PropelDMS · September 14, 2023 19:01
diff --git a/horseman-get-internal-links.js b/horseman-get-internal-links.js
 /**
 * This code first retrieves all the anchor elements in the page using document.querySelectorAll('a').
 * Then it filters out the anchor elements that are inside <head>, <header>, or <footer> tags.
 * After that, it extracts the "href" attribute of each remaining anchor element.
 * Finally, it filters out the URLs that are pointing to other pages on the same domain.
 */
 const isNestedInTags = (element) => {
    const allowedTags = ['head', 'header', 'footer'];
    let parent = element.parentElement;
    while (parent) {
        if (allowedTags.includes(parent.tagName.toLowerCase())) {
            return true;
        }
        parent = parent.parentElement;
    }
    return false;
 };

 // Get all anchor elements in the page
 const anchorElements = document.querySelectorAll('a');

 // Filter out anchor elements nested inside <head>, <header>, or <footer> tags
 const filteredAnchorElements = Array.from(anchorElements).filter((el) => !isNestedInTags(el));

 // Extract the "href" attribute of each anchor element
 const urls = Array.from(filteredAnchorElements).map((el) => el.href);

 // Get the current domain without protocol
 const currentDomain = window.location.host;

 // Filter out URLs pointing to other pages on the same domain
 const sameDomainUrls = urls.filter((url) => {
    const urlWithoutProtocol = url.replace(/^https?:\/\//, '');
    const urlDomain = urlWithoutProtocol.split('/')[0];

    return urlDomain === currentDomain;
 });

 // Filter out URLs with final URI parts starting with a hash mark
 const validUrls = sameDomainUrls.filter((url) => {
    const hashIndex = url.indexOf('#');
    return hashIndex === -1;
 });

 // Remove the protocol from each URL
 const finalUrls = validUrls.map((url) => url.replace(/^https?:\/\//, ''));

 return JSON.stringify(finalUrls);
	/**
	* This code first retrieves all the anchor elements in the page using document.querySelectorAll('a').
	* Then it filters out the anchor elements that are inside <head>, <header>, or <footer> tags.
	* After that, it extracts the "href" attribute of each remaining anchor element.
	* Finally, it filters out the URLs that are pointing to other pages on the same domain.
	*/
	const isNestedInTags = (element) => {
	const allowedTags = ['head', 'header', 'footer'];
	let parent = element.parentElement;
	while (parent) {
	if (allowedTags.includes(parent.tagName.toLowerCase())) {
	return true;
	}
	parent = parent.parentElement;
	}
	return false;
	};

	// Get all anchor elements in the page
	const anchorElements = document.querySelectorAll('a');

	// Filter out anchor elements nested inside <head>, <header>, or <footer> tags
	const filteredAnchorElements = Array.from(anchorElements).filter((el) => !isNestedInTags(el));

	// Extract the "href" attribute of each anchor element
	const urls = Array.from(filteredAnchorElements).map((el) => el.href);

	// Get the current domain without protocol
	const currentDomain = window.location.host;

	// Filter out URLs pointing to other pages on the same domain
	const sameDomainUrls = urls.filter((url) => {
	const urlWithoutProtocol = url.replace(/^https?:\/\//, '');
	const urlDomain = urlWithoutProtocol.split('/')[0];

	return urlDomain === currentDomain;
	});

	// Filter out URLs with final URI parts starting with a hash mark
	const validUrls = sameDomainUrls.filter((url) => {
	const hashIndex = url.indexOf('#');
	return hashIndex === -1;
	});

	// Remove the protocol from each URL
	const finalUrls = validUrls.map((url) => url.replace(/^https?:\/\//, ''));

	return JSON.stringify(finalUrls);