72 lines
2.1 KiB
Python
72 lines
2.1 KiB
Python
|
"""
|
||
|
|
Phase 0 Extraction routes: Fast JSON Extraction MVP.
|
||
|
|
|
||
|
|
No database storage - just extract and return JSON candidates.
|
||
|
|
Goal: 10-30 seconds per URL.
|
||
|
|
"""
|
||
|
|
|
||
|
|
from fastapi import APIRouter, HTTPException
|
||
|
|
import time
|
||
|
|
|
||
|
|
from ont_platform.core.extractors.web_extractor import extract_web_content
|
||
|
|
from ont_platform.core.extraction.lightweight_extractor import LightweightExtractor
|
||
|
|
|
||
|
|
router = APIRouter(prefix="/api/v1", tags=["extraction"])
|
||
|
|
|
||
|
|
|
||
|
|
@router.post("/extract/url")
|
||
|
|
async def extract_url(url: str):
|
||
|
|
"""
|
||
|
|
Extract candidates from URL (Phase 0 MVP).
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
{
|
||
|
|
"url": "...",
|
||
|
|
"title": "...",
|
||
|
|
"entities": [...],
|
||
|
|
"relations": [...],
|
||
|
|
"extraction_time_sec": 0.5,
|
||
|
|
"warnings": [...]
|
||
|
|
}
|
||
|
|
"""
|
||
|
|
if not url:
|
||
|
|
raise HTTPException(status_code=400, detail="url is required")
|
||
|
|
|
||
|
|
start_time = time.time()
|
||
|
|
|
||
|
|
try:
|
||
|
|
# Step 1: Extract web content with Trafilatura
|
||
|
|
extracted = extract_web_content(url=url)
|
||
|
|
|
||
|
|
# Step 2: Extract JSON candidates with lightweight extractor
|
||
|
|
lightweight = LightweightExtractor(use_llm=False)
|
||
|
|
candidates = lightweight.extract(
|
||
|
|
text=extracted.text,
|
||
|
|
project_id="default", # Phase 0: no projects yet
|
||
|
|
document_id="temp",
|
||
|
|
)
|
||
|
|
|
||
|
|
extraction_time = time.time() - start_time
|
||
|
|
|
||
|
|
# Return just the JSON (entities/relations are already dicts)
|
||
|
|
return {
|
||
|
|
"url": url,
|
||
|
|
"title": extracted.title,
|
||
|
|
"author": extracted.author,
|
||
|
|
"published_date": extracted.publish_date,
|
||
|
|
"language": extracted.language,
|
||
|
|
"text_length": len(extracted.text),
|
||
|
|
"entities": candidates.entities,
|
||
|
|
"relations": candidates.relations,
|
||
|
|
"extraction_time_sec": round(extraction_time, 2),
|
||
|
|
"entity_count": len(candidates.entities),
|
||
|
|
"relation_count": len(candidates.relations),
|
||
|
|
"warnings": candidates.warnings,
|
||
|
|
}
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
raise HTTPException(status_code=500, detail=f"Extraction failed: {str(e)}")
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ["router"]
|