☰

nT-Exporter

Export content URLs from newTumbl blog

  1. // ==UserScript==
  2. // @name         nT-Exporter
  3. // @namespace    https://www.newtumbl.com/
  4. // @version      1.3
  5. // @description  Export content URLs from newTumbl blog
  6. // @author       ceodoe
  7. // @license      GPLv3
  8. // @match        https://*.newtumbl.com/
  9. // @match        https://newtumbl.com/*
  10. // @icon         https://www.google.com/s2/favicons?sz=64&domain=newtumbl.com
  11. // @grant        none
  12. // @run-at       document-end
  13. // ==/UserScript==
  14.  
  15. window.setTimeout(function() {
  16.     let nav = document.querySelector("div.nav > ul");
  17.     let dumpBtn = document.createElement("li");
  18.     dumpBtn.innerText = "Export";
  19.  
  20.     dumpBtn.onclick = function() {
  21.         let urlArray = [];
  22.         let outputString = "";
  23.  
  24.         let imgs = document.querySelectorAll("img");
  25.         let mediaRegex = new RegExp(/^https:\/\/dn[0-9]\.newtumbl\.com\/img\/[0-9]+\/[0-9]+\/[0-9]\/[0-9]+\/nT_[A-Za-z0-9_]+\.jpg|gif|mp4$/);
  26.         let thumbnailRegex = new RegExp(/(_150|_300|_600)\.(jpg|gif|mp4)$/);
  27.         let avatarRegex = new RegExp(/^https:\/\/dn[0-9]\.newtumbl\.com\/img\/[0-9]+\/0\/0\//);
  28.  
  29.         for(let i = 0; i < imgs.length; i++) {
  30.             // Ignore avatars
  31.             if(!avatarRegex.test(imgs[i].src)) {
  32.                 if(mediaRegex.test(imgs[i].src)) {
  33.                     // Replace thumbnails with full version of the image
  34.                     if(thumbnailRegex.test(imgs[i].src)) {
  35.                         urlArray.push(imgs[i].src.replace(thumbnailRegex, ".$2"));
  36.                     } else {
  37.                         urlArray.push(imgs[i].src);
  38.                     }
  39.                 }
  40.             }
  41.         }
  42.  
  43.         let vids = document.querySelectorAll("video > source");
  44.         for(let i = 0; i < vids.length; i++) {
  45.             if(mediaRegex.test(vids[i].src)) {
  46.                 // If video hasn't been played yet, there is a .jpg video thumbnail with the same filename
  47.                 // loaded on top of it, which will have been included in the imgs loop, so we remove it
  48.  
  49.                 let vidThumb = vids[i].src.slice(0, -3) + "jpg";
  50.                 if(urlArray.includes(vidThumb)) {
  51.                     urlArray.splice(urlArray.indexOf(vidThumb), 1);
  52.                 }
  53.                 
  54.                 urlArray.push(vids[i].src);
  55.             }
  56.         }
  57.  
  58.         let urlSet = [...new Set(urlArray)];
  59.  
  60.         if(urlSet.length > 0) {
  61.             for(let i = 0; i < urlSet.length; i++) {
  62.                 outputString += urlSet[i] + "\n";
  63.             }
  64.     
  65.             let filePrefix = "newTumbl";
  66.     
  67.             // Are we on....
  68.             if(new RegExp(/^https:\/\/.+\.newtumbl\.com/).test(window.location.href)) {
  69.                 // A subdomain? Put blog url in prefix
  70.                 filePrefix = window.location.host.split(".")[0];
  71.             } else if(new RegExp(/^https:\/\/newtumbl\.com\/search/).test(window.location.href)) {
  72.                 // On the search page? Put search term in prefix
  73.                 filePrefix = decodeURIComponent(window.location.hash.substring(3)).replace(" ", "-");
  74.             } else if(new RegExp(/^https:\/\/newtumbl\.com\/blog\//).test(window.location.href)) {
  75.                 // On a /blog/ page? Put drafts or queue in prefix
  76.                 if(window.location.href.includes("/drafts")) {
  77.                     filePrefix = "drafts";
  78.                 } else if(window.location.href.includes("/queue")) {
  79.                     filePrefix = "queue";
  80.                 }
  81.             } else if(new RegExp(/^https:\/\/newtumbl\.com\/feed/).test(window.location.href)) {
  82.                 // On the feed? Put feed in prefix
  83.                 filePrefix = "feed";
  84.             } else if(new RegExp(/^https:\/\/newtumbl\.com\/dashboard/).test(window.location.href)) {
  85.                 // On the dashboard? Put dashboard in prefix
  86.                 filePrefix = "dashboard";
  87.             }
  88.  
  89.             let element = document.createElement('a');
  90.             element.setAttribute("href", "data:text/plain;charset=utf-8," + encodeURIComponent(outputString));
  91.             element.setAttribute("download", `${filePrefix}_${GM_info.script.name}-${Date.now()}.txt`);
  92.             element.style.display = "none";
  93.             document.body.appendChild(element);
  94.             element.click();
  95.             document.body.removeChild(element);
  96.  
  97.             alert("Success! " + GM_info.script.name + " found " + urlSet.length + " unique media elements on this page, and saved their URLs to a text file. In order to download the actual media files, feed the downloaded text file into your favourite downloader, such as wget or JDownloader 2.");
  98.         } else {
  99.             alert("No posts found on the current page.");
  100.         }
  101.     };
  102.  
  103.     nav.append(dumpBtn);
  104. }, 1500);