chore: import gti-maquina-comercial history via subtree

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> git-subtree-dir: gti-maquina-comercial git-subtree-mainline: 93ca82979e git-subtree-split: b77484946f
2026-09-28 15:50:08 -03:00
parent 93ca82979e b77484946f
commit f5af038e19
110 changed files with 27501 additions and 0 deletions
@@ -0,0 +1,44 @@
+#!/bin/bash
+# Baixa a base completa de CNPJ da Receita Federal (extrato mais recente) a partir do
+# espelho publico da Casa dos Dados (mesma base oficial, servida via Cloudflare).
+# Uso: bash scripts/baixar-base-rfb.sh
+set -e
+
+BASE_URL="https://dados-abertos-rf-cnpj.casadosdados.com.br/arquivos/2026-06-14"
+DEST_DIR="prospeccao/cnpj/rfb-raw"
+mkdir -p "$DEST_DIR"
+
+FILES=(
+  Cnaes.zip Motivos.zip Municipios.zip Naturezas.zip Paises.zip Qualificacoes.zip Simples.zip
+  Empresas0.zip Empresas1.zip Empresas2.zip Empresas3.zip Empresas4.zip
+  Empresas5.zip Empresas6.zip Empresas7.zip Empresas8.zip Empresas9.zip
+  Estabelecimentos0.zip Estabelecimentos1.zip Estabelecimentos2.zip Estabelecimentos3.zip Estabelecimentos4.zip
+  Estabelecimentos5.zip Estabelecimentos6.zip Estabelecimentos7.zip Estabelecimentos8.zip Estabelecimentos9.zip
+  Socios0.zip Socios1.zip Socios2.zip Socios3.zip Socios4.zip
+  Socios5.zip Socios6.zip Socios7.zip Socios8.zip Socios9.zip
+)
+
+TOTAL=${#FILES[@]}
+COUNT=0
+
+for FILE in "${FILES[@]}"; do
+  COUNT=$((COUNT+1))
+  DEST="$DEST_DIR/$FILE"
+
+  if [ -f "$DEST" ]; then
+    EXPECTED=$(curl -sI --max-time 20 "$BASE_URL/$FILE" | grep -i content-length | tr -d '\r' | awk '{print $2}')
+    ACTUAL=$(stat -c%s "$DEST" 2>/dev/null || stat -f%z "$DEST" 2>/dev/null)
+    if [ -n "$EXPECTED" ] && [ "$EXPECTED" == "$ACTUAL" ]; then
+      echo "[$COUNT/$TOTAL] $FILE ja existe e esta completo ($ACTUAL bytes). Pulando."
+      continue
+    fi
+  fi
+
+  echo "[$COUNT/$TOTAL] baixando $FILE ..."
+  curl -sS --retry 3 --retry-delay 5 --max-time 1800 -o "$DEST" "$BASE_URL/$FILE"
+  SIZE=$(stat -c%s "$DEST" 2>/dev/null || stat -f%z "$DEST" 2>/dev/null)
+  echo "[$COUNT/$TOTAL] $FILE concluido ($SIZE bytes)"
+done
+
+echo "download completo."
+du -sh "$DEST_DIR"