#!/bin/bash
# =============================================
# 国内服务器：2G headless stealth 抓取
# =============================================
# 适用场景：
#   - 日常轻量补充抓取
#   - RSS 优先 + headless stealth Web 回退
#   - 可选 SOCKS5 代理（修改 profiles/2g_headless.yaml 中 proxy.enabled）
#
# 用法：
#   bash scripts/domestic_crawl_2g.sh              # 抓取全部源
#   bash scripts/domestic_crawl_2g.sh reuters      # 只抓取指定源
# =============================================
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_DIR="$(dirname "$SCRIPT_DIR")"
cd "$PROJECT_DIR"

LOG() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*"; }

LOG "══════ 国内 2G headless stealth 抓取 ══════"
LOG "Profile: 2g_headless"
LOG "内存上限: 1800 MB"
LOG "浏览器模式: stealth headless"

# ── 加载 .env ──
export $(grep -v '^#' .env | grep -v '^$' | xargs 2>/dev/null || true)

# ── 设置 Profile ──
export EN_NEWS_PROFILE="2g_headless"

# ── 执行抓取 ──
SOURCE_ARG=""
if [ $# -ge 1 ]; then
    SOURCE_ARG="--source $1"
    LOG "目标源: $1"
else
    LOG "目标源: 全部启用源"
fi

PYTHONPATH=. .venv/bin/python3 -c "
from crawler.orchestrator import run_crawl_sync
import sys
source_filter = sys.argv[1] if len(sys.argv) > 1 else None
stats = run_crawl_sync(source_filter=source_filter)
print(f'抓取完成: {stats.sources_crawled} 源, {stats.total_articles} 篇')
" "$1"

LOG "══════ 2G 抓取完成 ✅ ══════"