Files
vreau-digital/services/seap-scraper/cron/scrape-anre.sh
T
Claude VM a6c03a091e initial: split from gov-agreg — vreau.digital standalone platform
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)
2026-05-13 00:10:32 +03:00

90 lines
3.0 KiB
Bash
Executable File

#!/bin/bash
# ANRE — Autoritatea Națională de Reglementare în domeniul Energiei.
# Scrapes 4 public registries from portal.anre.ro/PublicLists:
# electricitate (~5K), gaze (~350), atestat (~10K), electricieni (~100K).
#
# Mirrors scrape-regas.sh / scrape-bugetar.sh pattern: Infisical Machine
# Identity → env-file → docker run --env-file (NEVER -e $VAR), file deleted
# post-launch.
#
# Idempotent (UPSERT on sha1 PK / UNIQUE(nr_autorizare,nume_prenume)).
# Safe to run from cron.
#
# Env knobs:
# SOURCE=all|electricitate|gaze|atestat|electricieni (default: all)
# LIMIT=0 (default: 0 = full)
#
# Run:
# sudo SOURCE=electricitate LIMIT=100 /opt/vreaudigital/services/seap-scraper/cron/scrape-anre.sh
# sudo /opt/vreaudigital/services/seap-scraper/cron/scrape-anre.sh # full all sources
set -euo pipefail
SOURCE="${SOURCE:-all}"
LIMIT="${LIMIT:-0}"
LOG=/var/log/vreaudigital-anre.log
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG"; }
log "=== ANRE scrape started (source=$SOURCE limit=$LIMIT) ==="
if docker ps --filter name=vreaudigital-anre --format '{{.Names}}' | grep -q '^vreaudigital-anre$'; then
log "WARN: vreaudigital-anre already running, skipping this tick"
exit 0
fi
docker rm -f vreaudigital-anre 2>/dev/null || true
# ── Fetch DATABASE_URL via Infisical Machine Identity ──
source /opt/vreaudigital/.infisical-mi
TOKEN=$(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-anre-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"
# ANRE portal uses an intermediate CA cert chain that node's bundle doesn't trust.
# Cert is valid (verified OOB via Microsoft-IIS handshake), bypass for this scraper.
echo "NODE_TLS_REJECT_UNAUTHORIZED=0" >> "$ENVF"
unset DBURL TOKEN
cd /opt/vreaudigital/services/seap-scraper
if [ ! -d node_modules/tsx ]; then
log "Installing seap-scraper deps..."
docker run --rm -v "$(pwd):/work" -w /work --user "$(id -u):$(id -g)" \
node:22-alpine npm install --omit=optional 2>&1 | tee -a "$LOG" >/dev/null
fi
EXTRA_ARGS="--source=$SOURCE"
[ "$LIMIT" -gt 0 ] 2>/dev/null && EXTRA_ARGS="$EXTRA_ARGS --limit=$LIMIT"
CID=$(docker run -d \
--name vreaudigital-anre \
--network host \
--env-file "$ENVF" \
-v "$(pwd):/work" \
-w /work \
--user "$(id -u):$(id -g)" \
--restart no \
node:22-alpine \
npx tsx src/scrape-anre.ts $EXTRA_ARGS)
log "container started: $CID"
sleep 3
rm -f "$ENVF"
log "envfile cleaned"
docker wait vreaudigital-anre >/dev/null
EXIT_CODE=$(docker inspect -f '{{.State.ExitCode}}' vreaudigital-anre 2>/dev/null || echo "?")
docker logs vreaudigital-anre 2>&1 | tail -25 | tee -a "$LOG"
log "=== ANRE scrape done (exit=$EXIT_CODE) ==="
exit "$EXIT_CODE"