Lianja
Lianja
HTML Table to CSV
See more HTML-to-XML/Text Examples
Demonstrates a method for converting an HTML table to a CSV file.Note: This example requires Chilkat v9.5.0.77 or greater.
Chilkat Lianja Downloads
llSuccess = .F.
// 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
loHttp = createobject("CkHttp")
loBdHtml = createobject("CkBinData")
llSuccess = loHttp.QuickGetBd("https://example-code.com/data/etf_table.html",loBdHtml)
if (llSuccess <> .T.) then
? loHttp.LastErrorText
release loHttp
release loBdHtml
return
endif
// Convert to XML.
loHtx = createobject("CkHtmlToXml")
loHtx.SetHtmlBd(loBdHtml)
loSbXml = createobject("CkStringBuilder")
loHtx.ToXmlSb(loSbXml)
loXml = createobject("CkXml")
loXml.LoadSb(loSbXml,.T.)
// Remove attributes and sub-trees we don't need.
// (In other words, we're getting rid of clutter...)
lnNumRemoved = loXml.PruneTag("thead")
lnNumRemoved = loXml.PruneAttribute("style")
lnNumRemoved = loXml.PruneAttribute("class")
// Scrub the element and attribute content.
loXml.Scrub("ContentTrimEnds,ContentTrimInside,AttrTrimEnds,AttrTrimInside")
// Let's see what we have...
? loXml.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
lnCount_i = loXml.NumChildrenHavingTag("html|body|div")
do while i < lnCount_i
loXml.I = i
lcTable_role = loXml.ChilkatPath("html|body|div[i]|div|table|(role)")
lcTable_data_scrollx = loXml.ChilkatPath("html|body|div[i]|div|table|(data-scrollx)")
lcTable_data_sortdirection = loXml.ChilkatPath("html|body|div[i]|div|table|(data-sortdirection)")
lcTable_data_sorton = loXml.ChilkatPath("html|body|div[i]|div|table|(data-sorton)")
lcTable_id = loXml.ChilkatPath("html|body|div[i]|table|(id)")
lcTable_role = loXml.ChilkatPath("html|body|div[i]|table|(role)")
lcTable_data_scrollx = loXml.ChilkatPath("html|body|div[i]|table|(data-scrollx)")
lcTable_data_sortdirection = loXml.ChilkatPath("html|body|div[i]|table|(data-sortdirection)")
lcTable_data_sorton = loXml.ChilkatPath("html|body|div[i]|table|(data-sorton)")
j = 0
lnCount_j = loXml.NumChildrenHavingTag("html|body|div[i]|table|tbody|tr")
do while j < lnCount_j
loXml.J = j
lcTr_role = loXml.ChilkatPath("html|body|div[i]|table|tbody|tr[j]|(role)")
k = 0
lnCount_k = loXml.NumChildrenHavingTag("html|body|div[i]|table|tbody|tr[j]|td")
do while k < lnCount_k
loXml.K = k
lcText = loXml.GetChildContent("html|body|div[i]|table|tbody|tr[j]|td[k]|text")
k = k + 1
enddo
j = j + 1
enddo
i = i + 1
enddo
// Let's modify the above code to build the CSV.
loCsv = createobject("CkCsv")
loCsv.SetColumnName(0,"Ticker")
loCsv.SetColumnName(1,"Name")
loCsv.SetColumnName(2,"Sector")
loCsv.SetColumnName(3,"Country")
loCsv.SetColumnName(4,"Weight")
loCsv.SetColumnName(5,"Notional Vaue")
i = 0
lnCount_i = loXml.NumChildrenHavingTag("html|body|div")
do while i < lnCount_i
loXml.I = i
j = 0
lnCount_j = loXml.NumChildrenHavingTag("html|body|div[i]|table|tbody|tr")
do while j < lnCount_j
loXml.J = j
k = 0
lnCount_k = loXml.NumChildrenHavingTag("html|body|div[i]|table|tbody|tr[j]|td")
do while k < lnCount_k
loXml.K = k
loCsv.SetCell(j,k,loXml.GetChildContent("html|body|div[i]|table|tbody|tr[j]|td[k]|text"))
k = k + 1
enddo
j = j + 1
enddo
i = i + 1
enddo
loCsv.SaveFile("qa_output/brasil_etf.csv")
lcCsvStr = loCsv.SaveToString()
? lcCsvStr
// 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"
//
release loHttp
release loBdHtml
release loHtx
release loSbXml
release loXml
release loCsv