在Swift中将HTML转换为纯文本

我正在开发一个简单的RSS Reader应用程序，作为Xcode中的初学者项目。目前，我已设置它解析提要，并将标题，发布日期，描述和内容放置在WebView中。

我最近决定在用于选择帖子的TableView中显示说明（或内容的删节版本）。但是，这样做时：

cell.textLabel?.text = item.title?.uppercaseString
cell.detailTextLabel?.text = item.itemDescription //.itemDescription is a String

它显示了帖子的原始HTML。

我想知道如何仅将TableView的详细UILabel转换为纯HTML。

谢谢！

您可以添加此扩展名以将html代码转换为常规字符串：

编辑/更新：

讨论不应从后台线程调用HTML导入器（即，选项字典包含值为html的documentType）。它将尝试与主线程同步，失败并超时。从主线程调用它是可行的（但如果HTML包含对外部资源的引用，仍可能会超时，应该不惜一切代价避免这样做）。HTML导入机制旨在实现诸如markdown之类的东西（即，文本样式，颜色等），而不是用于常规HTML导入。

Xcode 11.4•Swift 5.2

extension Data {
    var html2AttributedString: NSAttributedString? {
        do {
            return try NSAttributedString(data: self, options: [.documentType: NSAttributedString.DocumentType.html, .characterEncoding: String.Encoding.utf8.rawValue], documentAttributes: nil)
        } catch {
            print("error:", error)
            return  nil
        }
    }
    var html2String: String { html2AttributedString?.string ?? "" }
}

extension StringProtocol {
    var html2AttributedString: NSAttributedString? {
        Data(utf8).html2AttributedString
    }
    var html2String: String {
        html2AttributedString?.string ?? ""
    }
}

cell.detailTextLabel?.text = item.itemDescription.html2String

斯威夫特4，Xcode 9

extension String {
    
    var utfData: Data {
        return Data(utf8)
    }
    
    var attributedHtmlString: NSAttributedString? {
        
        do {
            return try NSAttributedString(data: utfData, options: [
              .documentType: NSAttributedString.DocumentType.html,
              .characterEncoding: String.Encoding.utf8.rawValue
            ], 
            documentAttributes: nil)
        } catch {
            print("Error:", error)
            return nil
        }
    }
}

extension UILabel {
   func setAttributedHtmlText(_ html: String) {
      if let attributedText = html.attributedHtmlString {
         self.attributedText = attributedText
      } 
   }
}

这是我建议的答案。如果要放入函数中，请不要使用扩展名。

func decodeString(encodedString:String) -> NSAttributedString?
    {
        let encodedData = encodedString.dataUsingEncoding(NSUTF8StringEncoding)!
        do {
            return try NSAttributedString(data: encodedData, options: [NSDocumentTypeDocumentAttribute:NSHTMLTextDocumentType,NSCharacterEncodingDocumentAttribute:NSUTF8StringEncoding], documentAttributes: nil)
        } catch let error as NSError {
            print(error.localizedDescription)
            return nil
        }
    }

并调用该函数并将NSAttributedString转换为String

let attributedString = self.decodeString(encodedString)
let message = attributedString.string

请使用此代码测试detailTextLabel：

var attrStr = NSAttributedString(
        data: item.itemDescription.dataUsingEncoding(NSUnicodeStringEncoding, allowLossyConversion: true),
        options: [ NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType],
        documentAttributes: nil,
        error: nil)
cell.detailTextLabel?.text = attrStr

在swift3中尝试此解决方案

extension String{
    func convertHtml() -> NSAttributedString{
        guard let data = data(using: .utf8) else { return NSAttributedString() }
        do{
            return try NSAttributedString(data: data, options: [NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType, NSCharacterEncodingDocumentAttribute: String.Encoding.utf8.rawValue], documentAttributes: nil)
        }catch{
            return NSAttributedString()
        }
    }
}

使用

self.lblValDesc.attributedText = str_postdescription.convertHtml()

Swift4.0扩展

 extension String {
    var html2AttributedString: String? {
    guard let data = data(using: .utf8) else { return nil }
    do {
        return try NSAttributedString(data: data, options: [.documentType: NSAttributedString.DocumentType.html, .characterEncoding: String.Encoding.utf8.rawValue], documentAttributes: nil).string

    } catch let error as NSError {
        print(error.localizedDescription)
        return  nil
    }
  }
}

我使用了Danboz答案，只是将其更改为返回一个简单的String（而不是富文本字符串）：

static func htmlToText(encodedString:String) -> String?
{
    let encodedData = encodedString.dataUsingEncoding(NSUTF8StringEncoding)!
    do
    {
        return try NSAttributedString(data: encodedData, options: [NSDocumentTypeDocumentAttribute:NSHTMLTextDocumentType,NSCharacterEncodingDocumentAttribute:NSUTF8StringEncoding], documentAttributes: nil).string
    } catch let error as NSError {
        print(error.localizedDescription)
        return nil
    }
}

对我来说，它就像一种魅力，谢谢Danboz

let content = givenString // html included string
let attrStr = try! NSAttributedString(data: content.data(using: String.Encoding.unicode, allowLossyConversion: true)!,options: [ NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType],documentAttributes: nil)
self.labelName.attributedText = attrStr