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)
89 lines
3.1 KiB
Bash
Executable File
89 lines
3.1 KiB
Bash
Executable File
#!/bin/bash
|
||
# GNM — Garda Națională de Mediu.
|
||
# Scrapes the gnm.ro WordPress RSS feed (~36 pages × 10 items) for environmental
|
||
# enforcement press releases. Persists every release to gnm.comunicate, flags
|
||
# is_enforcement, and runs a regex pass to surface (firm, fine_lei) tuples into
|
||
# gnm.amenzi_extrase.
|
||
#
|
||
# Mirrors scrape-ancom.sh / scrape-anre.sh pattern: Infisical Machine Identity
|
||
# → env-file → docker run --env-file (NEVER -e $VAR), file deleted post-launch.
|
||
#
|
||
# Idempotent (UPSERT on guid; skip on raw_hash unchanged). Safe to run from cron.
|
||
#
|
||
# Env knobs:
|
||
# MAX_PAGES=0 (default: 0 = walk until empty, max 50)
|
||
# SINCE_DAYS=0 (default: 0 = no cutoff; >0 = stop at first item older than N days)
|
||
#
|
||
# Run:
|
||
# sudo MAX_PAGES=2 /opt/vreaudigital/services/seap-scraper/cron/scrape-gnm.sh # smoke (20 articles)
|
||
# sudo SINCE_DAYS=30 /opt/vreaudigital/services/seap-scraper/cron/scrape-gnm.sh # incremental
|
||
# sudo /opt/vreaudigital/services/seap-scraper/cron/scrape-gnm.sh # full (~360 articles)
|
||
set -euo pipefail
|
||
|
||
MAX_PAGES="${MAX_PAGES:-0}"
|
||
SINCE_DAYS="${SINCE_DAYS:-0}"
|
||
LOG=/var/log/vreaudigital-gnm.log
|
||
|
||
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG"; }
|
||
|
||
log "=== GNM scrape started (max_pages=$MAX_PAGES since_days=$SINCE_DAYS) ==="
|
||
|
||
if docker ps --filter name=vreaudigital-gnm --format '{{.Names}}' | grep -q '^vreaudigital-gnm$'; then
|
||
log "WARN: vreaudigital-gnm already running, skipping this tick"
|
||
exit 0
|
||
fi
|
||
docker rm -f vreaudigital-gnm 2>/dev/null || true
|
||
|
||
# ── Fetch DATABASE_URL via Infisical Machine Identity ──
|
||
source /opt/vreaudigital/.infisical-mi
|
||
TOKEN=$(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-gnm-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
|
||
|
||
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=""
|
||
[ "$MAX_PAGES" -gt 0 ] 2>/dev/null && EXTRA_ARGS="$EXTRA_ARGS --max-pages=$MAX_PAGES"
|
||
[ "$SINCE_DAYS" -gt 0 ] 2>/dev/null && EXTRA_ARGS="$EXTRA_ARGS --since-days=$SINCE_DAYS"
|
||
|
||
CID=$(docker run -d \
|
||
--name vreaudigital-gnm \
|
||
--network host \
|
||
--env-file "$ENVF" \
|
||
-v "$(pwd):/work" \
|
||
-w /work \
|
||
--user "$(id -u):$(id -g)" \
|
||
--restart no \
|
||
node:22-alpine \
|
||
npx tsx src/scrape-gnm.ts $EXTRA_ARGS)
|
||
log "container started: $CID"
|
||
|
||
sleep 3
|
||
rm -f "$ENVF"
|
||
log "envfile cleaned"
|
||
|
||
docker wait vreaudigital-gnm >/dev/null
|
||
EXIT_CODE=$(docker inspect -f '{{.State.ExitCode}}' vreaudigital-gnm 2>/dev/null || echo "?")
|
||
docker logs vreaudigital-gnm 2>&1 | tail -30 | tee -a "$LOG"
|
||
log "=== GNM scrape done (exit=$EXIT_CODE) ==="
|
||
|
||
exit "$EXIT_CODE"
|