batch-check.sh

#!/usr/bin/env bash
# batch-check.sh — 批量质检代理 / IP 列表，输出 CSV（ipyou.net）
#
# 站点不提供批量接口,本脚本就是「循环调用单个接口」的现成实现:
# 自动去重、限速(默认每个 1 秒)、失败重试,并把结果拼成 CSV。
#
# 用法:
#   ./batch-check.sh ips.txt              输出 CSV 到 stdout
#   ./batch-check.sh ips.txt > out.csv    存文件(Excel 可直接打开)
#   cat ips.txt | ./batch-check.sh        从管道读
#   ./batch-check.sh -t ips.txt           人眼友好的表格(非 CSV)
#   IPYOU_SLEEP=2 ./batch-check.sh ips.txt   放慢一点
#
# 输入格式: 每行一个 IP,支持 host:port / user:pass@host:port、# 注释、空行
# 依赖: curl + jq
set -euo pipefail

BASE="${IPYOU_BASE:-https://ipyou.net}"
TIMEOUT="${IPYOU_TIMEOUT:-15}"
SLEEP="${IPYOU_SLEEP:-1}"      # 每个 IP 之间的间隔,别把公共服务打爆
table=0

usage() { sed -n '2,17p' "$0" | sed 's/^# \{0,1\}//'; exit 0; }

while [ $# -gt 0 ]; do
  case "$1" in
    -t|--table) table=1; shift ;;
    -h|--help)  usage ;;
    *) break ;;
  esac
done

command -v jq >/dev/null 2>&1 || { echo "需要 jq: https://jqlang.github.io/jq/" >&2; exit 3; }

src="${1:--}"
ips=$(sed 's/#.*//' "$src" \
  | grep -oE '([0-9]{1,3}\.){3}[0-9]{1,3}' \
  | awk '!seen[$0]++')

[ -n "$ips" ] || { echo "没有找到可检测的 IP" >&2; exit 1; }
total=$(printf '%s\n' "$ips" | wc -l | tr -d ' ')
echo "共 $total 个 IP,逐个查询中(间隔 ${SLEEP}s)…" >&2

if [ "$table" = "0" ]; then
  echo "ip,country,city,isp,asn,type,score,level,blocklisted,tiktok,ecom,social,ai"
fi

# 取单个 IP 的 JSON;429 时退避重试
fetch() {
  local ip="$1" try out code
  for try in 1 2 3; do
    out=$(curl -s -w '\n%{http_code}' --max-time "$TIMEOUT" \
            -H "Accept: application/json" "$BASE/$ip" || true)
    code=$(printf '%s' "$out" | tail -1)
    if [ "$code" = "200" ]; then
      printf '%s' "$out" | sed '$d'
      return 0
    fi
    [ "$code" = "429" ] || return 1
    sleep $((try * 5))      # 触发限流:退避后重试
  done
  return 1
}

n=0
while IFS= read -r ip; do
  [ -z "$ip" ] && continue
  n=$((n + 1))
  [ "$n" -gt 1 ] && sleep "$SLEEP"

  if ! json=$(fetch "$ip"); then
    echo "  ! $ip 查询失败,跳过" >&2
    continue
  fi

  if [ "$table" = "1" ]; then
    echo "$json" | jq -r '
      [ .ip,
        (.usage_inferred.label // "-"),
        ((.ip_score.score // "") | tostring),
        (.ip_score.level // "-"),
        (if .blocklisted then "BLOCKED" else "-" end),
        (.geo_consensus.country_name // .geo.country // "-"),
        (.geo.isp // .geo_consensus.isp // "-") ] | @tsv' \
      | awk -F'\t' '{printf "%-16s %-10s %4s %-8s %-8s %-22s %s\n", $1,$2,$3,$4,$5,$6,$7}'
  else
    echo "$json" | jq -r '
      (.scenarios // []) as $s |
      [ .ip,
        (.geo_consensus.country_name // .geo.country // ""),
        (.geo_consensus.city // .geo.city // ""),
        (.geo.isp // .geo_consensus.isp // ""),
        (if .asn.number then "AS\(.asn.number)" else "" end),
        (.usage_inferred.label // ""),
        (.ip_score.score // ""),
        (.ip_score.level // ""),
        (.blocklisted // false),
        ($s | map(select(.name=="TikTok"))   | (.[0].stars // "")),
        ($s | map(select(.name=="跨境电商")) | (.[0].stars // "")),
        ($s | map(select(.name=="社媒运营")) | (.[0].stars // "")),
        ($s | map(select(.name=="AI 应用"))  | (.[0].stars // ""))
      ] | @csv'
  fi
done <<EOF
$ips
EOF