HTML解析器Html Agility Pack (HAP)源码(读取/写入DOM并支持纯XPATH或XSLT)

【实例简介】

Html Agility Pack (HAP)是一个灵活的HTML解析器，它构建了一个可读/写的DOM，并支持纯XPATH或XSLT（无需理解XPATH或XSLT即可使用，不用担心...）。 它是一个.NET代码库，允许您解析“来自网络”的HTML文件。 解析器对“真实世界”中的不规范HTML非常宽容。 对象模型与System.Xml提出的模型非常相似，但适用于HTML文档（或流）。

【实例截图】
【核心代码】
文件清单
└── html-agility-pack-98fd0dbbc5b21b306b2fb62f4dc70b8290fe1370
    ├── LICENSE
    ├── README.md
    └── src
        ├── HtmlAgilityPack.Master.sln
        ├── HtmlAgilityPack.Net20
        │   ├── HtmlAgilityPack.Net20.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.Net35
        │   ├── HtmlAgilityPack.Net35.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.Net40
        │   ├── HtmlAgilityPack.Net40.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.Net40-client
        │   ├── HtmlAgilityPack.Net40-client.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.Net45
        │   ├── HtmlAgilityPack.Net45.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.NetCore45
        │   ├── HtmlAgilityPack.NetCore45.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.NetStandard1_3
        │   └── AssemblyInfo.cs
        ├── HtmlAgilityPack.NETStandard1_3
        │   ├── HtmlAgilityPack.NETStandard1_3.csproj
        │   └── HtmlAgilityPack.snk
        ├── HtmlAgilityPack.NetStandard1_6
        │   ├── AssemblyInfo.cs
        │   ├── HtmlAgilityPack.NetStandard1_6.csproj
        │   └── HtmlAgilityPack.snk
        ├── HtmlAgilityPack.NetStandard2_0
        │   ├── AssemblyInfo.cs
        │   └── HtmlAgilityPack.snk
        ├── HtmlAgilityPack.NETStandard2_0
        │   └── HtmlAgilityPack.NETStandard2_0.csproj
        ├── HtmlAgilityPack.Portable-wp8
        │   ├── HtmlAgilityPack.Portable-wp8.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.Portable-wp81
        │   ├── HtmlAgilityPack.Portable-wp81.csproj
        │   ├── HtmlAgilityPack.snk
        │   └── Properties
        │       └── AssemblyInfo.cs
        ├── HtmlAgilityPack.Shared
        │   ├── crc32.cs
        │   ├── EncodingFoundException.cs
        │   ├── HtmlAgilityPack.Shared.projitems
        │   ├── HtmlAgilityPack.Shared.projitems.vspscc
        │   ├── HtmlAgilityPack.Shared.shproj
        │   ├── HtmlAgilityPack.Shared.shproj.vspscc
        │   ├── HtmlAttributeCollection.cs
        │   ├── HtmlAttribute.cs
        │   ├── HtmlCmdLine.cs
        │   ├── HtmlCommentNode.cs
        │   ├── HtmlConsoleListener.cs
        │   ├── HtmlDocument.cs
        │   ├── HtmlDocument.PathMethods.cs
        │   ├── HtmlDocument.Xpath.cs
        │   ├── HtmlElementFlag.cs
        │   ├── HtmlEntity.cs
        │   ├── HtmlNameTable.cs
        │   ├── HtmlNodeCollection.cs
        │   ├── HtmlNode.cs
        │   ├── HtmlNode.Encapsulator.cs
        │   ├── HtmlNodeNavigator.cs
        │   ├── HtmlNodeType.cs
        │   ├── HtmlNode.Xpath.cs
        │   ├── HtmlParseErrorCode.cs
        │   ├── HtmlParseError.cs
        │   ├── HtmlTextNode.cs
        │   ├── HtmlWeb.cs
        │   ├── HtmlWebException.cs
        │   ├── HtmlWeb.Xpath.cs
        │   ├── InvalidProgramException.cs
        │   ├── IOLibrary.cs
        │   ├── Metro
        │   │   ├── HtmlWeb.cs
        │   │   └── InvalidProgramException.cs
        │   ├── MimeTypeMap.cs
        │   ├── MixedCodeDocumentCodeFragment.cs
        │   ├── MixedCodeDocument.cs
        │   ├── MixedCodeDocumentFragment.cs
        │   ├── MixedCodeDocumentFragmentList.cs
        │   ├── MixedCodeDocumentFragmentType.cs
        │   ├── MixedCodeDocumentTextFragment.cs
        │   ├── NameValuePair.cs
        │   ├── NameValuePairList.cs
        │   ├── Trace.cs
        │   ├── Trace.FullFramework.cs
        │   └── Utilities.cs
        ├── HtmlAgilityPack.sln
        ├── HtmlAgilityPack.UAP10
        │   ├── HtmlAgilityPack.snk
        │   ├── HtmlAgilityPack.UAP10.csproj
        │   └── Properties
        │       └── AssemblyInfo.cs
        └── Tests
            ├── HtmlAgilityPack.Tests.Net45
            │   ├── files
            │   │   ├── attr_quote_expected.html
            │   │   ├── attr_quote.html
            │   │   ├── mshome.htm
            │   │   ├── overflow.html
            │   │   ├── regression.html
            │   │   └── test.html
            │   ├── HtmlAgilityPack.snk
            │   ├── HtmlAgilityPack.Tests.Net45.csproj
            │   ├── HtmlDocument.PreserveOriginalTest.cs
            │   ├── HtmlDocumentTests.cs
            │   ├── HtmlEntityTest.cs
            │   ├── HtmlNode.Tests.cs
            │   ├── mshome.htm
            │   ├── packages.config
            │   ├── Properties
            │   │   └── AssemblyInfo.cs
            │   └── UnitTest1.cs
            └── HtmlAgilityPack.Tests.NetStandard2_0
                ├── EncapsulationTestHtml.cs
                ├── EncapsulatorTests.cs
                ├── HtmlAgilityPack.Tests.NetStandard2_0.csproj
                └── HtmlNode_GetEncapsulatedData_NodeReturnType_Tests.cs

32 directories, 105 files