我正在尝试解析一个看起来像这样的表：
<table><tbody>
<tr><th a href=""></th><th></th></tr>
<tr><td class="v"></td><td class="d"></td><td class="h"></td><td class="a"> </td><td class="o"></td><td class="o"></td><td class="o"></td><td class="p"><table class="p" title="ttt"></table></td></tr>
<tr><td class="v"></td><td class="d"></td><td class="h"></td><td class="a"> </td><td class="o"></td><td class="o"></td><td class="o"></td><td class="p"><table class="p" title="eee"></table></td></tr>
<tr><td class="v"></td><td class="d"></td><td class="h"></td><td class="a"> </td><td class="o"></td><td class="o"></td><td class="o"></td><td class="p"><table class="p" title="rtr"></table></td></tr>
<tr><th a href=""></th><th></th></tr>
<tr><td class="v"></td><td class="d"></td><td class="h"></td><td class="a"> </td><td class="o"></td><td class="o"></td><td class="o"></td><td class="p"><table class="p" title="ouu"></table></td></tr>
<tr><td class="v"></td><td class="d"></td><td class="h"></td><td class="a"> </td><td class="o"></td><td class="o"></td><td class="o"></td><td class="p"><table class="p" title="teee"></table></td></tr>
</tbody></table>
我在ASP.net中使用此代码来获取我想要的每一行中的单元格：
var getHtmlWeb = new HtmlWeb();
var document = getHtmlWeb.Load(txtbox.Text);
//get tables
foreach (HtmlNode table in document.DocumentNode.SelectNodes("//table"))
{
//get each table row
foreach (HtmlNode row in table.SelectNodes("tr"))
{
Outputlabel.Text += "row: <br />";
//get table head tags that have a link, get the Inner text
if((row.SelectSingleNode("//th//a").InnerText) != null)
{
Outputlabel.Text += row.SelectSingleNode("//th//a").InnerText + "<br />";
}
// get the cells with the classes I want
string d = row.SelectSingleNode("//td[@class='d']").InnerText;
Outputlabel.Text += row.SelectSingleNode("//td[@class='d']").InnerText + " ";
string h = row.SelectSingleNode("//td[@class='h']").InnerText;
Outputlabel.Text += row.SelectSingleNode("//td[@class='h']").InnerText + " ";
string a = row.SelectSingleNode("//td[@class='a']").InnerText;
Outputlabel.Text += row.SelectSingleNode("//td[@class='a']").InnerText + " ";
string op = "";
//there are 3 classes in each row to have the class="o"
if (row.SelectNodes("//td[@class='o']") != null)
{
foreach (HtmlNode o in row.SelectNodes("//td[@class='o']"))
{
op += o.InnerText;
}
Outputlabel.Text += op + " ";
}
var pr = row.SelectSingleNode("//td//table[@class='p']");
string pr = probability.Attributes["title"].Value;
Outputlabel.Text += pr + "<br />";
}
}
我只获得了第一个表的第一行，并且重复多次...而且我没有得到类“o”和td标记中带有类“p”的表的标题“ p“
答案 0 :(得分：0)
public static void Main(string[] args)
{
string html = @"<!DOCTYPE html>
<html>
<body>
<table>
<tbody>
<tr>
<th a href="""">a</th>
<th>d2</th>
</tr>
<tr>
<td class=""v"">b</td>
<td class=""d"">v</td>
<td class=""h"">g</td>
<td class=""a""> d </td>
<td class=""o"">e</td>
<td class=""o"">j</td>
<td class=""o"">z</td>
<td class=""p"">
<table class=""p"" title=""ttt""></table>
</td>
</tr>
<tr>
<td class=""v"">1</td>
<td class=""d"">2</td>
<td class=""h"">3</td>
<td class=""a""> 4 </td>
<td class=""o"">5</td>
<td class=""o"">6</td>
<td class=""o"">7</td>
<td class=""p"">
<table class=""p"" title=""eee""></table>
</td>
</tr>
<tr>
<td class=""v"">a1</td>
<td class=""d"">b2</td>
<td class=""h"">v3</td>
<td class=""a""> d4 </td>
<td class=""o"">e5</td>
<td class=""o"">j6</td>
<td class=""o"">z7</td>
<td class=""p"">
<table class=""p"" title=""rtr""></table>
</td>
</tr>
<tr>
<th a href="""">23</th>
<th>qaaa</th>
</tr>
<tr>
<td class=""v"">az</td>
<td class=""d"">b2</td>
<td class=""h"">a b</td>
<td class=""a""> aaaa </td>
<td class=""o"">aa</td>
<td class=""o"">a</td>
<td class=""o"">aaa</td>
<td class=""p"">
<table class=""p"" title=""ouu""></table>
</td>
</tr>
<tr>
<td class=""v"">z</td>
<td class=""d"">zz</td>
<td class=""h"">zzz</td>
<td class=""a""> zzzz </td>
<td class=""o"">zzzzzz</td>
<td class=""o"">zzzzz</td>
<td class=""o"">zzzzzzz</td>
<td class=""p"">
<table class=""p"" title=""teee""></table>
</td>
</tr>
</tbody>
</table></body>
</html>";
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(html);
var coll = doc.DocumentNode.Descendants().Where(x => x.Name == "th" ||
(x.Name == "td" &&
(x.Attributes["class"].Value == "v" ||
x.Attributes["class"].Value == "d" ||
x.Attributes["class"].Value == "h" ||
x.Attributes["class"].Value == "a" ||
x.Attributes["class"].Value == "o")) ||
(x.Name=="table" && x.Attributes["class"] != null && x.Attributes["class"].Value == "p")).ToList();
foreach (HtmlNode node in coll)
{
if(node.Name=="table")
{
Console.WriteLine(node.Attributes["title"].Value);
}
else
{
Console.WriteLine(node.InnerText.Trim());
}
}
}
你应该采取特定的元素而不是整个表格。以下代码采用th,td InnerText的所有table并返回class="p"的{{1}}标题。
以后请格式化您的HTML！
这是你逻辑的关键部分。我没有选择td class="p"，因为您只从表标题中获取此元素。
var coll = doc.DocumentNode.Descendants().Where(x => x.Name == "th" ||
(x.Name == "td" &&
(x.Attributes["class"].Value == "v" ||
x.Attributes["class"].Value == "d" ||
x.Attributes["class"].Value == "h" ||
x.Attributes["class"].Value == "a" ||
x.Attributes["class"].Value == "o")) ||
(x.Name=="table" && x.Attributes["class"] != null && x.Attributes["class"].Value == "p")).ToList();
答案 1 :(得分：0)
它似乎以这种方式用于在线html文件：
HtmlWeb getHtmlWeb = new HtmlWeb();
HtmlDocument doc = getHtmlWeb.Load(txtbox.Text);
string d = "//td[@class='d']";
string h = "//td[@class='h']";
string a = "//td[@class='a']";
string p = "//table[@class='p']";
HtmlNodeCollection ds = doc.DocumentNode.SelectNodes(d);
HtmlNodeCollection hs = doc.DocumentNode.SelectNodes(h);
HtmlNodeCollection as = doc.DocumentNode.SelectNodes(a);
HtmlNodeCollection ps = doc.DocumentNode.SelectNodes(p);
foreach (HtmlNode n in ds)
{
Outputlabel.Text += n.InnerHtml + "<br />";
}
foreach (HtmlNode h in hs)
{
Outputlabel.Text += h.InnerHtml + "<br />";
}
foreach (HtmlNode a in as)
{
Outputlabel.Text += a.Attributes["href"].Value + "<br />";
}
foreach (HtmlNode p in ps)
{
Outputlabel.Text += p.Attributes["title"].Value + "<br />";
}