Wayback Machine Small Bug Fixes

Fixes encoded ampersands on Wayback Machine's captures graph and problems that arise when trailing slashes are missing in an URL and other small issues universally present in all crawled sites

Stan na 09-01-2016. Zobacz najnowsza wersja.

Aby zainstalować ten skrypt, wymagana jest instalacje jednego z następujących rozszerzeń: Tampermonkey, Greasemonkey lub Violentmonkey.

Aby zainstalować ten skrypt, wymagana jest instalacje jednego z następujących rozszerzeń: Tampermonkey, Violentmonkey.

Aby zainstalować ten skrypt, wymagana jest instalacje jednego z następujących rozszerzeń: Tampermonkey, Violentmonkey.

Aby zainstalować ten skrypt, wymagana będzie instalacja rozszerzenia Tampermonkey lub Userscripts.

You will need to install an extension such as Tampermonkey to install this script.

Aby zainstalować ten skrypt, musisz zainstalować rozszerzenie menedżera skryptów użytkownika.

(Mam już menedżera skryptów użytkownika, pozwól mi to zainstalować!)

You will need to install an extension such as Stylus to install this style.

You will need to install an extension such as Stylus to install this style.

You will need to install an extension such as Stylus to install this style.

Będziesz musiał zainstalować rozszerzenie menedżera stylów użytkownika, aby zainstalować ten styl.

Będziesz musiał zainstalować rozszerzenie menedżera stylów użytkownika, aby zainstalować ten styl.

Musisz zainstalować rozszerzenie menedżera stylów użytkownika, aby zainstalować ten styl.

(Mam już menedżera stylów użytkownika, pozwól mi to zainstalować!)

// ==UserScript==
// @name          Wayback Machine Small Bug Fixes
// @namespace     DoomTay
// @description   Fixes encoded ampersands on Wayback Machine's captures graph and problems that arise when trailing slashes are missing in an URL and other small issues universally present in all crawled sites
// @version       1.2.1
// @include       http://web.archive.org/web/*
// @include       https://web.archive.org/web/*
// @exclude       /\*/
// @grant         none

// ==/UserScript==

var toolbarNav = document.getElementById("wm-graph-anchor");
var lastFolder = window.location.href.substring(window.location.href.lastIndexOf("/") + 1);
var pics = document.images;
var backgrounds = document.querySelectorAll("[background]");
var shouldHaveTrailingSlash = window.location.href.lastIndexOf(".") < window.location.href.lastIndexOf("/") || window.location.href.substring(window.location.href.lastIndexOf("//") + 2) == lastFolder;
var hasTrailingSlash = window.location.href.lastIndexOf("/") == window.location.href.length - 1;
var domain = window.location.href.substring(0,window.location.href.indexOf("/",window.location.href.lastIndexOf("//") + 2));

function fixToolbar()
{
	while(toolbarNav.href.indexOf("&amp;") > -1) toolbarNav.href = toolbarNav.href.replace("&amp;","&");
}

//Fix cases of &amp; in the capture graph
if(toolbarNav) fixToolbar();

if(!document.getElementsByTagName("base")[0])
{
	var base = document.createElement("base");
	if(shouldHaveTrailingSlash && !hasTrailingSlash) base.href = window.location.href + "/";
	else base.href = domain + "/";
	document.head.appendChild(base);
}
	

for(var i = 0; i < pics.length; i++)
{
	//Skip over stuff related to the Wayback Machine toolbar and data URIs
	if((document.getElementById("wm-ipp") && document.getElementById("wm-ipp").contains(pics[i])) || pics[i].src.indexOf("data:") > -1) continue;
	//Refresh images in case the "base url" had to be modified.
	pics[i].src = pics[i].src;
	//For whatever reason, some images will point to within Internet Archive's "main" servers, instead of the crawled site. This attempts to fix that.
	if(pics[i].src.indexOf("http://web.archive.org/web") == -1) pics[i].src = domain + pics[i].src.substring(pics[i].src.indexOf("/",pics[i].src.lastIndexOf("//") + 2));
}
for(var b = 0; b < backgrounds.length; b++)
{
	var bg = backgrounds[b].background || backgrounds[b].getAttribute("background");
	//Skip over stuff related to the Wayback Machine toolbar and data URIs
	if((document.getElementById("wm-ipp") && document.getElementById("wm-ipp").contains(backgrounds[b])) || bg.indexOf("data:") > -1) continue;
	//Refresh images in case the "base url" had to be modified.
	changeBackground(backgrounds[b],bg);
	//For whatever reason, some images will point to within Internet Archive's "main" servers, instead of the crawled site. This attempts to fix that.
	if(relativeToAbsolute(bg).indexOf("http://web.archive.org/web") == -1) 
	{
		var absoluteBG = relativeToAbsolute(bg)
		changeBackground(backgrounds[b],domain + absoluteBG.substring(absoluteBG.indexOf("/",absoluteBG.lastIndexOf("//") + 2)));
	}
}

function relativeToAbsolute(bgURL)
{
	var img = new Image();
	img.src = bgURL;
	return img.src;
}

function changeBackground(node, newBackground)
{
	if(node.background) node.background = newBackground;
	else if(backgrounds[b].getAttribute("background")) backgrounds[b].setAttribute("background",newBackground);
}

var observer = new MutationObserver(function(mutations) {
	mutations.forEach(function(mutation) {
		if(mutation.type == "attributes" && mutation.target == toolbarNav) fixToolbar();
	});    
});

var config = { attributes: true, childList: true, characterData: true, subtree: true, attributeFilter: ["href"] };
if(toolbarNav) observer.observe(toolbarNav, config);