import Foundation
let pattern = #"(?i)<a\s+href="(?:https?:\/\/)?(?:w{3}\.)?(?:[^"\/]*\.)?([a-z0-9_-]+\.[a-z0-9_-]{2,6})(\/[^"]*)?"[^>]*>(?!.*\1.*)(?:https?:\/\/)?(?:w{3}\.)?(?:[^"\/]*\.)?([a-z0-9_-]+\.[a-z0-9_-]{2,6})(\/[^"]*)?.*?<\/a>"#
let regex = try! NSRegularExpression(pattern: pattern, options: .anchorsMatchLines)
let testString = #"""
<a href="http://www.test1.net/dir1/index.html" target="_blank">test1.net/admin</a> <-- NOT MATCH
<a href="https://test2.com">THIS SITE</a> <-- NOT MATCH
<a href="https://subdomain.test3.org">test2.org</a> <-- MATCH
<a href="http://www2.test4.com" target="_blank">https://global.test4.com/index.html</a> <-- NOT MATCH
<a href="http://eu.test5.com">https://evil.com/eu.test5.com/</a> <-- MATCH
<a href="http://eu.site6.com/index.html" target="_blank">https://eu.evil.com</a> <-- MATCH
<a href="https://site7.com/">http://www.site7.com/123/test</a> <-- NOT MATCH
"""#
let stringRange = NSRange(location: 0, length: testString.utf16.count)
let matches = regex.matches(in: testString, range: stringRange)
var result: [[String]] = []
for match in matches {
var groups: [String] = []
for rangeIndex in 1 ..< match.numberOfRanges {
let nsRange = match.range(at: rangeIndex)
guard !NSEqualRanges(nsRange, NSMakeRange(NSNotFound, 0)) else { continue }
let string = (testString as NSString).substring(with: nsRange)
groups.append(string)
}
if !groups.isEmpty {
result.append(groups)
}
}
print(result)
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Swift 5.2, please visit: https://developer.apple.com/documentation/foundation/nsregularexpression