Files
NetPanel/NetPanel.Help/HtmlTag.cs
2023-07-23 00:36:17 +08:00

228 lines
11 KiB
C#
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

using System;
using System.Collections;
using System.Collections.Generic;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;
namespace NetPanel.Help
{
public class HtmlTag
{
private String m_Name;
private String m_BeginTag;
private String m_InnerHTML;
private Hashtable m_Attributes = new Hashtable();
static Regex attrReg = new Regex(@"([a-zA-Z1-9_-]+)\s*=\s*(\x27|\x22)([^\x27\x22]*)(\x27|\x22)", RegexOptions.IgnoreCase);
private HtmlTag(string name, string beginTag, string innerHTML)
{
m_Name = name;
m_BeginTag = beginTag;
m_InnerHTML = innerHTML;
MatchCollection matchs = attrReg.Matches(beginTag);
foreach (Match match in matchs)
{
m_Attributes[match.Groups[1].Value.ToUpper()] = match.Groups[3].Value;
}
}
public string GetBeginTag()
{
return m_BeginTag;
}
public List<HtmlTag> FindTag(String name)
{
return FindTag(m_InnerHTML, name, String.Format(@"<{0}(\s[^<>]*|)>", name));
}
public List<HtmlTag> FindImgTag()
{
return FindTag(m_InnerHTML, "img", @"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>");
}
public List<HtmlTag> FindTag(String name, String format)
{
return FindTag(m_InnerHTML, name, format);
}
public List<HtmlTag> FindTagByAttr(String tagName, String attrName, String attrValue)
{
return FindTagByAttr(m_InnerHTML, tagName, attrName, attrValue);
}
public String TagName
{
get { return m_Name; }
}
public String InnerHTML
{
get { return m_InnerHTML; }
}
public String InnerText
{
get { return checkStr(m_InnerHTML); }
}
public String GetAttribute(string name)
{
return m_Attributes[name.ToUpper()] as String;
}
public String FindDate
{
get
{
Match m = Regex.Match(InnerText, @"(?<date>((1[6-9]|[2-3]\d)\d{2})-(\d{1,2})-(\d{1,2}))");
if (m.Groups.Count > 0)
{
return m.Groups["date"].Value;
}
else
{
return null;
}
}
}
public static string checkStr2(string html)
{
html = html.Replace("<br>", "$br$");
html = html.Replace("<br/>", "$br/$");
System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" no[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
html = regex1.Replace(html, ""); //过滤<script></script>标记
html = regex2.Replace(html, ""); //过滤href=javascript: (<A>) 属性
html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on...事件
html = regex4.Replace(html, ""); //过滤iframe
html = regex5.Replace(html, ""); //过滤frameset
html = regex6.Replace(html, ""); //过滤frameset
// html = regex7.Replace(html, ""); //过滤frameset
// html = regex8.Replace(html, ""); //过滤frameset
html = regex9.Replace(html, "");
html = html.Replace(" ", "");
html = html.Replace("</strong>", "");
html = html.Replace("<strong>", "");
html = html.Replace("$br$", "<br>");
html = html.Replace("$br/$", "<br/>");
return html;
}
public static string checkStr(string html)
{
if (string.IsNullOrEmpty(html))
{
return html;
}
System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" no[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
html = regex1.Replace(html, ""); //过滤<script></script>标记
html = regex2.Replace(html, ""); //过滤href=javascript: (<A>) 属性
html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on...事件
html = regex4.Replace(html, ""); //过滤iframe
html = regex5.Replace(html, ""); //过滤frameset
html = regex6.Replace(html, ""); //过滤frameset
html = regex7.Replace(html, ""); //过滤frameset
html = regex8.Replace(html, ""); //过滤frameset
html = regex9.Replace(html, "");
html = html.Replace(" ", "");
html = html.Replace("</strong>", "");
html = html.Replace("<strong>", "");
html = html.Replace("&nbsp;", " ");
return html;
}
public static string HtmlToText(string str)
{
string m_outstr = str;
m_outstr = new Regex(@"(?m)<script[^>]*>(\w|\W)*?</script[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
m_outstr = new Regex(@"(?m)<style[^>]*>(\w|\W)*?</style[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
m_outstr = new Regex(@"(?m)<select[^>]*>(\w|\W)*?</select[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
//m_outstr = new Regex(@"(?m)<a[^>]*>(\w|\W)*?</a[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
Regex objReg = new System.Text.RegularExpressions.Regex("(<[^>]+?>)|&nbsp;", RegexOptions.Multiline | RegexOptions.IgnoreCase);
m_outstr = objReg.Replace(m_outstr, "");
Regex objReg2 = new System.Text.RegularExpressions.Regex("(\\s)+", RegexOptions.Multiline | RegexOptions.IgnoreCase);
m_outstr = objReg2.Replace(m_outstr, " ");
return m_outstr;
}
/// <summary>
/// 在文本html的文本查找标志名为tagName,并且属性attrName的值为attrValue的所有标志
/// 例如FindTagByAttr(html, "div", "class", "demo")
/// 返回所有class为demo的div标志
/// </summary>
public static List<HtmlTag> FindTagByAttr(String html, String tagName, String attrName, String attrValue)
{
String format = String.Format(@"<{0}\s[^<>]*{1}\s*=\s*(\x27|\x22){2}(\x27|\x22)[^<>]*>", tagName, attrName, attrValue);
return FindTag(html, tagName, format);
}
public static List<HtmlTag> FindTag(String html, String name, String format)
{
Regex reg = new Regex(format, RegexOptions.IgnoreCase);
Regex tagReg = new Regex(String.Format(@"<(\/|)({0})(\s[^<>]*|)>", name), RegexOptions.IgnoreCase);
List<HtmlTag> tags = new List<HtmlTag>();
int start = 0;
while (true)
{
Match match = reg.Match(html, start);
if (match.Success)
{
start = match.Index + match.Length;
Match tagMatch = null;
int beginTagCount = 1;
while (true)
{
tagMatch = tagReg.Match(html, start);
if (!tagMatch.Success)
{
tagMatch = null;
break;
}
start = tagMatch.Index + tagMatch.Length;
if (tagMatch.Groups[1].Value == "/") beginTagCount--;
else beginTagCount++;
if (beginTagCount == 0) break;
}
if (tagMatch != null)
{
HtmlTag tag = new HtmlTag(name, match.Value, html.Substring(match.Index + match.Length, tagMatch.Index - match.Index - match.Length));
tags.Add(tag);
}
else
{
break;
}
}
else
{
break;
}
}
return tags;
}
}
}