Claude VM
a6c03a091e
Moved from gov-agreg/src/pages/achizitii/* to root (drop prefix). - 22 pages migrated, 127 files total - All internal links: /achizitii/X → /X (176 occurrences fixed) - AchizitiiLayout subnav rewritten: /X paths, top-right link to vreaudigital.ro hub - BaseLayout new (vreau.digital branding, OG tags, site URL) - astro.config.mjs: site https://vreau.digital, server output (was static) - docker-compose: port 5096 (vreaudigital is 5095), container vreau-digital - deploy.sh: paths /opt/vreau-digital, log /var/log/vreau-digital-deploy.log Backend shared with gov-agreg: - PostgreSQL satra (same schemas: seap, firms, anaf, anre, ...) - Photon, Martin tiles - Infisical /vreaudigital path (DATABASE_URL etc. shared) build: PASS (npx astro check 0 errors, npm run build 5s vite + 10s server)
85 lines
2.7 KiB
Bash
Executable File
85 lines
2.7 KiB
Bash
Executable File
#!/bin/bash
|
|
# ANAF datornici scraper — runs scrape-anaf-datornici.ts in node:22-alpine.
|
|
# Mirrors enrich-anaf.sh / scrape-regas.sh pattern: Infisical Machine Identity
|
|
# → env-file → docker run --env-file (NEVER -e $VAR), file deleted post-launch.
|
|
#
|
|
# Default source: data.gov.ro Q1-2016 snapshot (only public bulk source available;
|
|
# anaf.ro/restante/ live is CAPTCHA-blocked — see ANAF-DATORNICI-RECIPES.md).
|
|
#
|
|
# Idempotent (uses ON CONFLICT (cui, publication_date) DO UPDATE). Safe to run
|
|
# from cron, but in practice this is a one-shot until live scraping unlocks.
|
|
|
|
set -euo pipefail
|
|
|
|
SOURCE="${SOURCE:-datagov2016}"
|
|
DRY_RUN="${DRY_RUN:-0}"
|
|
LOG=/var/log/vreaudigital-anaf-datornici.log
|
|
|
|
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG"; }
|
|
|
|
log "=== ANAF datornici scrape started (source=$SOURCE dry-run=$DRY_RUN) ==="
|
|
|
|
if docker ps --filter name=vreaudigital-anaf-datornici --format '{{.Names}}' \
|
|
| grep -q '^vreaudigital-anaf-datornici$'; then
|
|
log "WARN: vreaudigital-anaf-datornici already running, skipping this tick"
|
|
exit 0
|
|
fi
|
|
docker rm -f vreaudigital-anaf-datornici 2>/dev/null || true
|
|
|
|
# ── Fetch DATABASE_URL via Infisical Machine Identity ──
|
|
source /opt/vreaudigital/.infisical-mi
|
|
TOKEN=$(infisical login --method=universal-auth \
|
|
--domain="$INFISICAL_API_URL" \
|
|
--client-id="$INFISICAL_CLIENT_ID" \
|
|
--client-secret="$INFISICAL_CLIENT_SECRET" \
|
|
--silent --plain)
|
|
|
|
umask 077
|
|
ENVF=$(mktemp /tmp/.vreaudigital-env.XXXXXX)
|
|
DBURL=$(infisical secrets get DATABASE_URL \
|
|
--domain="$INFISICAL_API_URL" \
|
|
--projectId="$INFISICAL_PROJECT_ID" \
|
|
--env="$INFISICAL_ENV" --path="$INFISICAL_PATH" \
|
|
--token="$TOKEN" --plain --silent)
|
|
echo "DATABASE_URL=$DBURL" > "$ENVF"
|
|
unset DBURL TOKEN
|
|
|
|
# ── Launch detached docker container ──
|
|
cd /opt/vreaudigital/services/seap-scraper
|
|
|
|
if [ ! -d node_modules/tsx ]; then
|
|
log "Installing seap-scraper deps..."
|
|
docker run --rm -v "$(pwd):/work" -w /work --user "$(id -u):$(id -g)" \
|
|
node:22-alpine npm install --omit=optional 2>&1 | tee -a "$LOG" >/dev/null
|
|
fi
|
|
|
|
DRY_FLAG=""
|
|
if [ "$DRY_RUN" = "1" ]; then
|
|
DRY_FLAG="--dry-run"
|
|
fi
|
|
|
|
CID=$(docker run -d \
|
|
--name vreaudigital-anaf-datornici \
|
|
--network host \
|
|
--env-file "$ENVF" \
|
|
-v "$(pwd):/work" \
|
|
-w /work \
|
|
--user "$(id -u):$(id -g)" \
|
|
--restart no \
|
|
node:22-alpine \
|
|
npx tsx src/scrape-anaf-datornici.ts \
|
|
--source="$SOURCE" \
|
|
$DRY_FLAG)
|
|
log "container started: $CID"
|
|
|
|
sleep 3
|
|
rm -f "$ENVF"
|
|
log "envfile cleaned"
|
|
|
|
docker wait vreaudigital-anaf-datornici >/dev/null
|
|
EXIT_CODE=$(docker inspect -f '{{.State.ExitCode}}' vreaudigital-anaf-datornici 2>/dev/null || echo "?")
|
|
docker logs vreaudigital-anaf-datornici 2>&1 | tail -15 | tee -a "$LOG"
|
|
log "=== ANAF datornici scrape done (exit=$EXIT_CODE) ==="
|
|
|
|
exit "$EXIT_CODE"
|