Given a string str that contains some HTML tags, the task is to remove all the tags present in the given string str.
Examples:
Input: str = "<div><b>Geeks for Geeks</b></div>" Output: Geeks for Geeks
Input: str = "<a href="https://www.geeksforgeeks.org/">GFG</a>" Output: GFG
Approach:
The idea is to use Regular Expression to solve this problem. The following steps can be followed to compute the resultant string:
- Get the string.
- Since every HTML tags are enclosed in angular brackets(<>). Therefore use replaceAll() function in regex to replace every substring start with “<“ and ending with “>” to an empty string.
- The function is used as:
String str; str.replaceAll("\\", "");
Below is the implementation of the above approach:
C++
// C++ program for the above approach #include <iostream> #include <regex> using namespace std;
// Function to remove the HTML tags // from the given string void RemoveHTMLTags(string s)
{ const regex pattern( "\\<.*?\\>" );
// Use regex_replace function in regex
// to erase every tags enclosed in <>
s = regex_replace(s, pattern, "" );
// Print string after removing tags
cout << s;
return ;
} // Driver Code int main()
{ // Given String
string str = "<div><b>Geeks for Geeks</b></div>" ;
// Function call to print the
// HTML string after removing tags
RemoveHTMLTags(str);
return 0;
} // This code is contributed by yuvraj_chandra |
Java
// Java program for the above approach class GFG {
// Function to remove the HTML tags
// from the given tags
static void RemoveHTMLTags(String str)
{
// Use replaceAll function in regex
// to erase every tags enclosed in <>
str = str.replaceAll( "\\<.*?\\>" , "" );
// Print string after removing tags
System.out.println(str);
}
// Driver Code
public static void main(String[] args)
{
String str;
// Given String
str = "<div><b>Geeks for Geeks</b></div>" ;
// Function call to print the
// HTML string after removing tags
RemoveHTMLTags(str);
}
} |
Python3
# Python3 program for the # above approach import re
# Function to remove the HTML tags # from the given tags def RemoveHTMLTags(strr):
# Print string after removing tags
print (re. compile (r '<[^>]+>' ).sub('', strr))
# Driver code if __name__ = = '__main__' :
# Given String
strr = "<div><b>Geeks for Geeks</b></div>"
# Function call to print the HTML
# string after removing tags
RemoveHTMLTags(strr);
# This code is contributed by vikas_g |
C#
// C# program for the above approach using System;
class GFG{
// Function to remove the HTML tags // from the given tags static void RemoveHTMLTags(String str)
{ // Use replaceAll function in regex
// to erase every tags enclosed in <>
// str = Regex.Replace(str, "<.*?>", String.Empty)
System.Text.RegularExpressions.Regex rx =
new System.Text.RegularExpressions.Regex( "<[^>]*>" );
str = rx.Replace(str, "" );
// Print string after removing tags
Console.WriteLine(str);
} // Driver code public static void Main(String []args)
{ String str;
// Given String
str = "<div><b>Geeks for Geeks</b></div>" ;
// Function call to print the
// HTML string after removing tags
RemoveHTMLTags(str);
} } // This code is contributed by vikas_g |
Javascript
<script> // JavaScript program for the above approach // Function to remove the HTML tags // from the given string function RemoveHTMLTags(s) {
const pattern = new RegExp( "\\<.*?\\>" );
// Use regex_replace function in regex
// to erase every tags enclosed in <>
s = new String(s).replace(pattern, "" );
// Print string after removing tags
document.write(s);
return ;
} // Driver Code // Given String let str = "<div><b>Geeks for Geeks</b></div>" ;
// Function call to print the // HTML string after removing tags RemoveHTMLTags(str); </script> |
Output:
Geeks for Geeks
Time Complexity: O(N) where N is the length of the given string.
Auxiliary Space: O(1)