Files
DomGod/app/main.py
Malin 7acff12242 feat: persistent DuckDB index, new filters, pagination fix, enrich UX
- Build /data/domains.duckdb on first run (tld+parts columns + ART index)
  → TLD filter goes from ~60s full scan to <100ms index lookup
  → System still works (slower) while index builds in background
- New /api/domains params: alpha_only, no_sld, keyword
  → alpha_only: domains with only letters (no hyphens/numbers)
  → no_sld: parts=2, excludes com.es / net.es patterns
  → keyword: LIKE '%term%' niche search
- /api/domains and /api/enriched now return total count for pagination
- Pagination: shows total matches, page X of Y, Next disabled at last page
- Enrich button: toast notifications instead of alert(), error handling
- Select all on page button, clear selection button
- Stats/TLD breakdown cached after first load (no repeat full scan)
- Header shows index build status (building → ready)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-13 17:00:08 +02:00

207 lines
6.6 KiB
Python

import os
import asyncio
import logging
from pathlib import Path
from contextlib import asynccontextmanager
import httpx
import aiosqlite
from fastapi import FastAPI, Query
from fastapi.responses import StreamingResponse, JSONResponse
from fastapi.staticfiles import StaticFiles
from dotenv import load_dotenv
load_dotenv()
from app.db import (
DATA_DIR, PARQUET_PATH, SQLITE_PATH,
init_db, get_stats, get_domains, get_enriched,
queue_domains, get_queue_status, build_duckdb_index, index_status,
)
from app.enricher import start_worker, pause_worker, resume_worker, is_running
from app.scorer import run_scoring
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
logger = logging.getLogger(__name__)
PARQUET_URL = os.getenv("PARQUET_URL", "")
async def download_parquet():
if PARQUET_PATH.exists():
logger.info("Using cached parquet at %s", PARQUET_PATH)
return
DATA_DIR.mkdir(parents=True, exist_ok=True)
tmp_path = PARQUET_PATH.with_suffix(".tmp")
downloaded = tmp_path.stat().st_size if tmp_path.exists() else 0
headers = {"Range": f"bytes={downloaded}-"} if downloaded > 0 else {}
logger.info("Downloading parquet from %s (offset=%d)...", PARQUET_URL, downloaded)
async with httpx.AsyncClient(follow_redirects=True, timeout=None) as client:
async with client.stream("GET", PARQUET_URL, headers=headers) as resp:
if resp.status_code == 416:
tmp_path.rename(PARQUET_PATH)
return
resp.raise_for_status()
total = int(resp.headers.get("content-length", 0)) + downloaded
mode = "ab" if downloaded > 0 else "wb"
with open(tmp_path, mode) as f:
received = downloaded
async for chunk in resp.aiter_bytes(chunk_size=1024 * 1024):
f.write(chunk)
received += len(chunk)
if total:
logger.info("Download: %.1f%% (%d/%d)", received / total * 100, received, total)
tmp_path.rename(PARQUET_PATH)
logger.info("Parquet download complete")
@asynccontextmanager
async def lifespan(app: FastAPI):
await download_parquet()
await init_db()
# Build DuckDB index in background — queries still work (slower) while building
asyncio.create_task(build_duckdb_index())
start_worker()
logger.info("DomGod ready on port 6677")
yield
app = FastAPI(title="DomGod", lifespan=lifespan)
# ── API ──────────────────────────────────────────────────────────────────────
@app.get("/api/stats")
async def stats():
return await get_stats()
@app.get("/api/index/status")
async def get_index_status():
return index_status()
@app.get("/api/domains")
async def domains(
tld: str = Query(None),
page: int = Query(1, ge=1),
limit: int = Query(100, ge=1, le=500),
live_only: bool = Query(False),
alpha_only: bool = Query(False),
no_sld: bool = Query(False),
keyword: str = Query(None),
):
total, rows = await get_domains(
tld=tld, page=page, limit=limit,
alpha_only=alpha_only, no_sld=no_sld,
keyword=keyword, live_only=live_only,
)
return {"page": page, "limit": limit, "total": total, "results": rows}
@app.post("/api/enrich/batch")
async def enrich_batch(body: dict):
domains_list = body.get("domains", [])
if not domains_list:
return JSONResponse({"error": "no domains provided"}, status_code=400)
await queue_domains(domains_list)
resume_worker()
return {"queued": len(domains_list)}
@app.get("/api/enrich/status")
async def enrich_status():
status = await get_queue_status()
status["worker_running"] = is_running()
return status
@app.post("/api/enrich/retry")
async def enrich_retry():
async with aiosqlite.connect(SQLITE_PATH) as db:
await db.execute("UPDATE job_queue SET status='pending', error=NULL WHERE status='failed'")
await db.commit()
resume_worker()
return {"status": "retrying"}
@app.post("/api/enrich/pause")
async def enrich_pause():
pause_worker()
return {"status": "paused"}
@app.post("/api/enrich/resume")
async def enrich_resume():
resume_worker()
return {"status": "resumed"}
@app.get("/api/enriched")
async def enriched(
min_score: int = Query(0, ge=0, le=100),
cms: str = Query(None),
country: str = Query(None),
page: int = Query(1, ge=1),
limit: int = Query(100, ge=1, le=1000),
):
total, rows = await get_enriched(min_score=min_score, cms=cms, country=country, page=page, limit=limit)
return {"page": page, "limit": limit, "total": total, "results": rows}
@app.get("/api/export")
async def export_csv(
min_score: int = Query(0),
cms: str = Query(None),
country: str = Query(None),
tier: str = Query(None),
):
if tier == "hot":
min_score = 80
elif tier == "warm":
min_score = 50
max_score = 79 if tier == "warm" else 100
async def generate():
yield "domain,score,cms,ssl_expiry_days,ip_country,is_live,status_code,has_mx,server,page_title,enriched_at\n"
p = 1
while True:
_, rows = await get_enriched(min_score=min_score, cms=cms, country=country, page=p, limit=500)
if not rows:
break
for r in rows:
if r.get("score", 0) > max_score:
continue
line = ",".join(
f'"{str(r.get(col) or "").replace(chr(34), chr(39))}"'
for col in ["domain", "score", "cms", "ssl_expiry_days", "ip_country",
"is_live", "status_code", "has_mx", "server", "page_title", "enriched_at"]
)
yield line + "\n"
p += 1
fname = f"domgod_{tier or 'export'}_score{min_score}.csv"
return StreamingResponse(
generate(), media_type="text/csv",
headers={"Content-Disposition": f'attachment; filename="{fname}"'},
)
@app.post("/api/score/run")
async def score_run():
return await run_scoring()
# ── Static UI ────────────────────────────────────────────────────────────────
static_dir = Path(__file__).parent / "static"
app.mount("/", StaticFiles(directory=str(static_dir), html=True), name="static")
if __name__ == "__main__":
import uvicorn
uvicorn.run("app.main:app", host="0.0.0.0", port=6677, log_level="info")