Could you advise me with writing a greasemonkey script displaying only anchors () in a web page and deleting everything else?
thank you
This code will wipe out everything but a list of the href's from links (added line breaks for clarity):
var links = document.querySelectorAll ("a");
//--- Build up new body, that will just display hrefs.
var newPageStr = "";
for (var J=0, L=links.length; J < L; ++J) {
//--- Skip links with empty href's.
var href = links[J].href;
if ( /\w/.test (href) ) {
newPageStr += '' + href + '<br>';
}
}
//--- Replace everything on the page with the link list.
document.close ();
document.open ();
document.write (newPageStr);
document.close ();
Update:
Since document.write() seems to flake in the GM environment, here's a DOM-based alternative:
var links = document.querySelectorAll ("a");
//--- Build up new body, that will just display hrefs.
var newPageStr = "";
for (var J=0, L=links.length; J < L; ++J) {
//--- Skip links with empty href's.
var href = links[J].href;
if ( /\w/.test (href) ) {
newPageStr += '' + href + '<br>';
}
}
//--- Erase everything from the page's body:
var b = document.body;
var p = b.parentNode;
p.removeChild (b);
//--- Add our new link list.
var newB = document.createElement ("BODY");
newB.innerHTML = newPageStr;
p.appendChild (newB);
var tags = document.getElementsByTagName('*');
for (var i = 0; i < tags.length; i++) {
if (tags[i].tagName != 'A') {
tags[i].style.color = 'transparent';
tags[i].style.background = 'none';
tags[i].style.border = 'none';
}
}
Related
I found this useful code
var x = document.querySelectorAll("a");
var myarray = []
for (var i=0; i<x.length; i++){
var nametext = x[i].textContent;
var cleantext = nametext.replace(/\s+/g, ' ').trim();
var cleanlink = x[i].href;
myarray.push([cleantext,cleanlink]);
};
function make_table() {
var table = '<table><thead><th>Name</th><th>Links</th></thead><tbody>';
for (var i=0; i<myarray.length; i++) {
table += '<tr><td>'+ myarray[i][0] + '</td><td>'+myarray[i][1]+'</td></tr>';
};
var w = window.open("");
w.document.write(table);
}
make_table()
When you add this to the web browser console - it opens up a new webpage with all weblinks with names
however some of the names are shortned.
is there a way to edit it so it shows the entire text name for that link
I used the following TreeWalker as a template from this post https://stackoverflow.com/a/37178130/7102491 and modified it to skip the element 'script', to prevent certain pages like a google search from breaking to no avail. Does anyone know how I can change the code to prevent breaking certain pages? Thanks.
var replaceArry = [
[/b/gi, 'better'],
[/Terms of service/gi, 'Términos y condiciones'],
[/Privacy policy/gi, 'Privacidad'],
// etc.
];
var numTerms = replaceArry.length;
var txtWalker = document.createTreeWalker (
document.body,
NodeFilter.SHOW_TEXT,
{ acceptNode: function (node) {
//-- Skip whitespace-only nodes
if (node.nodeValue.trim() && node.parentNode.nodeName != 'SCRIPT')
return NodeFilter.FILTER_ACCEPT;
return NodeFilter.FILTER_SKIP;
}
},
false
);
var txtNode = null;
while (txtNode = txtWalker.nextNode () ) {
var oldTxt = txtNode.nodeValue;
for (var J = 0; J < numTerms; J++) {
oldTxt = oldTxt.replace (replaceArry[J][0], replaceArry[J][1]);
}
txtNode.nodeValue = oldTxt;
}
I need to read the "Top Nav", the "Children Nodes" and check if each node is visible.
I am using JSOM to accomplish this. Everything is working fine except for the get_isVisible() function. It always returns true. MSDN: http://msdn.microsoft.com/en-us/library/office/jj246297.aspx
I am on a publishing site in 2013 and I know some of the items are hidden. (My web and context are defined outside of this snippet)
var visParents = [], visChildren = [];
var topNodes = web.get_navigation().get_topNavigationBar();
context.load(topNodes);
context.executeQueryAsync(onQuerySucceeded, onQueryFailed)
function onQuerySucceeded() {
var nodeInfo = '';
var nodeEnumerator = topNodes.getEnumerator();
while (nodeEnumerator.moveNext()) {
var node = nodeEnumerator.get_current();
nodeInfo += node.get_title() + '\n';
if (node.get_isVisible())
visParents.push(node);
}
console.log("Current nodes: \n\n" + nodeInfo);
console.log("Visible Parents", visParents)
}
function onQueryFailed(sender, args) {
alert('Request failed. ' + args.get_message() + '\n' + args.get_stackTrace());
}
It is a known issue, it seems that SP.NavigationNode.isVisible property does not correspond to the property that indicates whether navigation node is hidden or shown.
Please refer "Hidden" property of SPNavigationNode for a details
The following function demonstrates how to retrieve hidden node Urls:
function getGlobalNavigationExcludedUrls(Success,Error)
{
var context = new SP.ClientContext.get_current();
var web = context.get_web();
var subwebs = web.get_webs();
var pagesList = web.get_lists().getByTitle("Pages");
var pageItems = pagesList.getItems(SP.CamlQuery.createAllItemsQuery());
var allProperties = web.get_allProperties();
context.load(web);
context.load(subwebs);
context.load(allProperties);
context.load(pageItems);
context.executeQueryAsync(
function() {
var excludedIds = allProperties.get_item('__GlobalNavigationExcludes').split(';');
var exludedUrls = [];
for (var i = 0; i < excludedIds.length - 1; i++ )
{
for (var j = 0; j < subwebs.get_count(); j++ )
{
var subweb = subwebs.getItemAtIndex(j);
if(subweb.get_id().toString() == excludedIds[i]){
exludedUrls.push(subweb.get_serverRelativeUrl());
break;
}
}
for (var j = 0; j < pageItems.get_count(); j++ )
{
var pageItem = pageItems.getItemAtIndex(j);
if(pageItem.get_item('UniqueId').toString() == excludedIds[i]){
exludedUrls.push(web.get_serverRelativeUrl() + pageItem.get_item('FileRef'));
break;
}
}
}
Success(exludedUrls);
},
Error
);
}
//Usage: print excluded nodes Urls
getGlobalNavigationExcludedUrls(function(excludedNodeUrls){
for (var j = 0; j < excludedNodeUrls.length; j++ )
{
console.log(excludedNodeUrls[j]);
}
},
function(sender,args){
console.log(args.get_message());
});
I need to offer a feature which allows InDesign users to select a page range in an InDesign document and create a new document out of those pages. This sounds simple, but it isn't...
I have tried many different ways of doing this but they have all failed to some degree. Some methods put all pages in a single spread (which sometimes makes InDesign crash). The best I've been able to do (see code below) still has problems at the beginning and the end (see screenshots below):
The original document:
The new document:
The question: How can I create a new document out of a subset of another document's pages (in InDesign using ExtendScript) without having the problems shown in the screenshots?
note: The behavior of the script is quite different in CS5.5 and CS6. My question concerns CS6.
The second screenshot was obtained by applying the following code to the document shown in the first screenshot:
CODE
var firstPageName = { editContents: "117" }; // This page number is actually entered by the user in an integerEditbox
var lastPageName = { editContents: "136" }; // This page number is actually entered by the user in an integerEditbox
var sourceDocument = app.activeDocument;
var destDocument = app.documents.add();
destDocument.importStyles(ImportFormat.paragraphStylesFormat, new File(sourceDocument.filePath + "/" + sourceDocument.name), GlobalClashResolutionStrategy.LOAD_ALL_WITH_OVERWRITE);
destDocument.importStyles(ImportFormat.characterStylesFormat, new File(sourceDocument.filePath + "/" + sourceDocument.name), GlobalClashResolutionStrategy.LOAD_ALL_WITH_OVERWRITE);
destDocument.viewPreferences.horizontalMeasurementUnits = sourceDocument.viewPreferences.horizontalMeasurementUnits;
destDocument.viewPreferences.verticalMeasurementUnits = sourceDocument.viewPreferences.verticalMeasurementUnits;
destDocument.documentPreferences.facingPages = sourceDocument.documentPreferences.facingPages;
destDocument.documentPreferences.pageHeight = sourceDocument.documentPreferences.pageHeight;
destDocument.documentPreferences.pageWidth = sourceDocument.documentPreferences.pageWidth;
destDocument.documentPreferences.pageSize = sourceDocument.documentPreferences.pageSize;
var sourceSpreads = sourceDocument.spreads;
var nbSourceSpreads = sourceSpreads.length;
var firstPageFound = false;
var lastPageFound = false;
var i;
var newSpreadNeeded;
var currentDestSpread;
for (i = 0; !lastPageFound, i < nbSourceSpreads; ++i) {
newSpreadNeeded = true;
var sourcePages = sourceSpreads[i].pages;
var nbSourcePages = sourcePages.length;
var j;
for (j = 0; !lastPageFound, j < nbSourcePages; ++j) {
if (sourcePages[j].name === firstPageName.editContents) {
firstPageFound = true;
destDocument.documentPreferences.startPageNumber = parseInt(firstPageName.editContents); // We want to preserve page numbers
}
if (firstPageFound) {
// Copy this page over to the new document.
var firstInNewSpread = false;
if (newSpreadNeeded) {
currentDestSpread = destDocument.spreads.add();
newSpreadNeeded = false;
firstInNewSpread = true;
}
var newPage = sourcePages[j].duplicate(LocationOptions.AT_END, currentDestSpread);
var k;
for (k = 0; k < newPage.index; ++k) {
currentDestSpread.pages[k].remove();
}
}
if (sourcePages[j].name === lastPageName.editContents) {
lastPageFound = true;
}
}
}
destDocument.spreads[0].remove();
I was hacking around and came up with this little script. Although it approaches the problem from the opposite direction, it seems to work fine here. Also, I'm still running in InDesign CS5, but maybe it will work for you. Hopefully I got the gist of your question?
This will extract pages 3 through 5 into a separate document:
var doc = app.activeDocument;
var newFilePath = doc.filePath + "/subset_" + doc.name;
var newFile = File(newFilePath); // Create a new file path
doc.saveACopy(newFile); // Save a copy of the doc
var newDoc = app.open(newFile); // Open the copy
var firstPageNum = 3; // First page number in the range
var lastPageNum = 5; // Last page number in the range
var firstPage = newDoc.pages[firstPageNum-1];
var lastPage = newDoc.pages[lastPageNum-1];
// Remove all text from the last page in the range to the end of the document
var lastPageFrames = lastPage.textFrames.everyItem().getElements();
for (var i=0; i < lastPageFrames.length; i++) {
var frame = lastPageFrames[i];
var parentStory = frame.parentStory;
var lastFrameInsert = frame.insertionPoints.lastItem();
var lastStoryInsert = parentStory.insertionPoints.lastItem();
var textAfter = parentStory.insertionPoints.itemByRange(lastFrameInsert,lastStoryInsert);
textAfter.remove();
};
// Remove all text from the beginning of the document to the first page in the range
var firstPageFrames = firstPage.textFrames.everyItem().getElements();
for (var i=0; i < firstPageFrames.length; i++) {
var frame = firstPageFrames[i];
var parentStory = frame.parentStory;
var firstFrameInsert = frame.insertionPoints.firstItem();
var textBefore = parentStory.insertionPoints.itemByRange(0,firstFrameInsert.index);
textBefore.remove();
};
// Remove the pages that aren't in the range
var allPages = newDoc.pages.everyItem().getElements();
for (var i=0; i < allPages.length; i++) {
var page = allPages[i];
if (i < firstPageNum || i > lastPageNum) {
page.remove();
}
};
I'm trying to create a simple chrome extension using the following google RSS reader sample,
http://code.google.com/chrome/extensions/samples.html#597015d3bcce3da693b02314afd607bec4f55291
I can add links in the pop-up window that open tabs, but not from the feeds themselves.
Looping through the items in the feed, grabbing title tags and link tags, I want the title to link the the appropriate sites
var entries = doc.getElementsByTagName('item');
var count = Math.min(entries.length, maxFeedItems);
for (var i = 0; i < count; i++) {
item = entries.item(i);
// Grab the title for the feed item.
var itemTitle = item.getElementsByTagName('title')[0];
if (itemTitle) {
itemTitle = itemTitle.textContent;
} else {
itemTitle = "Unknown title";
}
// Grab the link for this feed item
var itemLink = item.getElementsByTagName('link')[0];
if (itemLink) {
itemLink = itemLink.textContent;
} else {
itemLink = "Unknown link";
}
var title = document.createElement("a");
title.className = "item_title";
title.innerText = itemTitle; //display title in iframe
title.addEventListener("click", titleLink); // should open link when clicking on title, but does not.
}
// -------------------------------------------------------------------
// Show |url| in a new tab.
function showUrl(url) {
// Only allow http and https URLs.
if (url.indexOf("http:") != 0 && url.indexOf("https:") != 0) {
return;
}
chrome.tabs.create({url: url});
}
function moreStories(event) {
showUrl(moreStoriesUrl);
}
function titleLink(event) {
showUrl(itemLink);
}
Any thoughts on why this is not working.
If I replace title.addEventListener("click", titleLink); with title.addEventListener("click", moreStories); each title will link to moreStories, I cannot get each title to link to itemLink.
Thanks
Its a bit hard to answer your question without the whole code, but Ill give it a shot ;)
First up, titleLink() isnt going to work because itemLink isnt known. When you create title (the link) you should of attached it to that...say title.href=itemLink then in tiltleLinks you could access that href with showUrl(event.currentTarget.href)
Also did you fix the error in that example?...if not then change frameLoaded to....
function frameLoaded() {
var links = document.getElementsByTagName("A");
for (i = 0; i < links.length; i++) {
var clssName = links[i].className;
if (clssName != "item_title" && clssName != "open_box") {
links[i].addEventListener("click", showStory);
}
}
window.addEventListener("message", messageHandler);
}
If you still have probs could you attach the whole code so I can see what your doing and Ill give you a hand.
Thank you very much for your help.
code title.href=itemLink and code showUrl(event.currentTarget.href) was exactly what I needed.
For completeness, here is the full code,
<script id="iframe_script">
function reportHeight() {
var msg = JSON.stringify({type:"size", size:document.body.offsetHeight});
parent.postMessage(msg, "*");
}
function frameLoaded() {
var links = document.getElementsByTagName("A");
for (i = 0; i < links.length; i++) {
var class = links[i].className;
if (class != "item_title" && class != "open_box") {
links[i].addEventListener("click", showStory);
}
}
window.addEventListener("message", messageHandler);
}
function showStory(event) {
var href = event.currentTarget.href;
parent.postMessage(JSON.stringify({type:"show", url:href}), "*");
event.preventDefault();
}
function messageHandler(event) {
reportHeight();
}
</script>
<script>
// Feed URL.
var feedUrl = 'http://localhost/newsfeed.xml';
// The XMLHttpRequest object that tries to load and parse the feed.
var req;
function main() {
req = new XMLHttpRequest();
req.onload = handleResponse;
req.onerror = handleError;
req.open("GET", feedUrl, true);
req.send(null);
}
// Handles feed parsing errors.
function handleFeedParsingFailed(error) {
var feed = document.getElementById("feed");
feed.className = "error";
feed.innerText = "Error: " + error;
}
// Handles errors during the XMLHttpRequest.
function handleError() {
handleFeedParsingFailed('Failed to fetch RSS feed.');
}
// Handles parsing the feed data we got back from XMLHttpRequest.
function handleResponse() {
var doc = req.responseXML;
if (!doc) {
handleFeedParsingFailed("Not a valid feed.");
return;
}
buildPreview(doc);
}
// The maximum number of feed items to show in the preview.
var maxFeedItems = 10;
// Where the more stories link should navigate to.
var moreStoriesUrl;
function buildPreview(doc) {
// Get the link to the feed source.
var link = doc.getElementsByTagName("link");
var parentTag = link[0].parentNode.tagName;
if (parentTag != "item" && parentTag != "entry") {
moreStoriesUrl = link[0].textContent;
}
// Setup the title image.
var images = doc.getElementsByTagName("image");
var titleImg;
if (images.length != 0) {
var urls = images[0].getElementsByTagName("url");
if (urls.length != 0) {
titleImg = urls[0].textContent;
}
}
var img = document.getElementById("title");
// Listen for mouse and key events
if (titleImg) {
img.src = titleImg;
if (moreStoriesUrl) {
document.getElementById("title_a").addEventListener("click",moreStories);
document.getElementById("title_a").addEventListener("keydown",
function(event) {
if (event.keyCode == 13) {
moreStories(event);
}});
}
} else {
img.style.display = "none";
}
// Construct the iframe's HTML.
var iframe_src = "<!doctype html><html><head><script>" +
document.getElementById("iframe_script").textContent + "<" +
"/script></head><body onload='frameLoaded();' " +
"style='padding:0px;margin:0px;'>";
var feed = document.getElementById("feed");
// Set ARIA role indicating the feed element has a tree structure
feed.setAttribute("role", "tree");
var entries = doc.getElementsByTagName('item');
var count = Math.min(entries.length, maxFeedItems);
for (var i = 0; i < count; i++) {
item = entries.item(i);
// Grab the title for the feed item.
var itemTitle = item.getElementsByTagName('title')[0];
if (itemTitle) {
itemTitle = itemTitle.textContent;
} else {
itemTitle = "Unknown title";
}
// Grab the link for the feed item.
var itemLink = item.getElementsByTagName('link')[0];
if (itemLink) {
itemLink = itemLink.textContent;
} else {
itemLink = "Unknown link";
}
var item = document.createElement("div");
var title = document.createElement("a");
title.innerText = itemTitle; //display title in iframe
title.href=itemLink;
title.addEventListener("click", titleLink);
item.appendChild(title);
feed.appendChild(item);
}
if (moreStoriesUrl) {
var more = document.createElement("a");
more.className = "more";
more.innerText = "***Site Main Page*** \u00BB";
more.tabIndex = 0;
more.addEventListener("click", moreStories);
more.addEventListener("keydown", function(event) {
if (event.keyCode == 13) {
moreStories(event);
}});
feed.appendChild(more);
}
}
// -------------------------------------------------------------------
// Show |url| in a new tab.
function showUrl(url) {
// Only allow http and https URLs.
if (url.indexOf("http:") != 0 && url.indexOf("https:") != 0) {
return;
}
chrome.tabs.create({url: url});
}
// -------------------------------------------------------------------
function moreStories(event) {
showUrl(moreStoriesUrl);
}
function titleLink(event) {
showUrl(event.currentTarget.href);
}
function keyHandlerShowDesc(event) {
// Display content under heading when spacebar or right-arrow pressed
// Hide content when spacebar pressed again or left-arrow pressed
// Move to next heading when down-arrow pressed
// Move to previous heading when up-arrow pressed
if (event.keyCode == 32) {
showDesc(event);
} else if ((this.parentNode.className == "item opened") &&
(event.keyCode == 37)) {
showDesc(event);
} else if ((this.parentNode.className == "item") && (event.keyCode == 39)) {
showDesc(event);
} else if (event.keyCode == 40) {
if (this.parentNode.nextSibling) {
this.parentNode.nextSibling.children[1].focus();
}
} else if (event.keyCode == 38) {
if (this.parentNode.previousSibling) {
this.parentNode.previousSibling.children[1].focus();
}
}
}
function showDesc(event) {
var item = event.currentTarget.parentNode;
var items = document.getElementsByClassName("item");
for (var i = 0; i < items.length; i++) {
var iframe = items[i].getElementsByClassName("item_desc")[0];
if (items[i] == item && items[i].className == "item") {
items[i].className = "item opened";
iframe.contentWindow.postMessage("reportHeight", "*");
// Set the ARIA state indicating the tree item is currently expanded.
items[i].getElementsByClassName("item_title")[0].
setAttribute("aria-expanded", "true");
iframe.tabIndex = 0;
} else {
items[i].className = "item";
iframe.style.height = "0px";
// Set the ARIA state indicating the tree item is currently collapsed.
items[i].getElementsByClassName("item_title")[0].
setAttribute("aria-expanded", "false");
iframe.tabIndex = -1;
}
}
}
function iframeMessageHandler(e) {
// Only listen to messages from one of our own iframes.
var iframes = document.getElementsByTagName("IFRAME");
for (var i = 0; i < iframes.length; i++) {
if (iframes[i].contentWindow == e.source) {
var msg = JSON.parse(e.data);
if (msg) {
if (msg.type == "size") {
iframes[i].style.height = msg.size + "px";
}
else if (msg.type == "show") {
var url = msg.url;
if (url.indexOf("http://localhost/index.html") == 0) {
// If the URL is a redirect URL, strip of the destination and go to
// that directly. This is necessary because the Google news
// redirector blocks use of the redirects in this case.
var index = url.indexOf("&url=");
if (index >= 0) {
url = url.substring(index + 5);
index = url.indexOf("&");
if (index >= 0)
url = url.substring(0, index);
}
}
showUrl(url);
}
}
return;
}
}
}
window.addEventListener("message", iframeMessageHandler);
</script>
Thanks again for the help.
-Mike