Stripping out HTML tags from a string
HtmlIosSwiftHtml Problem Overview
How do I remove HTML tags from a string so that I can output clean text?
let str = string.stringByReplacingOccurrencesOfString("<[^>]+>", withString: "", options: .RegularExpressionSearch, range: nil)
print(str)
Html Solutions
Solution 1 - Html
Hmm, I tried your function and it worked on a small example:
var string = "<!DOCTYPE html> <html> <body> <h1>My First Heading</h1> <p>My first paragraph.</p> </body> </html>"
let str = string.stringByReplacingOccurrencesOfString("<[^>]+>", withString: "", options: .RegularExpressionSearch, range: nil)
print(str)
//output " My First Heading My first paragraph. "
Can you give an example of a problem?
Swift 4 and 5 version:
var string = "<!DOCTYPE html> <html> <body> <h1>My First Heading</h1> <p>My first paragraph.</p> </body> </html>"
let str = string.replacingOccurrences(of: "<[^>]+>", with: "", options: .regularExpression, range: nil)
Solution 2 - Html
Since HTML is not a regular language (HTML is a context-free language), you cannot use Regular Expressions. See: Using regular expressions to parse HTML: why not?
I would consider using NSAttributedString instead.
let htmlString = "LCD Soundsystem was the musical project of producer <a href='http://www.last.fm/music/James+Murphy' class='bbcode_artist'>James Murphy</a>, co-founder of <a href='http://www.last.fm/tag/dance-punk' class='bbcode_tag' rel='tag'>dance-punk</a> label <a href='http://www.last.fm/label/DFA' class='bbcode_label'>DFA</a> Records. Formed in 2001 in New York City, New York, United States, the music of LCD Soundsystem can also be described as a mix of <a href='http://www.last.fm/tag/alternative%20dance' class='bbcode_tag' rel='tag'>alternative dance</a> and <a href='http://www.last.fm/tag/post%20punk' class='bbcode_tag' rel='tag'>post punk</a>, along with elements of <a href='http://www.last.fm/tag/disco' class='bbcode_tag' rel='tag'>disco</a> and other styles. <br />"
let htmlStringData = htmlString.dataUsingEncoding(NSUTF8StringEncoding)!
let options: [String: AnyObject] = [NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType, NSCharacterEncodingDocumentAttribute: NSUTF8StringEncoding]
let attributedHTMLString = try! NSAttributedString(data: htmlStringData, options: options, documentAttributes: nil)
let string = attributedHTMLString.string
Or, as Irshad Mohamed in the comments would do it:
let attributed = try NSAttributedString(data: htmlString.data(using: .unicode)!, options: [NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType], documentAttributes: nil)
print(attributed.string)
Solution 3 - Html
Mohamed solution but as a String extension in Swift 4.
extension String {
func stripOutHtml() -> String? {
do {
guard let data = self.data(using: .unicode) else {
return nil
}
let attributed = try NSAttributedString(data: data, options: [.documentType: NSAttributedString.DocumentType.html, .characterEncoding: String.Encoding.utf8.rawValue], documentAttributes: nil)
return attributed.string
} catch {
return nil
}
}
}
Solution 4 - Html
I'm using the following extension to remove specific HTML elements:
extension String {
func deleteHTMLTag(tag:String) -> String {
return self.stringByReplacingOccurrencesOfString("(?i)</?\(tag)\\b[^<]*>", withString: "", options: .RegularExpressionSearch, range: nil)
}
func deleteHTMLTags(tags:[String]) -> String {
var mutableString = self
for tag in tags {
mutableString = mutableString.deleteHTMLTag(tag)
}
return mutableString
}
}
This makes it possible to only remove <a> tags from a string, e.g.:
let string = "my html <a href="">link text</a>"
let withoutHTMLString = string.deleteHTMLTag("a") // Will be "my html link text"
Solution 5 - Html
extension String{
var htmlStripped : String{
return self.replacingOccurrences(of: "<[^>]+>", with: "", options: .regularExpression, range: nil)
}
}
Happy Coding
Solution 6 - Html
I prefer to use a regular expression than to use NSAttributedString HTML conversion, be advised that is pretty time consuming and need to be run on the main thread too. More information here: https://developer.apple.com/documentation/foundation/nsattributedstring/1524613-initwithdata
For me this made the trick, first I remove any CSS inline styling, and later all the HTML tags. Probably not solid as the NSAttributedString option, but way faster for my case.
extension String {
func withoutHtmlTags() -> String {
let str = self.replacingOccurrences(of: "<style>[^>]+</style>", with: "", options: .regularExpression, range: nil)
return str.replacingOccurrences(of: "<[^>]+>", with: "", options: .regularExpression, range: nil)
}
}
Solution 7 - Html
swift 4 :
extension String {
func deleteHTMLTag(tag:String) -> String {
return self.replacingOccurrences(of: "(?i)</?\(tag)\\b[^<]*>", with: "", options: .regularExpression, range: nil)
}
func deleteHTMLTags(tags:[String]) -> String {
var mutableString = self
for tag in tags {
mutableString = mutableString.deleteHTMLTag(tag: tag)
}
return mutableString
}
}
Solution 8 - Html
Updated for Swift 4:
guard let htmlStringData = htmlString.data(using: .unicode) else { fatalError() }
let options: [NSAttributedString.DocumentReadingOptionKey: Any] = [
.documentType: NSAttributedString.DocumentType.html
.characterEncoding: String.Encoding.unicode.rawValue
]
let attributedHTMLString = try! NSAttributedString(data: htmlStringData, options: options, documentAttributes: nil)
let string = attributedHTMLString.string
Solution 9 - Html
Swift 5
extension String {
public func trimHTMLTags() -> String? {
guard let htmlStringData = self.data(using: String.Encoding.utf8) else {
return nil
}
let options: [NSAttributedString.DocumentReadingOptionKey : Any] = [
.documentType: NSAttributedString.DocumentType.html,
.characterEncoding: String.Encoding.utf8.rawValue
]
let attributedString = try? NSAttributedString(data: htmlStringData, options: options, documentAttributes: nil)
return attributedString?.string
}
}
Use:
let str = "my html <a href='https://www.google.com'>link text</a>"
print(str.trimHTMLTags() ?? "--") //"my html link text"