Skip to content Skip to sidebar Skip to footer

Extract Text And Links From Html Using Regular Expressions

I would like to extract text from an html document keeping the links inside it. for example: From this HTML code
bla1 bla1 bla1

Solution 2:

Temporarily encode <a href ...>...</a> into something else, remove all other tags then restore the <a> tags:

// Example in javascript:string.
    replace(/<a(.*?)>/g,'\0$1\0').
    replace(/<\/a>/,'\1').
    replace(/<[^>]*>/,'').
    replace(/\0(.*?)\0/,'<a$1>').
    replace(/\1/,'</a>');

In the code above I use the NUL and SOH characters (ASCII 0x00 and 0x01) as replacements for <a> tags simply because it is highly unlikely that they would appear in strings. Feel free to replace them with any other character or sequence of characters that would not appear in your string.

From additional comments it appears you're operating in a browser. In which case the browser has already parsed the HTML for you into a nice DOM tree. Use DOM methods to parse through the tree and process it the way you want:

functionsimpleHTML (domNode) {
    var ret = "";
    if (domNode.nodeType === Node.ELEMENT_NODE) {
        var children = domNode.childNodes;
        for (var i=0;i<children.length;i++) {
            var child = children[i];

            // Filter out unwanted nodes to speed up processing.// For example, you can ignore 'SCRIPT' nodes etc.if (child.nodeName != 'SCRIPT') {
                if (child.nodeName == 'A') {
                    ret += '<a href="' + child.href + '">' +
                               simpleHTML(child) +
                           '</a>';
                }
                else {
                    ret += simpleHTML(child);
                }
            }
        }
    }
    elseif (domNode.nodeType === Node.TEXT_NODE) {
        ret +=  domNode.nodeValue;
    }
    return ret;
}
// serialize the whole document:var simpleDocument = simpleHTML(document.body);

// serialize a div:var simpleDiv = simpleHTML(document.getElementById('some_div'));

// filter a html formatted string:var temp = document.createElement('DIV');
temp.innerHTML = original_string;
simple_string = simpleHTML(temp);

Post a Comment for "Extract Text And Links From Html Using Regular Expressions"