How to Use RegEx to Extract URL and Link Text from HTML Anchor Code?

Questions & Suggestions
, , ,
7

It's a shame that it does not look possible to do in JXA (at least I could not see any way to create the DOM document)

JXA doesn't have a built-in reference to a browser name-space, but it can, of course, still pass code over to Chrome or Safari, opening a window if there isn't one.

Here's a quick draft of a JXA example:

// passing the link HTML directly here (at bottom), but it could be from the value of a KM VAR

(function(strLinkHTML) {
	
	// This function will be converted to a string and 
	// evaluated in the browser context, with an argument supplied
	// by .apply()
	
	function linkParse(strLinkHTML) {
		var oDiv, oNode;
	
		(oDiv = document.createElement('div')
		).innerHTML = strLinkHTML;
		
		return (
			oNode = oDiv.firstChild
		) ? "[" + oNode.text + "](" + oNode.href + ")" : ""
	}
	
	var appChrome = Application("Google Chrome");
		lstWins = appChrome.windows();
		lngWins = lstWins.length,
		
		// If no window is open we make one
		
		oWin = lngWins ? lstWins[0] : appChrome.Window().make(),
		
		// Compose the .js we need ...
		
		strJS = '(' + linkParse.toString() + ').apply(null, [\'' + strLinkHTML + '\'])';
		
	
	// and run it in Chrome - the Safari syntax is slightly different here
	return (
		oWin.activeTab.execute({
			javascript: strJS
		})
	);
	
})(
	'<a href="http://www.google.com/?q=purescript">purescript</a>'
);