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

Swift 5.1 Version

import UIKit

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
        }
    }
}

Also, if you want to extract date, images, metadata, title and description, you can use my pod named:

.

Readability kit

Answer 2

Swift 4

I really like the solution using documentAttributes. However, it is may too slow for parsing files and/or usage in table view cells. I can't believe that Apple does not provide a decent solution for this.

As a workaround, I found this String Extension on GitHub which works perfectly and is fast for decoding.

So for situations in which the given answer is to slow, see the solution suggest in this link: https://gist.github.com/mwaterfall/25b4a6a06dc3309d9555

Note: it does not parse HTML tags.

Answer 3

Swift 2 version of @akashivskyy's extension,

 extension String {
     init(htmlEncodedString: String) {
         if let encodedData = htmlEncodedString.dataUsingEncoding(NSUTF8StringEncoding){
             let attributedOptions : [String: AnyObject] = [
            NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType,
            NSCharacterEncodingDocumentAttribute: NSUTF8StringEncoding
        ]

             do{
                 if let attributedString:NSAttributedString = try NSAttributedString(data: encodedData, options: attributedOptions, documentAttributes: nil){
                     self.init(attributedString.string)
                 }else{
                     print("error")
                     self.init(htmlEncodedString)     //Returning actual string if there is an error
                 }
             }catch{
                 print("error: \(error)")
                 self.init(htmlEncodedString)     //Returning actual string if there is an error
             }

         }else{
             self.init(htmlEncodedString)     //Returning actual string if there is an error
         }
     }
 }

Answer 4

Elegant Swift 4 Solution

If you want a string,

myString = String(htmlString: encodedString)

add this extension to your project:

extension String {

    init(htmlString: String) {
        self.init()
        guard let encodedData = htmlString.data(using: .utf8) else {
            self = htmlString
            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.localizedDescription)")
            self = htmlString
        }
    }
}

If you want an NSAttributedString with bold, italic, links, etc.,

textField.attributedText = try? NSAttributedString(htmlString: encodedString)

add this extension to your project:

extension NSAttributedString {

    convenience init(htmlString html: String) throws {
        try self.init(data: Data(html.utf8), options: [
            .documentType: NSAttributedString.DocumentType.html,
            .characterEncoding: String.Encoding.utf8.rawValue
            ], documentAttributes: nil)
    }

}

Answer 5

Swift 4

func decodeHTML(string: String) -> String? {

    var decodedString: String?

    if let encodedData = string.data(using: .utf8) {
        let attributedOptions: [NSAttributedString.DocumentReadingOptionKey : Any] = [
            .documentType: NSAttributedString.DocumentType.html,
            .characterEncoding: String.Encoding.utf8.rawValue
        ]

        do {
            decodedString = try NSAttributedString(data: encodedData, options: attributedOptions, documentAttributes: nil).string
        } catch {
            print("\(error.localizedDescription)")
        }
    }

    return decodedString
}

Answer 6

Swift 4

extension String {

    mutating func toHtmlEncodedString() {
        guard let encodedData = self.data(using: .utf8) else {
            return
        }

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

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