<->archive.is

by noromanba 2015-05-26 [2015/05/26 07:14:56]

come and go archive.is w/ list and detail page

@@ -1,5 +1,5 @@
 /*
- * @title <->archive.past
+ * @title <->archive.is
  * @description come and go archive.is w/ list and detail page
  * @include http://*
  * @include https://*
@@ -8,40 +8,45 @@
  * @javascript_url
  */
 
-// OBSOLETE .today? turn back .is
-// 〜2014-04-15     http://archive.is
-// 2014-04-15〜     http://archive.today
-// 2015-04-23?      http://archive.is
-//  2015-04-20 ".today" but 2015-04-23, 302 redirect to ".is"
-//  - http://web.archive.org/web/20150420033512/https://archive.today/
-//  - http://web.archive.org/web/20150423204200/http://archive.today/
-//   - http://web.archive.org/web/*/archive.today
+// OBSOLETE .today, turn back .is
+// ~2014-04-15?      http://archive.is
+//  2014-04-15?~     http://archive.today
+//  2015-04-23?      http://archive.is
+//  2015-04-20 ".today" -> 2015-04-23, 302 redirect to ".is"
+//  - http://web.archive.org/web/*/archive.today
+//   - http://web.archive.org/web/20150420033512/https://archive.today/
+//   - http://web.archive.org/web/20150423204200/http://archive.today/
 
 // c.f.
 // https://archive.is/ (Bookmarklet for immediately save)
 // https://archive.is/faq.html
 (function () {
-    if (/archive\.is/.test(location.hostname) && location.pathname) {
+    var url;
+
+    if (/archive\.is$/.test(location.hostname)) {
         var saved = document.querySelector('input[name="q"][value]');
         if (!saved || !saved.value) return;
 
         // TBD regexp capture
-        var url = saved.value;
+        url = saved.value;
         url = url.replace(/^\*\./,'').replace(/\*$/, ''); // remove wildcard
 
         location.href = url.indexOf('http') > -1 ?
-        //*
             url.slice(url.lastIndexOf('http')) : // remove some 'http://'; e.g. wayback, H::B et. al
-        /*/
-            url :
-        //*/
             'http://' + url;
     } else {
-        // TODO canonical TBD remove protocol
-        location.href = 'https://archive.is/' + location.href;
+        // canonical
+        // http://let.hatelabo.jp/noromanba/let/hLHVzOTQjfYH
+        // https://gist.github.com/noromanba/d730ccf3ae5e6916cd60
+        url = (document.head.querySelector('meta[property="og:url"][content]') || {}).content ||
+            (document.head.querySelector('link[rel="canonical"][href]') || {}).href ||
+            location.href;
+
+        location.href = 'http://archive.is/' + url;
     }
 })();
 
+// DBG
 // archive.is are awesome, but markup awful
 //
 // - https://archive.is/

• /*
   * @title <->archive.is
   * @description come and go archive.is w/ list and detail page
   * @include http://*
   * @include https://*
   * @contributor noromanba
   * @license MIT License http://opensource.org/licenses/MIT
   * @javascript_url
   */
  
  // OBSOLETE .today, turn back .is
  // ~2014-04-15?      http://archive.is
  //  2014-04-15?~     http://archive.today
  //  2015-04-23?      http://archive.is
  //  2015-04-20 ".today" -> 2015-04-23, 302 redirect to ".is"
  //  - http://web.archive.org/web/*/archive.today
  //   - http://web.archive.org/web/20150420033512/https://archive.today/
  //   - http://web.archive.org/web/20150423204200/http://archive.today/
  
  // c.f.
  // https://archive.is/ (Bookmarklet for immediately save)
  // https://archive.is/faq.html
  (function () {
      var url;
  
      if (/archive\.is$/.test(location.hostname)) {
          var saved = document.querySelector('input[name="q"][value]');
          if (!saved || !saved.value) return;
  
          // TBD regexp capture
          url = saved.value;
          url = url.replace(/^\*\./,'').replace(/\*$/, ''); // remove wildcard
  
          location.href = url.indexOf('http') > -1 ?
              url.slice(url.lastIndexOf('http')) : // remove some 'http://'; e.g. wayback, H::B et. al
              'http://' + url;
      } else {
          // canonical
          // http://let.hatelabo.jp/noromanba/let/hLHVzOTQjfYH
          // https://gist.github.com/noromanba/d730ccf3ae5e6916cd60
          url = (document.head.querySelector('meta[property="og:url"][content]') || {}).content ||
              (document.head.querySelector('link[rel="canonical"][href]') || {}).href ||
              location.href;
  
          location.href = 'http://archive.is/' + url;
      }
  })();
  
  // DBG
  // archive.is are awesome, but markup awful
  //
  // - https://archive.is/
  //  - https://archive.is/www.google.co.jp/ (list page)
  //   - 1 visible input
  //    - #q name="q"
  //  - https://archive.is/MjjoE (detail page, include wayback)
  //   - 4 visible inputs, div#header
  //    - [ ] Saved from:      submit tabindex"=-1" (wayback url)
  //     - http://web.archive.org/web/20040831080059/http://www.google.co.jp/
  //    - [ ] Redirected from: name="q" readonly (wayback url)
  //    - [ ] Via:             readonly (via url)
  //    - [x] Original:        readonly (saved url)
  // - 5 input patterns, e.g. Google Japan
  //  - http://google.co.jp
  //  - https://google.co.jp
  //  - google.co.jp
  //  - http://www.google.co.jp/*
  //  - *.google.co.jp
  //
  // ':nth-last-of-type(1)', ':last-of-type' return first element (with attr sel)
  // WTH, WTF plz add #id or .class or data-*, I WANT to get original url EASILY
  
  

• Permalink RAW Packed Userscript LOADER Metadata ?

  Permalink

  このページへの個別リンクです。

  RAW

  書かれたコードへの直接のリンクです。

  Packed

  文字列が圧縮された書かれたコードへのリンクです。

  Userscript

  Greasemonkey 等で利用する場合の .user.js へのリンクです。

  Loader

  @require やソースコードが長い場合に多段ロードする Loader コミのコードへのリンクです。

  Metadata

  コード中にコメントで @xxx と書かれたメタデータの JSON です。