Convert a HTML table with rowspans to datatable C#

Question

1.00/5 (1 vote)

See more:

I need to convert a Html Table to DataTable in C#. I used HtmlAgilityPack but it does not convert it well because of rowspans. The code I am currently using is:

 private static DataTable convertHtmlTableToDataTable()
    {
        WebClient webClient = new WebClient();
        string urlContent = webClient.DownloadString("http://example.com");

        string tableCode = getTableCode(urlContent);

        string htmlCode = tableCode.Replace(" ", " ");

        HtmlDocument doc = new HtmlDocument();
        doc.LoadHtml(htmlCode);
        var headers = doc.DocumentNode.SelectNodes("//tr/th");
        DataTable table = new DataTable();

        foreach (HtmlNode header in headers)
        {
            table.Columns.Add(header.InnerText);
        }
        foreach (var row in doc.DocumentNode.SelectNodes("//tr[td]"))
        {
            table.Rows.Add(row.SelectNodes("td").Select(td => td.InnerText).ToArray());
        }
        return table;
    }

And this is a part of Html Table:

 <pre lang="HTML"> <table class="tabel" cellspacing="0" border="0">
    <caption style="font-family:Verdana; font-size:20px;">SEMGRP</caption>
    <tr>
        <th class="celula" >Ora</th>
        <th  class="latime_celula celula">Luni</th>
        <th  class="latime_celula celula">Marti</th>
        <th  class="latime_celula celula">Miercuri</th>
        <th  class="latime_celula celula">Joi</th>
        <th  class="latime_celula celula">Vineri</th>
    </tr>
    <tr>
        <td class="celula" nowrap="nowrap">8-9</td>
        <td class="celula" rowspan="2">
                                <table border="0" align="center">
                                    <tr>
                                        <td nowrap="nowrap" align="center">   
                                            Curs    
                                            <br />
                                            <a class="link_celula" href="afis_n0.php?id_tip=287&tip=p">Prof</a> 
                                            <br />
                                            <a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a>
                                            <br />
                                        </td>
                                    </tr>
                                </table>
        </td>
        <td class="celula" rowspan="2">
                                <table border="0" align="center">
                                    <tr>
                                        <td nowrap="nowrap" align="center">
                                            Curs    
                                            <br />
                                            <a class="link_celula" href="afis_n0.php?id_tip=287&tip=p">Prof</a> 
                                            <br />
                                            <a class="link_celula" href="afis_n0.php?id_tip=12&tip=s">Sala</a>  
                                            <br />
                                        </td>
                                    </tr>
                                </table>
        </td>
        <td class="celula"> </td>
        <td class="celula"> </td>
        <td class="celula" rowspan="2">
                                <table border="0" align="center">
                                    <tr>
                                        <td nowrap="nowrap" align="center">
                                        Curs
                                        <br />
                                        <a class="link_celula" href="afis_n0.php?id_tip=293&tip=p">Prof</a>
                                        <br />
                                        <a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a>
                                        <br />
                                        </td>
                                    </tr>
                                </table>
        </td>
    </tr>
    <tr>
        <td class="celula" nowrap="nowrap">9-10</td>
        <td class="celula"> </td>
        <td class="celula"> </td>
    </tr>
    <tr>
        <td class="celula" nowrap="nowrap">10-11</td>
        <td class="celula" rowspan="2">
                                <table border="0" align="center">
                                    <tr>
                                        <td nowrap="nowrap" align="center">   Curs
                                        <br /><a class="link_celula" href="afis_n0.php?id_tip=303&tip=p">Prof</a>
                                        <br /><a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a>
                                        <br />
                                        </td>
                                    </tr>
                                </table>
        </td>
        <td class="celula" rowspan="2">
                                <table border="0" align="center">
                                    <tr>
                                        <td nowrap="nowrap" align="center">   Curs
                                        <br />
                                        <a class="link_celula" href="afis_n0.php?id_tip=331&tip=p">Prof</a>
                                        <br />
                                        <a class="link_celula" href="afis_n0.php?id_tip=14&tip=s">Sala</a>  
                                        <br />
                                        </td>
                                    </tr>
                                </table>
        </td>
        <td class="celula" rowspan="2">
                                <table border="0" align="center">
                                    <tr>
                                        <td nowrap="nowrap" align="center">   Curs
                                        <br /><a class="link_celula" href="afis_n0.php?id_tip=330&tip=p">Prof</a>   
                                        <br /><a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a> 
                                        <br />
                                        </td>
                                    </tr>
                                </table>
        </td>
        <td class="celula"> </td>
        <td class="celula" rowspan="2">
                                <table border="0" align="center">
                                    <tr>
                                        <td nowrap="nowrap" align="center">   Curs
                                        <br />
                                        <a class="link_celula" href="afis_n0.php?id_tip=293&tip=p">Prof</a>
                                        <br />
                                        <a class="link_celula" href="afis_n0.php?id_tip=10&tip=s">Sala</a>  <br />
                                        </td>
                                    </tr>
                                </table>
        </td>
    </tr>
    <tr>
        <td class="celula" nowrap="nowrap">11-12</td>
        <td class="celula"> </td>
    </tr>
    <tr>

I tried some solutions but I did not find any good...

What I have tried:

Thanks for any help in advance.

Posted 22-Apr-17 13:20pm

StefanTP

Updated 22-Apr-17 21:58pm

Add a Solution

2 solutions

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

RickZeeland · Answer 1 · 2017-04-22T21:27:00

Solution 1

This seems to be a good library.
Cross framework (WinForms/WPF/PDF/Metro/Mono/etc.), Multipurpose (UI Controls / Image generation / PDF generation / etc.), 100% managed (C#), High performance HTML Rendering library: HTML Renderer - Home[^]

Posted 22-Apr-17 21:27pm

RickZeeland

Member 13146073 · Answer 2 · 2017-04-22T21:58:00

private static DataTable convertHtmlTableToDataTable()
{
WebClient webClient = new WebClient();
string urlContent = webClient.DownloadString("http://example.com");

string tableCode = getTableCode(urlContent);

string htmlCode = tableCode.Replace(" ", " ");

HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(htmlCode);
var headers = doc.DocumentNode.SelectNodes("//tr/th");
DataTable table = new DataTable();

foreach (HtmlNode header in headers)
{
table.Columns.Add(header.InnerText);
}
foreach (var row in doc.DocumentNode.SelectNodes("//tr[td]"))
{
table.Rows.Add(row.SelectNodes("td").Select(td => td.InnerText).ToArray());
}
return table;
}

And this is a part of Html Table:

HTML

<table class="tabel" cellspacing="0" border="0"><caption style="font-family:Verdana; font-size:20px;">SEMGRP</caption><tbody><tr><th class="celula">Ora</th><th class="latime_celula celula">Luni</th><th class="latime_celula celula">Marti</th><th class="latime_celula celula">Miercuri</th><th class="latime_celula celula">Joi</th><th class="latime_celula celula">Vineri</th></tr><tr><td class="celula" nowrap="nowrap">8-9</td><td class="celula" rowspan="2">




                            <table border="0" align="center"><tbody><tr><td nowrap="nowrap" align="center">
                                        Curs
                                        <br>
                                        <a class="link_celula" href="afis_n0.php?id_tip=287&tip=p">Prof</a>
                                        <br>
                                        <a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a>
                                        <br>
                                    </td></tr></tbody></table>
    </td><td class="celula" rowspan="2">




                            <table border="0" align="center"><tbody><tr><td nowrap="nowrap" align="center">
                                        Curs
                                        <br>
                                        <a class="link_celula" href="afis_n0.php?id_tip=287&tip=p">Prof</a>
                                        <br>
                                        <a class="link_celula" href="afis_n0.php?id_tip=12&tip=s">Sala</a>
                                        <br>
                                    </td></tr></tbody></table>
    </td><td class="celula"> </td><td class="celula"> </td><td class="celula" rowspan="2">




                            <table border="0" align="center"><tbody><tr><td nowrap="nowrap" align="center">
                                    Curs
                                    <br>
                                    <a class="link_celula" href="afis_n0.php?id_tip=293&tip=p">Prof</a>
                                    <br>
                                    <a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a>
                                    <br>
                                    </td></tr></tbody></table>
    </td></tr><tr><td class="celula" nowrap="nowrap">9-10</td><td class="celula"> </td><td class="celula"> </td></tr><tr><td class="celula" nowrap="nowrap">10-11</td><td class="celula" rowspan="2">




                            <table border="0" align="center"><tbody><tr><td nowrap="nowrap" align="center">   Curs
                                    <br><a class="link_celula" href="afis_n0.php?id_tip=303&tip=p">Prof</a>
                                    <br><a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a>
                                    <br>
                                    </td></tr></tbody></table>
    </td><td class="celula" rowspan="2">




                            <table border="0" align="center"><tbody><tr><td nowrap="nowrap" align="center">   Curs
                                    <br>
                                    <a class="link_celula" href="afis_n0.php?id_tip=331&tip=p">Prof</a>
                                    <br>
                                    <a class="link_celula" href="afis_n0.php?id_tip=14&tip=s">Sala</a>
                                    <br>
                                    </td></tr></tbody></table>
    </td><td class="celula" rowspan="2">




                            <table border="0" align="center"><tbody><tr><td nowrap="nowrap" align="center">   Curs
                                    <br><a class="link_celula" href="afis_n0.php?id_tip=330&tip=p">Prof</a>
                                    <br><a class="link_celula" href="afis_n0.php?id_tip=9&tip=s">Sala</a>
                                    <br>
                                    </td></tr></tbody></table>
    </td><td class="celula"> </td><td class="celula" rowspan="2">




                            <table border="0" align="center"><tbody><tr><td nowrap="nowrap" align="center">   Curs
                                    <br>
                                    <a class="link_celula" href="afis_n0.php?id_tip=293&tip=p">Prof</a>
                                    <br>
                                    <a class="link_celula" href="afis_n0.php?id_tip=10&tip=s">Sala</a>  <br>
                                    </td></tr></tbody></table>
    </td></tr><tr><td class="celula" nowrap="nowrap">11-12</td><td class="celula"> </td></tr><tr></tr></tbody></table>