Use XPath to find the elements of interest

[GM_direct_download_links.git] / direct_download_links.user.js

diff --git a/direct_download_links.user.js b/direct_download_links.user.js
index 89fa057..9344012 100644 (file)
--- a/direct_download_links.user.js
+++ b/direct_download_links.user.js
@@ -28,6 +28,7 @@
 // @include        http://trovacinema.repubblica.it/*
 // @include        http://www.kataweb.it/tvzap/*
 // @include        http://www.rai.tv/*
 // @include        http://trovacinema.repubblica.it/*
 // @include        http://www.kataweb.it/tvzap/*
 // @include        http://www.rai.tv/*

+// @include        http://soundcloud.com/*

 // ==/UserScript==
 //
 
 // ==/UserScript==
 //
 


@@ -36,18 +37,19 @@
  *  - find a way to use the same string as in the @include lines to match the
  *    current window.location. Look for something like GM_testUrl() which builds
  *    the regexp starting from a glob line.
  *  - find a way to use the same string as in the @include lines to match the
  *    current window.location. Look for something like GM_testUrl() which builds
  *    the regexp starting from a glob line.

- *  - use xpath instead of regexp like in http://a32.me/2009/11/greasemonkey/

  *  - use jquery, like shown in http://a32.me/2009/11/greasemonkey/
  *  - use jquery, like shown in http://a32.me/2009/11/greasemonkey/

+ *  - Support the "download" attribute for anchors:
+ *    http://www.whatwg.org/specs/web-apps/current-work/multipage/links.html#downloading-resources

  */
 
 /* Fields supported by the "site" object.
  *
  * Manadatory fields:
  */
 
 /* Fields supported by the "site" object.
  *
  * Manadatory fields:

- *   pageURL: the URL of the page we are modifying
- *   urlContainer: the element containing the URL to link
+ *   locationRegExp: the regexp describing the URL of the page we are modifying
+ *   urlContainerXPath: the XPath of the element containing the URL to link

  *   urlRegexp: the regular expression for finding the URL, the first
  *              sub-pattern is taken as the URL
  *   urlRegexp: the regular expression for finding the URL, the first
  *              sub-pattern is taken as the URL

- *   linkDest: the element where to place the Direct Download link
+ *   linkDestXPath: the XPath of the element where to place the Direct Download link

  *
  *
  * Optional fields:
  *
  *
  * Optional fields:


@@ -75,27 +77,28 @@
 var supported_sites = [
   {
     locationRegexp: /^http:\/\/video\.repubblica\.it\/.*$/,
 var supported_sites = [
   {
     locationRegexp: /^http:\/\/video\.repubblica\.it\/.*$/,

-    urlContainer: 'contA',
+    urlContainerXPath: '//div[@id="contA"]',

     urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
     urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,

-    linkDest: 'contA',
+    linkDestXPath: '//div[@id="contA"]',

   },
   {
     locationRegexp: /^http:\/\/tv\.repubblica\.it\/.*$/,
   },
   {
     locationRegexp: /^http:\/\/tv\.repubblica\.it\/.*$/,

-    urlContainer: 'boxPlayer',
+    urlContainerXPath: '//div[@id="boxPlayer"]',

     urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
     linkDest: 'box_embed',
     urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
     linkDest: 'box_embed',

+    linkDestXPath: '//div[@id="box_embed"]',

   },
   {
     locationRegexp: /^http:\/\/trovacinema\.repubblica\.it\/.*$/,
   },
   {
     locationRegexp: /^http:\/\/trovacinema\.repubblica\.it\/.*$/,

-    urlContainer: 'col-center',
+    urlContainerXPath: '//div[@id="col-center"]',

     urlRegexp: /'flvUrl', '((http|mms):\/\/[^']*)'/,
     urlRegexp: /'flvUrl', '((http|mms):\/\/[^']*)'/,

-    linkDest: 'col-center',
+    linkDestXPath: '//div[@id="col-center"]',

   },
   {
     locationRegexp: /^http:\/\/www\.kataweb\.it\/tvzap\/.*$/,
   },
   {
     locationRegexp: /^http:\/\/www\.kataweb\.it\/tvzap\/.*$/,

-    urlContainer: 'tvzap_video',
+    urlContainerXPath: '//div[@id="tvzap_video"]',

     urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
     urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,

-    linkDest: 'playerCont',
+    linkDestXPath: '//div[@id="playerCont"]',

   },
   {
     locationRegexp: /^http:\/\/www\.rai\.tv\/.*$/,
   },
   {
     locationRegexp: /^http:\/\/www\.rai\.tv\/.*$/,


@@ -104,11 +107,17 @@ var supported_sites = [
           return true;
         };
     },
           return true;
         };
     },

-    urlContainer: 'Player',
+    urlContainerXPath: '//div[@id="Player"]',

     urlRegexp: /mediaUri=(http:\/\/[^,]*)/,
     onEvent: { evt: 'DOMNodeInserted', targetElement: 'object' },
     processURL: _rai_get_actual_url,
     urlRegexp: /mediaUri=(http:\/\/[^,]*)/,
     onEvent: { evt: 'DOMNodeInserted', targetElement: 'object' },
     processURL: _rai_get_actual_url,

-    linkDest: 'Player',
+    linkDestXPath: '//div[@id="Player"]',
+  },
+  {
+    locationRegexp: /^http:\/\/soundcloud.com\/.*$/,
+    urlContainerXPath: '//div[@id="main-content-inner"]',
+    urlRegexp: /"streamUrl":"([^"]*)"/,
+    linkDestXPath: '//div[@id="main-content-inner"]',

   },
 ];
 
   },
 ];
 


@@ -125,6 +134,10 @@ for (i = 0; i < supported_sites.length; i++) {
   }
 }
 
   }
 }
 

+function getElementByXPath(query, root) {
+  return document.evaluate(query, root || document, null, XPathResult.ANY_UNORDERED_NODE_TYPE, null).singleNodeValue;
+}
+

 /**
  * Add a Direct Download link on the page for the specified URL
  *
 /**
  * Add a Direct Download link on the page for the specified URL
  *


@@ -133,9 +146,9 @@ for (i = 0; i < supported_sites.length; i++) {
  * @return: null on error, true on success
  */
 function direct_download_link_add(pageURL, site) {
  * @return: null on error, true on success
  */
 function direct_download_link_add(pageURL, site) {

-  var element = document.getElementById(site.urlContainer);
+  var element = getElementByXPath(site.urlContainerXPath);

   if (!element) {
   if (!element) {

-    DDL_log('DirectDL (' + site.pageURL  + '): Cannot find the element ' + site.urlContainer + ' containing the URL.');
+    DDL_log('DirectDL (' + site.pageURL  + '): Cannot find the element ' + site.urlContainerXPath + ' containing the URL.');

     return null;
   }
 
     return null;
   }
 


@@ -192,7 +205,7 @@ function _add_link(e) {
   var site = e.site;
   var URL = e.URL;;
 
   var site = e.site;
   var URL = e.URL;;
 

-  var destination = document.getElementById(site.linkDest);
+  var destination = getElementByXPath(site.linkDestXPath);

   if (!destination) {
     DDL_log('DirectDl (' + site.pageURL + '): Cannot add the direct download link.');
     return;
   if (!destination) {
     DDL_log('DirectDl (' + site.pageURL + '): Cannot add the direct download link.');
     return;