Scrape site to report css selector occurrence in HTML - html

Question

I want to see how much of my team's code has been integrated into a large scale site.
I believe I can achieve this (albeit roughly), by getting statistics on the number of occurrences certain CSS selectors appear across all the HTML pages. I have some unique CSS class selectors that I would like to use when scraping the site to analyze:
On how many pages the selector occurs.
On any page it does, how many times.
I've looked around but can't find any tools - does anyone know of any, or could suggest any idea's that may help me quickly achieve this ?
Thanks in advance.

Answer 1

Thanks to everyone for their advice.
In the end I decided that there was no one tool that could help me gather the statistics in the way I described so I already started to build up the application I needed in Node. Although I've not used Node before I've found it quick to grasp with an intermediate knowledge of Javascript.
For anyone looking to do the same:
I've used Simplecrawler to run over the site and Cheerio to find selectors and from this I can create a simple report created in Json using FS.

Answer 2

I'd recommend you to use Google App Scripting. You might manage to crawl site's pages and count the CSS selector occurrences with regex. Modify he following code to search each page for CSS selector. The code explanation is here.
Code
function onOpen() {
DocumentApp.getUi() // Or DocumentApp or FormApp.
.createMenu('New scrape web docs')
.addItem('Enter Url', 'showPrompt')
.addToUi();
}
function showPrompt() {
var ui = DocumentApp.getUi();
var result = ui.prompt(
'Scrape whole website into text!',
'Please enter website url (with http(s)://):',
ui.ButtonSet.OK_CANCEL);
// Process the user's response.
var button = result.getSelectedButton();
var url = result.getResponseText();
var links=[];
var base_url = url;
if (button == ui.Button.OK) { // User clicked "OK".
if(!isValidURL(url))
{
ui.alert('Your url is not valid.');
}
else {
// gather initial links
var inner_links_arr = scrapeAndPaste(url, 1); // first run and clear the document
links = links.concat(inner_links_arr); // append an array to all the links
var new_links=[]; // array for new links
var processed_urls =[url]; // processed links
var link, current;
while (links.length)
{
link = links.shift(); // get the most left link (inner url)
processed_urls.push(link);
current = base_url + link;
new_links = scrapeAndPaste(current, 0); // second and consecutive runs we do not clear up the document
//ui.alert('Processed... ' + current + '\nReturned links: ' + new_links.join('\n') );
// add new links into links array (stack) if appropriate
for (var i in new_links){
var item = new_links[i];
if (links.indexOf(item) === -1 && processed_urls.indexOf(item) === -1)
links.push(item);
}
/* // alert message for debugging
ui.alert('Links in stack: ' + links.join(' ')
+ '\nTotal links in stack: ' + links.length
+ '\nProcessed: ' + processed_urls.join(' ')
+ '\nTotal processed: ' + processed_urls.length);
*/
}
}
}
}
function scrapeAndPaste(url, clear) {
var text;
try {
var html = UrlFetchApp.fetch(url).getContentText();
// some html pre-processing
if (html.indexOf('</head>') !== -1 ){
html = html.split('</head>')[1];
}
if (html.indexOf('</body>') !== -1 ){ // thus we split the body only
html = html.split('</body>')[0] + '</body>';
}
// fetch inner links
var inner_links_arr= [];
var linkRegExp = /href="(.*?)"/gi; // regex expression object
var match = linkRegExp.exec(html);
while (match != null) {
// matched text: match[0]
if (match[1].indexOf('#') !== 0
&& match[1].indexOf('http') !== 0
//&& match[1].indexOf('https://') !== 0
&& match[1].indexOf('mailto:') !== 0
&& match[1].indexOf('.pdf') === -1 ) {
inner_links_arr.push(match[1]);
}
// match start: match.index
// capturing group n: match[n]
match = linkRegExp.exec(html);
}
text = getTextFromHtml(html);
outputText(url, text, clear); // output text into the current document with given url
return inner_links_arr; //we return all inner links of this doc as array
} catch (e) {
MailApp.sendEmail(Session.getActiveUser().getEmail(), "Scrape error report at "
+ Utilities.formatDate(new Date(), "GMT", "yyyy-MM-dd HH:mm:ss"),
"\r\nMessage: " + e.message
+ "\r\nFile: " + e.fileName+ '.gs'
+ "\r\nWeb page under scrape: " + url
+ "\r\nLine: " + e.lineNumber);
outputText(url, 'Scrape error for this page cause of malformed html!', clear);
}
}
function getTextFromHtml(html) {
return getTextFromNode(Xml.parse(html, true).getElement());
}
function getTextFromNode(x) {
switch(x.toString()) {
case 'XmlText': return x.toXmlString();
case 'XmlElement': return x.getNodes().map(getTextFromNode).join(' ');
default: return '';
}
}
function outputText(url, text, clear){
var body = DocumentApp.getActiveDocument().getBody();
if (clear){
body.clear();
}
else {
body.appendHorizontalRule();
}
var section = body.appendParagraph(' * ' + url);
section.setHeading(DocumentApp.ParagraphHeading.HEADING2);
body.appendParagraph(text);
}
function isValidURL(url){
var RegExp = /^(([\w]+:)?\/\/)?(([\d\w]|%[a-fA-f\d]{2,2})+(:([\d\w]|%[a-fA-f\d]{2,2})+)?#)?([\d\w][-\d\w]{0,253}[\d\w]\.)+[\w]{2,4}(:[\d]+)?(\/([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)*(\?(&?([-+_~.\d\w]|%[a-fA-f\d]{2,2})=?)*)?(#([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)?$/;
if(RegExp.test(url)){
return true;
}else{
return false;
}
}