How do I decode HTML entities in Swift?

Question

I am pulling a JSON file from a site and one of the strings received is:

The Weeknd ‘King Of The Fall&         


        

Answer 1

Objective-C

+(NSString *) decodeHTMLEnocdedString:(NSString *)htmlEncodedString {
    if (!htmlEncodedString) {
        return nil;
    }

    NSData *data = [htmlEncodedString dataUsingEncoding:NSUTF8StringEncoding];
    NSDictionary *attributes = @{NSDocumentTypeDocumentAttribute:     NSHTMLTextDocumentType,
                             NSCharacterEncodingDocumentAttribute:     @(NSUTF8StringEncoding)};
    NSAttributedString *attributedString = [[NSAttributedString alloc]     initWithData:data options:attributes documentAttributes:nil error:nil];
    return [attributedString string];
}

Answer 2

Swift 4

---

• String extension computed variable
• Without extra guard, do, catch, etc...
• Returns the original strings if decoding fails

---

extension String {
    var htmlDecoded: String {
        let decoded = try? NSAttributedString(data: Data(utf8), options: [
            .documentType: NSAttributedString.DocumentType.html,
            .characterEncoding: String.Encoding.utf8.rawValue
        ], documentAttributes: nil).string

        return decoded ?? self
    }
}

Answer 3

Computed var version of @yishus' answer

public extension String {
    /// Decodes string with HTML encoding.
    var htmlDecoded: String {
        guard let encodedData = self.data(using: .utf8) else { return self }

        let attributedOptions: [String : Any] = [
            NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType,
            NSCharacterEncodingDocumentAttribute: String.Encoding.utf8.rawValue]

        do {
            let attributedString = try NSAttributedString(data: encodedData,
                                                          options: attributedOptions,
                                                          documentAttributes: nil)
            return attributedString.string
        } catch {
            print("Error: \(error)")
            return self
        }
    }
}

Answer 4

Swift 4 Version

extension String {

    init(htmlEncodedString: String) {
        self.init()
        guard let encodedData = htmlEncodedString.data(using: .utf8) else {
            self = htmlEncodedString
            return
        }

        let attributedOptions: [NSAttributedString.DocumentReadingOptionKey : Any] = [
            .documentType: NSAttributedString.DocumentType.html,
            .characterEncoding: String.Encoding.utf8.rawValue
        ]

        do {
            let attributedString = try NSAttributedString(data: encodedData, options: attributedOptions, documentAttributes: nil)
            self = attributedString.string
        } 
        catch {
            print("Error: \(error)")
            self = htmlEncodedString
        }
    }
}

Answer 5

Swift 3.0 version with actual font size conversion

Normally, if you directly convert HTML content to an attributed string, the font size is increased. You can try to convert an HTML string to an attributed string and back again to see the difference.

Instead, here is the actual size conversion that makes sure the font size does not change, by applying the 0.75 ratio on all fonts:

extension String {
    func htmlAttributedString() -> NSAttributedString? {
        guard let data = self.data(using: String.Encoding.utf16, allowLossyConversion: false) else { return nil }
        guard let attriStr = try? NSMutableAttributedString(
            data: data,
            options: [NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType],
            documentAttributes: nil) else { return nil }
        attriStr.beginEditing()
        attriStr.enumerateAttribute(NSFontAttributeName, in: NSMakeRange(0, attriStr.length), options: .init(rawValue: 0)) {
            (value, range, stop) in
            if let font = value as? UIFont {
                let resizedFont = font.withSize(font.pointSize * 0.75)
                attriStr.addAttribute(NSFontAttributeName,
                                         value: resizedFont,
                                         range: range)
            }
        }
        attriStr.endEditing()
        return attriStr
    }
}

Answer 6

Swift 4.1 +

var htmlDecoded: String {


    let attributedOptions: [NSAttributedString.DocumentReadingOptionKey : Any] = [

        NSAttributedString.DocumentReadingOptionKey.documentType : NSAttributedString.DocumentType.html,
        NSAttributedString.DocumentReadingOptionKey.characterEncoding : String.Encoding.utf8.rawValue
    ]


    let decoded = try? NSAttributedString(data: Data(utf8), options: attributedOptions
        , documentAttributes: nil).string

    return decoded ?? self
}