public object TestFeed(FeedModel feed, [FromUri] bool down, [FromUri] bool debug = false)
{
try
{
var compile = new UrlCompile();
var addrs = compile.GetResult(feed.Address);
var results = new List <ExtractResult>();
foreach (var addr in addrs)
{
feed.Address = addr.ToString();
var job = new FeedJob();
var snap = job.DoTask(feed, false);
if (string.IsNullOrEmpty(feed.RuiJiExpression))
{
results.Add(new ExtractResult());
continue;
}
var block = RuiJiBlockParser.ParserBlock(feed.RuiJiExpression);
var result = RuiJiExtractor.Extract(snap.Content, block);
if (!debug)
{
CrawlTaskFunc.ClearContent(result);
}
if (down)
{
var s = new FileStorage(Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "www", "download"));
var files = result.Content.ToString().Replace("\r\n", "\n").Split('\n');
foreach (var file in files)
{
if (!string.IsNullOrEmpty(file) && Uri.IsWellFormedUriString(file, UriKind.Absolute))
{
var res = Crawler.Request(file);
var c = new DownloadContentModel();
c.Url = file.Trim();
c.IsRaw = res.IsRaw;
c.Data = res.Data;
s.Insert(c);
}
}
}
results.Add(result);
}
return(results);
}
catch (Exception ex)
{
return(ex);
}
}
public object Run(object t, ParallelTask task)
{
var model = t as CrawlTaskModel;
var results = new List <ExtractResult>();
var reporter = task.Progress as IProgress <string>;
reporter.Report("正在读取Feed记录");
var feed = FeedLiteDb.GetFeed(model.FeedId);
reporter.Report("正在下载 Feed");
var compile = new CompileFeedAddress();
feed.Address = compile.Compile(feed.Address);
var job = new FeedJob();
var snap = job.DoTask(feed, false);
reporter.Report("Feed 下载完成");
var block = RuiJiExpression.ParserBlock(feed.RuiJiExpression);
var feedResult = RuiJiExtracter.Extract(snap.Content, block);
results.Add(feedResult);
reporter.Report("正在提取Feed地址");
var j = new FeedExtractJob();
var urls = j.ExtractAddress(snap);
reporter.Report("Feed地址提取完成");
foreach (var url in urls)
{
reporter.Report("正在提取地址 " + url);
var r = ContentQueue.Instance.Extract(url);
results.AddRange(r);
}
reporter.Report("计算完成");
if (!model.IncludeContent)
{
results.ForEach((m) =>
{
ClearContent(m);
});
}
return(results);
}
public object Run(object t, ParallelTask task)
{
var model = t as CrawlTaskModel;
var results = new List <object>();
var reporter = task.Progress as IProgress <string>;
reporter.Report("正在读取Feed记录");
var feed = FeedLiteDb.GetFeed(model.FeedId);
reporter.Report("正在下载 Feed");
var compile = new UrlCompile();
var addrs = compile.GetResult(feed.Address);
foreach (var addr in addrs)
{
feed.Address = addr.ToString();
var job = new FeedJob();
var snap = job.DoTask(feed, false);
reporter.Report("Feed 下载完成");
var block = RuiJiBlockParser.ParserBlock(feed.RuiJiExpression);
var feedResult = RuiJiExtractor.Extract(snap.Content, block);
results.Add(feedResult);
reporter.Report("正在提取Feed地址");
var j = new FeedExtractJob();
var urls = j.ExtractAddress(snap);
reporter.Report("Feed地址提取完成");
if (!string.IsNullOrEmpty(snap.RuiJiExpression))
{
foreach (var url in urls)
{
reporter.Report("正在提取地址 " + url);
var result = Cooperater.GetResult(url);
if (result != null)
{
var cm = new ContentModel();
cm.Id = model.FeedId;
cm.Url = url;
cm.Metas = result.Metas;
cm.CDate = DateTime.Now;
results.Add(cm);
}
}
}
reporter.Report("计算完成");
if (!model.IncludeContent)
{
results.ForEach((m) =>
{
ClearContent(m);
});
}
}
return(results);
}
