public void workWithTaskFileDB(string[] args)
{
try
{
string EXTRA_COLUMN1 = "未定义1";
string EXTRA_COLUMN2 = "未定义2";
string OUTPUT_FILENAME = "OUTPUT " + EXTRA_COLUMN1 + " " + EXTRA_COLUMN2 + ".xlsx";
string taskJson = "";
//这些参数在任务文件里面写上？
var taskk = Tools.Serializer.DeSerializeTSK(taskJson);
Console.WriteLine("读取正常任务文件...ok!");
for (int i = taskk.Current; i <= taskk.StarEnd; i = i + taskk.StarGap)
{
taskk.Current = i;
Console.WriteLine("当前进行到页码.............................." + i + "/" + taskk.StarEnd);
for (int j = 0; j < taskk.Processor.Count; j++)
{
Console.WriteLine("提取器位置..." + (j + 1).ToString() + "/" + taskk.Processor.Count);
//field1 每页的数量
var field0 = Tools.Scraper.Scrape(getor(taskk.CurrentURL), taskk.Processor[j]);
foreach (var c0Item in field0)
{
listResult.Add(new Models.Result()
{
c0 = c0Item
});
}
Console.WriteLine("提取到数据条数===" + field0.Count);
//含有子处理器，将field0交给另外个函数处理。处理完毕后保证field0是处理后的结果。
if (taskk.Processor[j].SubProcessor != null && taskk.Processor[j].SubProcessor.Count > 0)
{
Console.WriteLine("发现此项为含有扩展任务...爬取扩展任务~");
int subPsrColumn = taskk.Processor.Count;//扩展的SubPsr结果从列序号开始。
foreach (var c0Item in field0)
{
foreach (var subpro in taskk.Processor[j].SubProcessor)
{
var field0_sub0_s = Tools.Scraper.Scrape(getor(c0Item), subpro);
Models.Result c0Result = findByC0(c0Item);//先通过查找找到C0的Result的对象引用
foreach (var field0_sub0 in field0_sub0_s)
{
var cloneR = (c0Result.Clone() as Models.Result);
cloneR.c9 = field0_sub0;//稍后就c8
listResult.Add(cloneR);
}
}
}
List <List <string> > subResult = ProcessSub(taskk.Processor[j].SubProcessor, field0);
Console.WriteLine("扩展任务完成！");
}
#if outputView
Console.WriteLine("保存数据.............................OK!");
#endif
}
}
System.Diagnostics.Process.Start(OUTPUT_FILENAME);
}
catch (Exception err)
{
Console.WriteLine(err.ToString());
System.IO.File.WriteAllText("ERROR@" + DateTime.Now.ToString("yyyyMMdd HHmmss") + ".log", err.ToString());
}
Console.WriteLine("按任意键退出...");
//Console.ReadKey();
}
