Skip to content

Instantly share code, notes, and snippets.

@tjkelly

tjkelly/SERP URL Extractor, a la ViperChill

Created August 18, 2020 03:10
Show Gist options
  • Save tjkelly/a2aa1f4d2d1f1c87510a10b5669272f2 to your computer and use it in GitHub Desktop.
Save tjkelly/a2aa1f4d2d1f1c87510a10b5669272f2 to your computer and use it in GitHub Desktop.
Download ZIP
Based on Glen Allsop's "Advanced Google Chrome Bookmarklets for SEOs" — I got tired of getting the URL slug caught up in list, so I edited the JS a bit.
Raw
SERP URL Extractor, a la ViperChill
javascript:(function(){output="<html><head>";output+="<title>SEO SERP Extraction Tool</title>";output+='<style type="text/css">';output+="*{font-family:georgia;word-break:break-all}";output+="</style>";output+="</head><body>";pageAnchors=document.getElementsByTagName("a");divClasses=document.getElementsByTagName("div");var linkcount=0;var linkLocation="";var linkAnchorText="";output+="<h1>Results</h1>";output+='<div id="wrap"><table border="1" cellspacing="0" cellpadding="4"><th>#</th><th>Link</th><th>Anchor</th>';for(i=0;i<pageAnchors.length;i++){if(pageAnchors[i].parentNode.parentNode.getAttribute("class")!="iUh30"){var anchorText=pageAnchors[i].textContent;for(j=0;j<pageAnchors[i].childNodes.length;j++){if(pageAnchors[i].childNodes[j].className=="LC20lb DKV0Md"){var anchorText=pageAnchors[i].childNodes[j].textContent}}var anchorLink=pageAnchors[i].href;var linkAnchor=anchorLink+"\t"+anchorText;var anchorID=pageAnchors[i].id;if(anchorLink!=""){if(anchorLink.match(/^((?!google\.|cache|blogger.com|\.yahoo\.|youtube\.com\/\?gl=|youtube\.com\/results|javascript:|api\.technorati\.com|botw\.org\/search|del\.icio\.us\/url\/check|digg\.com\/search|search\.twitter\.com\/search|search\.yahoo\.com\/search|siteanalytics\.compete\.com|tools\.seobook\.com\/general\/keyword\/suggestions|web\.archive\.org\/web\/|whois\.domaintools\.com|www\.alexa\.com\/data\/details\/main|www\.bloglines\.com\/search|www\.majesticseo\.com\/search\.php|www\.semrush\.com\/info\/|www\.semrush\.com\/search\.php|www\.stumbleupon\.com\/url|wikipedia.org\/wiki\/Special:Search).)*$/i)){if(anchorID.match(/^((?!hdtb_more|hdtb_tls|uh_hl).)*$/i)){linkLocation+=anchorLink+"</li><li>";linkAnchorText+=anchorText+"</li><li>";linkcount++;if(anchorText===undefined){anchorText=pageAnchors[i].innerText}output+="<tr>";output+="<th>"+linkcount+"</th>";output+="<td>"+pageAnchors[i].href+"</a></td>";output+="<td>"+anchorText+"</td>";output+="</tr>\n"}}}}}output+="</table></div><br/><hr>";output+="<h1>URL List</h1>";output+="<ul><li>"+linkLocation+"</ul>";output+="<br/><hr>";output+="<h1>Anchor Text List</h1>";output+="<ul><li>"+linkAnchorText+"</ul>";output+="</body></html>";with(window.open()){document.write(output);document.close()}})();
/*!
* Unminified Code
*
* @author TJ Kelly - https://getmxt.com
*
* @date 2020-08-17
*
* @notes
* Based on Glen Allsop's "Advanced Google Chrome Bookmarklets for SEOs"
* https://detailed.com/chrome-bookmarklets-seo/
*
* I got tired of getting the URL slug caught up in list, so I edited the JS a bit.
*/
javascript: (function () {
output = "<html><head>";
output += "<title>SEO SERP Extraction Tool</title>";
output += '<style type="text/css">';
output += "*{font-family:georgia;word-break:break-all}";
output += "</style>";
output += "</head><body>";
pageAnchors = document.getElementsByTagName("a");
divClasses = document.getElementsByTagName("div");
var linkcount = 0;
var linkLocation = "";
var linkAnchorText = "";
output += "<h1>Results</h1>";
output += '<div id="wrap"><table border="1" cellspacing="0" cellpadding="4"><th>#</th><th>Link</th><th>Anchor</th>';
for (i = 0; i < pageAnchors.length; i++) {
if (pageAnchors[i].parentNode.parentNode.getAttribute("class") != "iUh30") {
var anchorText = pageAnchors[i].textContent;
for (j = 0; j < pageAnchors[i].childNodes.length; j++) {
if (pageAnchors[i].childNodes[j].className == "LC20lb DKV0Md") {
var anchorText = pageAnchors[i].childNodes[j].textContent
}
}
var anchorLink = pageAnchors[i].href;
var linkAnchor = anchorLink + "\t" + anchorText;
var anchorID = pageAnchors[i].id;
if (anchorLink != "") {
if (anchorLink.match(/^((?!google\.|cache|blogger.com|\.yahoo\.|youtube\.com\/\?gl=|youtube\.com\/results|javascript:|api\.technorati\.com|botw\.org\/search|del\.icio\.us\/url\/check|digg\.com\/search|search\.twitter\.com\/search|search\.yahoo\.com\/search|siteanalytics\.compete\.com|tools\.seobook\.com\/general\/keyword\/suggestions|web\.archive\.org\/web\/|whois\.domaintools\.com|www\.alexa\.com\/data\/details\/main|www\.bloglines\.com\/search|www\.majesticseo\.com\/search\.php|www\.semrush\.com\/info\/|www\.semrush\.com\/search\.php|www\.stumbleupon\.com\/url|wikipedia.org\/wiki\/Special:Search).)*$/i)) {
if (anchorID.match(/^((?!hdtb_more|hdtb_tls|uh_hl).)*$/i)) {
linkLocation += anchorLink + "</li><li>";
linkAnchorText += anchorText + "</li><li>";
linkcount++;
if (anchorText === undefined) {
anchorText = pageAnchors[i].innerText
}
output += "<tr>";
output += "<th>" + linkcount + "</th>";
output += "<td>" + pageAnchors[i].href + "</a></td>";
output += "<td>" + anchorText + "</td>";
output += "</tr>\n"
}
}
}
}
}
output += "</table></div><br/><hr>";
output += "<h1>URL List</h1>";
output += "<ul><li>" + linkLocation + "</ul>";
output += "<br/><hr>";
output += "<h1>Anchor Text List</h1>";
output += "<ul><li>" + linkAnchorText + "</ul>";
output += "</body></html>";
with(window.open()) {
document.write(output);
document.close()
}
})();
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment