites
2026-03-28 16:20:21 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/sutiszabalyzat
2026-03-28 16:20:22 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/szemeszeti-vizsgalatok
2026-03-28 16:20:24 | INFO | src.stages.stage_2_discovery_async | Crawl finished: 21 URLs in 3.4s (success=6, errors=2)
2026-03-28 16:20:26 | INFO | src.stages.stage_2_discovery_async | Crawl produced 0 URLs from BERT (threshold and above), fetching all
2026-03-28 16:20:26 | ERROR | src.stages.stage_2_discovery_async | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).
2026-03-28 16:20:26 | INFO | src.stages.stage_2_discovery_async | Attempting fallback: original URL with trafilatura+markdown
2026-03-28 16:20:41 | INFO | src.stages.stage_1_metadata_alt | Successfully connected to OpenSerp at http://openserp:7000/mega/search
2026-03-28 16:20:41 | INFO | src.stages.stage_1_metadata_alt | OpenSerp returned 2 results
2026-03-28 16:20:41 | INFO | src.stages.stage_1_metadata_alt | Result 1: Starlens magán szemészeti rendelő Nagykőrös - https://starlens.hu/
2026-03-28 16:20:41 | INFO | src.stages.stage_1_metadata_alt | Result 2: Adatvédelem - Starlens magán szemészeti rendelő Nagykőrös - https://starlens.hu/adatvedelem
2026-03-28 16:20:41 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 1/3: https://starlens.hu/
2026-03-28 16:20:41 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 2439 characters from contact page 1
2026-03-28 16:20:41 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 2/3: https://starlens.hu/adatvedelem
2026-03-28 16:20:42 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 17195 characters from contact page 2
2026-03-28 16:20:42 | INFO | src.stages.stage_1_metadata_alt | Calling OpenRouter for metadata extraction (model=openai/gpt-5-mini)
2026-03-28 16:20:55 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted metadata for: Starlens magán szemészeti rendelő Nagykőrös
2026-03-28 16:20:55 | INFO | src.stages.stage_1_metadata_alt | Alternative metadata extraction stage completed
2026-03-28 16:20:55 | INFO | src.stages.stage_4_reviews | Starting reviews scraping stage
2026-03-28 16:20:55 | INFO | src.stages.stage_4_reviews | Found metadata directly: company_name=Starlens magán szemészeti rendelő Nagykőrös, varos=Nagykőrös
2026-03-28 16:20:55 | INFO | src.stages.stage_4_reviews | input_path: /tmp/tmpd6vro_26
2026-03-28 16:20:55 | INFO | src.stages.stage_4_reviews | output_path: /tmp/tmpb8vqhnc8
2026-03-28 16:20:55 | INFO | src.stages.stage_4_reviews | Running google-maps-scraper (attempt 1/3)
2026-03-28 16:23:34 | INFO | prefect.pipeline.parallel | Starting parallel pipeline execution a3f2ab8c-9f28-43f1-91a8-62e9c6af1fa6 for URL: https://starlens.hu/
2026-03-28 16:23:34 | INFO | src.stages.stage_1_metadata_alt | Starting alternative metadata extraction stage
2026-03-28 16:23:34 | INFO | src.stages.stage_1_metadata_alt | Querying metadata for: https://starlens.hu/
2026-03-28 16:23:34 | INFO | src.stages.stage_2_discovery_async | Starting discovery-fetch-validation (async) for URL: https://starlens.hu/
2026-03-28 16:23:34 | INFO | src.stages.stage_2_discovery_async | Async discovery config: fetch=curl, output=html, prediction=http://docker-host:8000/predict
2026-03-28 16:23:34 | INFO | src.stages.stage_1_metadata_alt | Downloading main URL: https://starlens.hu/
2026-03-28 16:23:34 | INFO | src.stages.stage_2_discovery_async | Async crawl starting: https://starlens.hu/ (max_depth=2, max_concurrent=10)
2026-03-28 16:23:34 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 0): https://starlens.hu/
2026-03-28 16:23:35 | INFO | src.stages.stage_1_metadata_alt | Successfully extracted 692 characters from main URL
2026-03-28 16:23:35 | INFO | src.stages.stage_1_metadata_alt | Searching for contact pages using OpenSerp
2026-03-28 16:23:35 | 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 16:23:35 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/megkozelites
2026-03-28 16:23:35 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/szemeszeti-vizsgalatok
2026-03-28 16:23:35 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/adatvedelem
2026-03-28 16:23:35 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/sutiszabalyzat
2026-03-28 16:23:36 | INFO | src.stages.stage_2_discovery_async | Crawled (depth 1): https://starlens.hu/szemeszeti-vizsgalatok-dija
2026-03-28 16:23:37 | INFO | src.stages.stage_2_discovery_async | Crawl finished: 21 URLs in 3.2s (success=6, errors=2)
2026-03-28 16:23:40 | INFO | src.stages.stage_2_discovery_async | Crawl produced 0 URLs from BERT (threshold and above), fetching all
2026-03-28 16:23:40 | ERROR | src.stages.stage_2_discovery_async | Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).
2026-03-28 16:23:40 | INFO | src.stages.stage_2_discovery_async | Attempting fallback: original URL with trafilatura+markdown
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Successfully connected to OpenSerp at http://openserp:7000/mega/search
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | OpenSerp returned 2 results
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Result 1: Starlens magán szemészeti rendelő Nagykőrös - https://starlens.hu/
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Result 2: Adatvédelem - Starlens magán szemészeti rendelő Nagykőrös - https://starlens.hu/adatvedelem
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 1/3: https://starlens.hu/
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 2439 characters from contact page 1
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Trying to download contact page 2/3: https://starlens.hu/adatvedelem
2026-03-28 16:23:57 | INFO | src.stages.stage_4_reviews | google-maps-scraper completed successfully on attempt 1
2026-03-28 16:23:57 | INFO | src.stages.stage_4_reviews | Input fájl mentve: data/review/20260328_162357_starlens_magán_szemészeti_rendelő_nagykőrös_url_input.txt
2026-03-28 16:23:57 | INFO | src.stages.stage_4_reviews | Output fájl mentve: data/review/20260328_162357_starlens_magán_szemészeti_rendelő_nagykőrös_url_output.json
2026-03-28 16:23:57 | INFO | src.stages.stage_4_reviews | Reviews scraping completed. Found 0 reviews
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Successfully downloaded and converted 17195 characters from contact page 2
2026-03-28 16:23:57 | INFO | src.stages.stage_1_metadata_alt | Calling OpenRouter for metadata extraction (model=openai/gpt-5-mini)
2026-03-28 16:23:58 | INFO | prefect.pipeline.parallel | Branch 1 (metadata_alt -> reviews) completed successfully
2026-03-28 16:23:58 | ERROR | prefect.pipeline.parallel | Branch 2 failed: Async discovery: no BERT candidate URL produced valid content. Tried 0 URL(s).