public void TestUrlExtract()
{
var result = Cooperater.GetResult("http://www.cannews.com.cn/2018/0606/177699.shtml");
Assert.True(true);
}
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);
}