|
Chilkat • HOME • .NET Core C# • Android™ • AutoIt • C • C# • C++ • Chilkat2-Python • CkPython • Classic ASP • DataFlex • Delphi ActiveX • Delphi DLL • Go • Java • Lianja • Mono C# • Node.js • Objective-C • PHP ActiveX • PHP Extension • Perl • PowerBuilder • PowerShell • PureBasic • Ruby • SQL Server • Swift 2 • Swift 3,4,5... • Tcl • Unicode C • Unicode C++ • VB.NET • VBScript • Visual Basic 6.0 • Visual FoxPro • Xojo Plugin
(Delphi ActiveX) HTML Table to CSVDemonstrates a method for converting an HTML table to a CSV file. Note: This example requires Chilkat v9.5.0.77 or greater.
uses Winapi.Windows, Winapi.Messages, System.SysUtils, System.Variants, System.Classes, Vcl.Graphics, Vcl.Controls, Vcl.Forms, Vcl.Dialogs, Vcl.StdCtrls, Chilkat_TLB; ... procedure TForm1.Button1Click(Sender: TObject); var http: TChilkatHttp; bdHtml: TChilkatBinData; success: Integer; htx: THtmlToXml; sbXml: TChilkatStringBuilder; xml: TChilkatXml; numRemoved: Integer; i: Integer; count_i: Integer; table_role: WideString; table_data_scrollx: WideString; table_data_sortdirection: WideString; table_data_sorton: WideString; table_id: WideString; j: Integer; count_j: Integer; tr_role: WideString; k: Integer; count_k: Integer; tagPath: WideString; text: WideString; csv: TChilkatCsv; csvStr: WideString; begin // This example requires the Chilkat API to have been previously unlocked. // See Global Unlock Sample for sample code. // First download the HTML containing the table http := TChilkatHttp.Create(Self); bdHtml := TChilkatBinData.Create(Self); success := http.QuickGetBd('https://example-code.com/data/etf_table.html',bdHtml.ControlInterface); if (success <> 1) then begin Memo1.Lines.Add(http.LastErrorText); Exit; end; // Convert to XML. htx := THtmlToXml.Create(Self); htx.SetHtmlBd(bdHtml.ControlInterface); sbXml := TChilkatStringBuilder.Create(Self); htx.ToXmlSb(sbXml.ControlInterface); xml := TChilkatXml.Create(Self); xml.LoadSb(sbXml.ControlInterface,1); // Remove attributes and sub-trees we don't need. // (In other words, we're getting rid of clutter...) numRemoved := xml.PruneTag('thead'); numRemoved := xml.PruneAttribute('style'); numRemoved := xml.PruneAttribute('class'); // Scrub the element and attribute content. xml.Scrub('ContentTrimEnds,ContentTrimInside,AttrTrimEnds,AttrTrimInside'); // Let's see what we have... Memo1.Lines.Add(xml.GetXml()); // We have the following XML. // Copy this XML into the online tool at Generate Parsing Code from XML // as a starting point for accessing the data.. // <?xml version="1.0" encoding="utf-8"?> // <root> // <html> // <head> // <meta http-equiv="content-type" content="text/html; charset=UTF-8"/> // </head> // <body text="#000000" bgcolor="#FFFFFF"> // <div> // <div> // <table role="grid" data-scrollx="true" data-sortdirection="desc" data-sorton="-1"/> // </div> // </div> // <div> // <table id="topHoldingsTable" role="grid" data-scrollx="true" data-sortdirection="desc" data-sorton="-1"> // <tbody> // <tr role="row"> // <td> // <text>ITUB4</text> // </td> // <td> // <text>ITAU UNIBANCO HOLDING PREF SA</text> // </td> // <td> // <text>Financials</text> // </td> // <td> // <text>Brazil</text> // </td> // <td> // <text>10.94</text> // </td> // <td> // <text>998,954,813.73</text> // </td> // </tr> // <tr role="row"> // <td> // <text>BBDC4</text> // </td> // <td> // <text>BANCO BRADESCO PREF SA</text> // </td> // <td> // <text>Financials</text> // </td> // <td> // <text>Brazil</text> // </td> // <td> // <text>9.01</text> // </td> // <td> // <text>822,164,622.75</text> // </td> // </tr> // ... // ... // ... // </tbody> // </table> // </div> // </body> // </html> // </root> // // This is the code generated by the online tool: // i := 0; count_i := xml.NumChildrenHavingTag('html|body|div'); while i < count_i do begin xml.I := i; table_role := xml.ChilkatPath('html|body|div[i]|div|table|(role)'); table_data_scrollx := xml.ChilkatPath('html|body|div[i]|div|table|(data-scrollx)'); table_data_sortdirection := xml.ChilkatPath('html|body|div[i]|div|table|(data-sortdirection)'); table_data_sorton := xml.ChilkatPath('html|body|div[i]|div|table|(data-sorton)'); table_id := xml.ChilkatPath('html|body|div[i]|table|(id)'); table_role := xml.ChilkatPath('html|body|div[i]|table|(role)'); table_data_scrollx := xml.ChilkatPath('html|body|div[i]|table|(data-scrollx)'); table_data_sortdirection := xml.ChilkatPath('html|body|div[i]|table|(data-sortdirection)'); table_data_sorton := xml.ChilkatPath('html|body|div[i]|table|(data-sorton)'); j := 0; count_j := xml.NumChildrenHavingTag('html|body|div[i]|table|tbody|tr'); while j < count_j do begin xml.J := j; tr_role := xml.ChilkatPath('html|body|div[i]|table|tbody|tr[j]|(role)'); k := 0; count_k := xml.NumChildrenHavingTag('html|body|div[i]|table|tbody|tr[j]|td'); while k < count_k do begin xml.K := k; text := xml.GetChildContent('html|body|div[i]|table|tbody|tr[j]|td[k]|text'); k := k + 1; end; j := j + 1; end; i := i + 1; end; // Let's modify the above code to build the CSV. csv := TChilkatCsv.Create(Self); csv.SetColumnName(0,'Ticker'); csv.SetColumnName(1,'Name'); csv.SetColumnName(2,'Sector'); csv.SetColumnName(3,'Country'); csv.SetColumnName(4,'Weight'); csv.SetColumnName(5,'Notional Vaue'); i := 0; count_i := xml.NumChildrenHavingTag('html|body|div'); while i < count_i do begin xml.I := i; j := 0; count_j := xml.NumChildrenHavingTag('html|body|div[i]|table|tbody|tr'); while j < count_j do begin xml.J := j; k := 0; count_k := xml.NumChildrenHavingTag('html|body|div[i]|table|tbody|tr[j]|td'); while k < count_k do begin xml.K := k; csv.SetCell(j,k,xml.GetChildContent('html|body|div[i]|table|tbody|tr[j]|td[k]|text')); k := k + 1; end; j := j + 1; end; i := i + 1; end; csv.SaveFile('qa_output/brasil_etf.csv'); csvStr := csv.SaveToString(); Memo1.Lines.Add(csvStr); // Our CSV looks like this: // Ticker,Name,Sector,Country,Weight,Notional Vaue // ITUB4,ITAU UNIBANCO HOLDING PREF SA,Financials,Brazil,10.94,"998,954,813.73" // BBDC4,BANCO BRADESCO PREF SA,Financials,Brazil,9.01,"822,164,622.75" // VALE3,CIA VALE DO RIO DOCE SH,Materials,Brazil,8.60,"785,290,260.07" // PETR4,PETROLEO BRASILEIRO PREF SA,Energy,Brazil,5.68,"518,124,434.10" // PETR3,PETROBRAS,Energy,Brazil,4.86,"443,254,438.53" // B3SA3,B3 BRASIL BOLSA BALCAO SA,Financials,Brazil,4.57,"417,636,740.16" // ABEV3,AMBEV SA,Consumer Staples,Brazil,4.57,"417,216,913.63" // BBAS3,BANCO DO BRASIL SA,Financials,Brazil,3.25,"296,921,232.15" // ITSA4,ITAUSA INVESTIMENTOS ITAU PREF SA,Financials,Brazil,2.90,"265,153,684.52" // LREN3,LOJAS RENNER SA,Consumer Discretionary,Brazil,2.25,"205,832,175.98" // end; |
||||
© 2000-2024 Chilkat Software, Inc. All Rights Reserved.