初始化

2026-07-18 16:13:52 +08:00
parent c0070f0a5c
commit fe8b417ab6
75 changed files with 12898 additions and 1 deletions
@@ -0,0 +1,68 @@
+#!/bin/bash
+# =============================================
+# 国内服务器：8G headful + HTTP 代理抓取
+# =============================================
+# 适用场景：
+#   - 所有新闻源直接使用 headful Playwright 浏览器抓取
+#   - HTTP 代理 (127.0.0.1:3128) → Privoxy → SOCKS5(ss-local) 访问海外
+#   - 比海外 RSS 方式抓取更可靠，解决反爬问题
+#
+# 前置条件：
+#   sudo apt install xvfb
+#   Xvfb :99 -screen 0 1280x1024x24 &     # 首次启动
+#   HTTP 代理 127.0.0.1:3128 已运行（privoxy）
+#
+# 用法：
+#   bash scripts/domestic_crawl_8g.sh              # 抓取全部源
+#   bash scripts/domestic_crawl_8g.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 8G headful + HTTP 代理抓取 ══════"
+LOG "Profile: 8g_headful"
+LOG "内存上限: 7500 MB"
+LOG "浏览器模式: headful (Xvfb :99)"
+LOG "HTTP 代理: 127.0.0.1:3128 (Privoxy → SOCKS5)"
+
+# ── 加载 .env ──
+export $(grep -v '^#' .env | grep -v '^$' | xargs 2>/dev/null || true)
+
+# ── 启动 Xvfb（如果尚未运行）──
+if ! pgrep -x "Xvfb" > /dev/null; then
+    LOG "启动 Xvfb 虚拟显示器 :99 ..."
+    Xvfb :99 -screen 0 1280x1024x24 -ac +extension RANDR &
+    sleep 1
+    LOG "Xvfb 已启动 (PID: $(pgrep -x Xvfb))"
+else
+    LOG "Xvfb 已在运行 (PID: $(pgrep -x Xvfb))"
+fi
+
+export DISPLAY=:99
+
+# ── 设置 Profile ──
+export EN_NEWS_PROFILE="8g_headful"
+
+# ── 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 "══════ 8G 抓取完成 ✅ ══════"