public void TestGetRule() { ServerManager.StartServers(); var response = Crawler.Request("http://www.ruijihg.com/2018/05/20/ruiji-solr-net/"); if (response.StatusCode != System.Net.HttpStatusCode.OK) { return; } var content = response.Data.ToString(); var block = Feeder.GetExtractBlock("http://www.ruijihg.com/2018/05/20/ruiji-solr-net/").First(); var r = Extractor.Extract(new ExtractRequest { Blocks = new List <ExtractFeatureBlock> { block }, Content = content }); Assert.True(r[0].Content.ToString().Length > 0); Assert.True(r[0].Tiles.Count > 0); }
public List <ExtractResult> Extract(string url) { var cralwer = new RuiJi.Net.NodeVisitor.Crawler(); var response = cralwer.Request(url); var content = response.Data.ToString(); var results = new List <ExtractResult>(); var blocks = Feeder.GetExtractBlock(url); blocks.ForEach((m) => { var r = RuiJi.Net.NodeVisitor.Extracter.Extract(new ExtractRequest { Block = m, Content = content }); results.Add(r); }); return(results); }