using System;
using System.Text.RegularExpressions;
public class Example
{
public static void Main()
{
string pattern = @"<(?:div|ul|li)(?=[^>]*\bclass=""([^""]+)"")(?=(?:[^>]*\bdata-\w+=""([^""]+)"")?)";
string input = @"With preg_match_all I want to get class and data-attributes in html.
I asked a similar question before. The correct answer to the previous responsibility was done with DOM. But as an alternative to the DOM structure, I also need a regex version.
The pattern works fine. However, if the lines are side-by-side, they also take class names from tags that should not be accepted.
<div class=""noproblem"">
<ul class=""noproblem"" data-ss=""1"">
<li class=""noproblem"" data-ss=""1"">
<!-- <i> is not my tag. but there s no problem with that. because it s underneath . -->
<i class=""no_problem""></i>
</li>
</ul>
</div>
<div class=""noproblem"" data-ss=""1""> <!-- problem: data-ss is not accepted -->
<ul class=""noproblem"" data-ss=""1"">
<!-- <i> is not my tag. my tags: div|ul|li . -->
<li class=""noproblem""><i class=""this_is_problem""></i>
</li>
</ul>
</div>
<div class=""noproblem"">
<ul class=""noproblem"">
<!-- <i> is not my tag. my tags: div|ul|li . -->
<li class=""noproblem""><i class=""this_is_problem""></i>
</li>
<!-- <span> is not my tag. my tags: div|ul|li . -->
<li class=""test""><span class=""this_is_problem""></span></li>
<!-- (li class empty version): <span> is not my tag. my tags: div|ul|li . -->
<li><span class=""this_is_problem""></span></li>
</ul>
</div>";
RegexOptions options = RegexOptions.Multiline;
foreach (Match m in Regex.Matches(input, pattern, options))
{
Console.WriteLine("'{0}' found at index {1}.", m.Value, m.Index);
}
}
}
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 C#, please visit: https://msdn.microsoft.com/en-us/library/system.text.regularexpressions.regex(v=vs.110).aspx