[C#] - 从 HTML 代码中 转换 / 提取 可读文字(PlainText)的方法
2024-08-26 18:40:42
背景
在做网页数据分析的时候,我们关注的部分是内容,可以过滤掉HTML标签、Javascript、CSS等代码。
目标输入
<b>Hello World.</b><br/><p><i>Is there anyone out there?</i><p>
输出结果
Hello World. Is there anyone out there?
开发工具
Html Agility Pack
http://html-agility-pack.net/
实现方案1:(过滤规则严谨,保留HTML版式,推荐使用!)
//small but important modification to class https://github.com/zzzprojects/html-agility-pack/blob/master/src/Samples/Html2Txt/HtmlConvert.cs
public static class HtmlToText
{ public static string Convert(string path)
{
HtmlDocument doc = new HtmlDocument();
doc.Load(path);
return ConvertDoc(doc);
} public static string ConvertHtml(string html)
{
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(html);
return ConvertDoc(doc);
} public static string ConvertDoc (HtmlDocument doc)
{
using (StringWriter sw = new StringWriter())
{
ConvertTo(doc.DocumentNode, sw);
sw.Flush();
return sw.ToString();
}
} internal static void ConvertContentTo(HtmlNode node, TextWriter outText, PreceedingDomTextInfo textInfo)
{
foreach (HtmlNode subnode in node.ChildNodes)
{
ConvertTo(subnode, outText, textInfo);
}
}
public static void ConvertTo(HtmlNode node, TextWriter outText)
{
ConvertTo(node, outText, new PreceedingDomTextInfo(false));
}
internal static void ConvertTo(HtmlNode node, TextWriter outText, PreceedingDomTextInfo textInfo)
{
string html;
switch (node.NodeType)
{
case HtmlNodeType.Comment:
// don't output comments
break;
case HtmlNodeType.Document:
ConvertContentTo(node, outText, textInfo);
break;
case HtmlNodeType.Text:
// script and style must not be output
string parentName = node.ParentNode.Name;
if ((parentName == "script") || (parentName == "style"))
{
break;
}
// get text
html = ((HtmlTextNode)node).Text;
// is it in fact a special closing node output as text?
if (HtmlNode.IsOverlappedClosingElement(html))
{
break;
}
// check the text is meaningful and not a bunch of whitespaces
if (html.Length == )
{
break;
}
if (!textInfo.WritePrecedingWhiteSpace || textInfo.LastCharWasSpace)
{
html= html.TrimStart();
if (html.Length == ) { break; }
textInfo.IsFirstTextOfDocWritten.Value = textInfo.WritePrecedingWhiteSpace = true;
}
outText.Write(HtmlEntity.DeEntitize(Regex.Replace(html.TrimEnd(), @"\s{2,}", " ")));
if (textInfo.LastCharWasSpace = char.IsWhiteSpace(html[html.Length - ]))
{
outText.Write(' ');
}
break;
case HtmlNodeType.Element:
string endElementString = null;
bool isInline;
bool skip = false;
int listIndex = ;
switch (node.Name)
{
case "nav":
skip = true;
isInline = false;
break;
case "body":
case "section":
case "article":
case "aside":
case "h1":
case "h2":
case "header":
case "footer":
case "address":
case "main":
case "div":
case "p": // stylistic - adjust as you tend to use
if (textInfo.IsFirstTextOfDocWritten)
{
outText.Write("\r\n");
}
endElementString = "\r\n";
isInline = false;
break;
case "br":
outText.Write("\r\n");
skip = true;
textInfo.WritePrecedingWhiteSpace = false;
isInline = true;
break;
case "a":
if (node.Attributes.Contains("href"))
{
string href = node.Attributes["href"].Value.Trim();
if (node.InnerText.IndexOf(href, StringComparison.InvariantCultureIgnoreCase)==-)
{
endElementString = "<" + href + ">";
}
}
isInline = true;
break;
case "li":
if(textInfo.ListIndex>)
{
outText.Write("\r\n{0}.\t", textInfo.ListIndex++);
}
else
{
outText.Write("\r\n*\t"); //using '*' as bullet char, with tab after, but whatever you want eg "\t->", if utf-8 0x2022
}
isInline = false;
break;
case "ol":
listIndex = ;
goto case "ul";
case "ul": //not handling nested lists any differently at this stage - that is getting close to rendering problems
endElementString = "\r\n";
isInline = false;
break;
case "img": //inline-block in reality
if (node.Attributes.Contains("alt"))
{
outText.Write('[' + node.Attributes["alt"].Value);
endElementString = "]";
}
if (node.Attributes.Contains("src"))
{
outText.Write('<' + node.Attributes["src"].Value + '>');
}
isInline = true;
break;
default:
isInline = true;
break;
}
if (!skip && node.HasChildNodes)
{
ConvertContentTo(node, outText, isInline ? textInfo : new PreceedingDomTextInfo(textInfo.IsFirstTextOfDocWritten){ ListIndex = listIndex });
}
if (endElementString != null)
{
outText.Write(endElementString);
}
break;
}
}
}
internal class PreceedingDomTextInfo
{
public PreceedingDomTextInfo(BoolWrapper isFirstTextOfDocWritten)
{
IsFirstTextOfDocWritten = isFirstTextOfDocWritten;
}
public bool WritePrecedingWhiteSpace {get;set;}
public bool LastCharWasSpace { get; set; }
public readonly BoolWrapper IsFirstTextOfDocWritten;
public int ListIndex { get; set; }
}
internal class BoolWrapper
{
public BoolWrapper() { }
public bool Value { get; set; }
public static implicit operator bool(BoolWrapper boolWrapper)
{
return boolWrapper.Value;
}
public static implicit operator BoolWrapper(bool boolWrapper)
{
return new BoolWrapper{ Value = boolWrapper };
}
}
实现方案2:(过滤规则不严谨,适用于结构简单的HTML)
public static string StripHTML(string HTMLText, bool decode = true)
{
Regex reg = new Regex("<[^>]+>", RegexOptions.IgnoreCase);
var stripped = reg.Replace(HTMLText, "");
return decode ? HttpUtility.HtmlDecode(stripped) : stripped;
}
参考资料
https://stackoverflow.com/a/25178738
https://stackoverflow.com/a/732110
最新文章
- CozyRSS开发记录22-界面退化
- MyEclispe 2016 CI 0发布(附下载)
- iOS Crash常规跟踪方法及Bugly集成运用
- PHP的三种输出方式
- pull刷新
- Mobile Web调试工具Weinre (reproduce)
- UIWebView获得内容的高-作出自适应高的UIWebView
- tomcat 解析(五)-Tomcat的核心组成和启动过程
- SQLite使用教程4 附加数据库
- 一点BPXA的思考
- CSS减肥的工具–Firefox插件 CSS Usage
- Codeforces 734F Anton and School(位运算)
- Linux学习:curl 与 wget命令
- [UWP小白日记-10]程序启动屏(ios解锁既视感)
- [转]AI+RPA 融合更智能
- MPP-编码示例
- MySqlBulkLoader设置Columns时要注意的地方
- .net core Identity集成IdentityServer(2) 实现IprofileService接口在accesstoken中增加自定义claims
- WRT 下 C++ wstring, string, String^ 互转
- Spooling Directory Source使用技巧