c# - Las etiquetas HTML Agility Pack NO están en la lista blanca

tags html-parsing

Question

Intento crear una función que elimine las etiquetas html y los atributos que no están en una lista blanca. Tengo el siguiente HTML:

<b>first text </b>
<b>second text here
<a>some text here</a>
<a>some text here</a>
</b>
<a>some twxt here</a>

Estoy usando HTML Agility Pack y el código que tengo hasta ahora es:

static List<string> WhiteNodeList = new List<string> { "b" };
static List<string> WhiteAttrList = new List<string> { };
static HtmlNode htmlNode;
public static void RemoveNotInWhiteList(out string _output, HtmlNode pNode, List<string> pWhiteList, List<string> attrWhiteList)
{
// remove all attributes not on white list
foreach (var item in pNode.ChildNodes)
{
item.Attributes.Where(u => attrWhiteList.Contains(u.Name) == false).ToList().ForEach(u => RemoveAttribute(u));
}
// remove all html and their innerText and attributes if not on whitelist.
//pNode.ChildNodes.Where(u => pWhiteList.Contains(u.Name) == false).ToList().ForEach(u => u.Remove());
//pNode.ChildNodes.Where(u => pWhiteList.Contains(u.Name) == false).ToList().ForEach(u => u.ParentNode.ReplaceChild(ConvertHtmlToNode(u.InnerHtml),u));
//pNode.ChildNodes.Where(u => pWhiteList.Contains(u.Name) == false).ToList().ForEach(u => u.Remove());
for (int i = 0; i < pNode.ChildNodes.Count; i++)
{
if (!pWhiteList.Contains(pNode.ChildNodes[i].Name))
{
HtmlNode _newNode = ConvertHtmlToNode(pNode.ChildNodes[i].InnerHtml);
pNode.ChildNodes[i].ParentNode.ReplaceChild(_newNode, pNode.ChildNodes[i]);
if (pNode.ChildNodes[i].HasChildNodes && !string.IsNullOrEmpty(pNode.ChildNodes[i].InnerText.Trim().Replace("/r/n", "")))
{
HtmlNode outputNode1 = pNode.ChildNodes[i];
for (int j = 0; j < pNode.ChildNodes[i].ChildNodes.Count; j++)
{
string _childNodeOutput;
RemoveNotInWhiteList(out _childNodeOutput,
pNode.ChildNodes[i], WhiteNodeList, WhiteAttrList);
pNode.ChildNodes[i].ReplaceChild(ConvertHtmlToNode(_childNodeOutput), pNode.ChildNodes[i].ChildNodes[j]);
i++;
}
}
}
}
// Console.WriteLine(pNode.OuterHtml);
_output = pNode.OuterHtml;
}
private static void RemoveAttribute(HtmlAttribute u)
{
u.Value = u.Value.ToLower().Replace("javascript", "");
u.Remove();
}
public static HtmlNode ConvertHtmlToNode(string html)
{
HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
doc.LoadHtml(html);
if (doc.DocumentNode.ChildNodes.Count == 1)
return doc.DocumentNode.ChildNodes[0];
else return doc.DocumentNode;
}

La salida que intento lograr es

<b>first text </b>
<b>second text here
some text here
some text here
</b>
some twxt here

Eso significa que solo quiero mantener las etiquetas <b> .
La razón por la que estoy haciendo esto es porque algunos de los usuarios copian y pegan desde MS WORD en el editor de wywsywyg html.

Gracias.!

Answer 1

Gracias por el código, ¡¡¡gran cosa !!

Hice pocas optimizaciones ...

class TagSanitizer
{
List<HtmlNode> _deleteNodes = new List<HtmlNode>();
public static void Sanitize(HtmlNode node)
{
new TagSanitizer().Clean(node);
}
void Clean(HtmlNode node)
{
CleanRecursive(node);
for (int i = _deleteNodes.Count - 1; i >= 0; i--)
{
HtmlNode nodeToDelete = _deleteNodes[i];
nodeToDelete.ParentNode.RemoveChild(nodeToDelete, true);
}
}
void CleanRecursive(HtmlNode node)
{
if (node.NodeType == HtmlNodeType.Element)
{
if (Config.TagsWhiteList.ContainsKey(node.Name) == false)
{
_deleteNodes.Add(node);
}
else if (node.HasAttributes)
{
for (int i = node.Attributes.Count - 1; i >= 0; i--)
{
HtmlAttribute currentAttribute = node.Attributes[i];
string[] allowedAttributes = Config.TagsWhiteList[node.Name];
if (allowedAttributes != null)
{
if (allowedAttributes.Contains(currentAttribute.Name) == false)
{
node.Attributes.Remove(currentAttribute);
}
}
else
{
node.Attributes.Remove(currentAttribute);
}
}
}
}
if (node.HasChildNodes)
{
node.ChildNodes.ToList().ForEach(v => CleanRecursive(v));
}
}
}

Answer 2

heh, aparentemente CASI encontré una respuesta en una publicación de blog que alguien hizo ...

using System.Collections.Generic;
using System.Linq;
using HtmlAgilityPack;
namespace Wayloop.Blog.Core.Markup
{
public static class HtmlSanitizer
{
private static readonly IDictionary<string, string[]> Whitelist;
static HtmlSanitizer()
{
Whitelist = new Dictionary<string, string[]> {
{ "a", new[] { "href" } },
{ "strong", null },
{ "em", null },
{ "blockquote", null },
};
}
public static string Sanitize(string input)
{
var htmlDocument = new HtmlDocument();
htmlDocument.LoadHtml(input);
SanitizeNode(htmlDocument.DocumentNode);
return htmlDocument.DocumentNode.WriteTo().Trim();
}
private static void SanitizeChildren(HtmlNode parentNode)
{
for (int i = parentNode.ChildNodes.Count - 1; i >= 0; i--) {
SanitizeNode(parentNode.ChildNodes[i]);
}
}
private static void SanitizeNode(HtmlNode node)
{
if (node.NodeType == HtmlNodeType.Element) {
if (!Whitelist.ContainsKey(node.Name)) {
node.ParentNode.RemoveChild(node);
return;
}
if (node.HasAttributes) {
for (int i = node.Attributes.Count - 1; i >= 0; i--) {
HtmlAttribute currentAttribute = node.Attributes[i];
string[] allowedAttributes = Whitelist[node.Name];
if (!allowedAttributes.Contains(currentAttribute.Name)) {
node.Attributes.Remove(currentAttribute);
}
}
}
}
if (node.HasChildNodes) {
SanitizeChildren(node);
}
}
}
}

Obtuve HtmlSanitizer desde aquí Aparentemente no quita las etiquetas, pero elimina el elemento por completo.

OK, aquí está la solución para aquellos que la necesitarán más tarde.

public static class HtmlSanitizer
{
private static readonly IDictionary<string, string[]> Whitelist;
private static List<string> DeletableNodesXpath = new List<string>();
static HtmlSanitizer()
{
Whitelist = new Dictionary<string, string[]> {
{ "a", new[] { "href" } },
{ "strong", null },
{ "em", null },
{ "blockquote", null },
{ "b", null},
{ "p", null},
{ "ul", null},
{ "ol", null},
{ "li", null},
{ "div", new[] { "align" } },
{ "strike", null},
{ "u", null},
{ "sub", null},
{ "sup", null},
{ "table", null },
{ "tr", null },
{ "td", null },
{ "th", null }
};
}
public static string Sanitize(string input)
{
if (input.Trim().Length < 1)
return string.Empty;
var htmlDocument = new HtmlDocument();
htmlDocument.LoadHtml(input);
SanitizeNode(htmlDocument.DocumentNode);
string xPath = HtmlSanitizer.CreateXPath();
return StripHtml(htmlDocument.DocumentNode.WriteTo().Trim(), xPath);
}
private static void SanitizeChildren(HtmlNode parentNode)
{
for (int i = parentNode.ChildNodes.Count - 1; i >= 0; i--)
{
SanitizeNode(parentNode.ChildNodes[i]);
}
}
private static void SanitizeNode(HtmlNode node)
{
if (node.NodeType == HtmlNodeType.Element)
{
if (!Whitelist.ContainsKey(node.Name))
{
if (!DeletableNodesXpath.Contains(node.Name))
{
//DeletableNodesXpath.Add(node.Name.Replace("?",""));
node.Name = "removeableNode";
DeletableNodesXpath.Add(node.Name);
}
if (node.HasChildNodes)
{
SanitizeChildren(node);
}
return;
}
if (node.HasAttributes)
{
for (int i = node.Attributes.Count - 1; i >= 0; i--)
{
HtmlAttribute currentAttribute = node.Attributes[i];
string[] allowedAttributes = Whitelist[node.Name];
if (allowedAttributes != null)
{
if (!allowedAttributes.Contains(currentAttribute.Name))
{
node.Attributes.Remove(currentAttribute);
}
}
else
{
node.Attributes.Remove(currentAttribute);
}
}
}
}
if (node.HasChildNodes)
{
SanitizeChildren(node);
}
}
private static string StripHtml(string html, string xPath)
{
HtmlDocument htmlDoc = new HtmlDocument();
htmlDoc.LoadHtml(html);
if (xPath.Length > 0)
{
HtmlNodeCollection invalidNodes = htmlDoc.DocumentNode.SelectNodes(@xPath);
foreach (HtmlNode node in invalidNodes)
{
node.ParentNode.RemoveChild(node, true);
}
}
return htmlDoc.DocumentNode.WriteContentTo(); ;
}
private static string CreateXPath()
{
string _xPath = string.Empty;
for (int i = 0; i < DeletableNodesXpath.Count; i++)
{
if (i != DeletableNodesXpath.Count - 1)
{
_xPath += string.Format("//{0}|", DeletableNodesXpath[i].ToString());
}
else _xPath += string.Format("//{0}", DeletableNodesXpath[i].ToString());
}
return _xPath;
}
}

Cambié el nombre del nodo porque si tuviera que analizar un nodo de espacio de nombres XML se bloquearía en el análisis xpath.