Enhance manual crawling functionality in GXGPMonitorApp to skip database saving for both announcements and filtered results. Update logging to reflect manual crawl mode actions, ensuring clarity in the process. Adjusted comments for better understanding of the manual crawling logic.
This commit is contained in:
Executable
+90
@@ -0,0 +1,90 @@
|
||||
#!/bin/bash
|
||||
# 定时爬取脚本启动器
|
||||
# 用于启动广西政府采购网公告定时爬取任务
|
||||
# 自动激活项目虚拟环境并运行Python脚本
|
||||
|
||||
# 设置脚本遇到错误时退出
|
||||
set -e
|
||||
|
||||
# 获取脚本所在目录的绝对路径
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
PROJECT_ROOT="$SCRIPT_DIR"
|
||||
|
||||
echo "========================================"
|
||||
echo "🕒 广西政府采购网公告定时爬取任务"
|
||||
echo "📂 项目目录: $PROJECT_ROOT"
|
||||
echo "⏰ 开始时间: $(date '+%Y-%m-%d %H:%M:%S')"
|
||||
echo "========================================"
|
||||
|
||||
# 检查虚拟环境
|
||||
VENV_PATH="$PROJECT_ROOT/venv"
|
||||
if [ ! -d "$VENV_PATH" ]; then
|
||||
echo "❌ 错误: 找不到虚拟环境目录"
|
||||
echo " 预期路径: $VENV_PATH"
|
||||
echo " 请确保虚拟环境已正确创建"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 检查虚拟环境激活脚本
|
||||
VENV_ACTIVATE="$VENV_PATH/bin/activate"
|
||||
if [ ! -f "$VENV_ACTIVATE" ]; then
|
||||
echo "❌ 错误: 找不到虚拟环境激活脚本"
|
||||
echo " 预期路径: $VENV_ACTIVATE"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ 找到虚拟环境: $VENV_PATH"
|
||||
|
||||
# 激活虚拟环境
|
||||
echo "🔧 激活虚拟环境..."
|
||||
echo " 激活脚本: $VENV_ACTIVATE"
|
||||
source "$VENV_ACTIVATE"
|
||||
|
||||
# 检查Python环境(在虚拟环境中)
|
||||
if ! command -v python &> /dev/null; then
|
||||
echo "❌ 错误: 虚拟环境中未找到Python命令"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 检查Python版本(在虚拟环境中)
|
||||
PYTHON_VERSION=$(python --version 2>&1 | cut -d' ' -f2 | cut -d. -f1-2)
|
||||
echo "🐍 Python版本 (虚拟环境): $PYTHON_VERSION"
|
||||
|
||||
# 检查项目目录
|
||||
if [ ! -d "$PROJECT_ROOT/gx_gp_monitor" ]; then
|
||||
echo "❌ 错误: 找不到gx_gp_monitor目录"
|
||||
echo " 预期路径: $PROJECT_ROOT/gx_gp_monitor"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 检查cron_crawl.py文件
|
||||
CRON_SCRIPT="$PROJECT_ROOT/gx_gp_monitor/cron_crawl.py"
|
||||
if [ ! -f "$CRON_SCRIPT" ]; then
|
||||
echo "❌ 错误: 找不到cron_crawl.py文件"
|
||||
echo " 预期路径: $CRON_SCRIPT"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ 环境检查通过"
|
||||
echo "🚀 启动定时爬取脚本..."
|
||||
|
||||
# 切换到项目根目录
|
||||
cd "$PROJECT_ROOT"
|
||||
|
||||
# 执行定时爬取脚本
|
||||
python "$CRON_SCRIPT"
|
||||
EXIT_CODE=$?
|
||||
|
||||
echo "========================================"
|
||||
echo "🏁 任务完成"
|
||||
echo "📅 结束时间: $(date '+%Y-%m-%d %H:%M:%S')"
|
||||
echo "🔚 退出代码: $EXIT_CODE"
|
||||
|
||||
if [ $EXIT_CODE -eq 0 ]; then
|
||||
echo "✅ 任务执行成功"
|
||||
else
|
||||
echo "❌ 任务执行失败"
|
||||
fi
|
||||
|
||||
echo "========================================"
|
||||
exit $EXIT_CODE
|
||||
Reference in New Issue
Block a user