1 // direct_download_links - Add direct download links
4 // Copyright (C) 2011,2012 Antonio Ospite <ospite@studenti.unina.it>
5 // Released under the GPL license
6 // http://www.gnu.org/copyleft/gpl.html
8 // --------------------------------------------------------------------
10 // This is a Greasemonkey user script.
12 // To install, you need Greasemonkey: https://addons.mozilla.org/en-US/firefox/addon/748
13 // Then restart Firefox and revisit this script.
14 // Under Tools, there will be a new menu item to "Install User Script".
15 // Accept the default configuration and install.
17 // To uninstall, go to Tools/Manage User Scripts,
18 // select "Direct Download Links", and click Uninstall.
20 // --------------------------------------------------------------------
23 // @name Direct Download Links
24 // @namespace http://git.ao2.it/GM_direct_download_links.git
25 // @description Add direct download links
27 // @grant GM_xmlhttpRequest
28 // @include http://video.repubblica.it/*
29 // @include http://tv.repubblica.it/*
30 // @include http://trovacinema.repubblica.it/*
31 // @include http://www.kataweb.it/tvzap/*
32 // @include http://www.rai.tv/*
33 // @include http://soundcloud.com/*
34 // @include http://www.telecinco.es/*
35 // @include http://slideshare.net/*
36 // @include http://www.slideshare.net/*
42 * - find a way to use the same string as in the @include lines to match the
43 * current window.location. Look for something like GM_testUrl() which builds
44 * the regexp starting from a glob line.
45 * - use jquery, like shown in http://a32.me/2009/11/greasemonkey/
46 * - Support the "download" attribute for anchors:
47 * http://www.whatwg.org/specs/web-apps/current-work/multipage/links.html#downloading-resources
50 /* Fields supported by the "site" object.
53 * locationRegExp: the regexp describing the URL of the page we are modifying
54 * urlContainerXPath: the XPath of the element containing the URL to link
55 * urlRegexp: the regular expression for finding the URL, the first
56 * sub-pattern is taken as the URL
57 * linkDestXPath: the XPath of the element where to place the Direct Download link
62 * initCommand: a function called before the regExp is matched, this can
63 * be useful in cases when some action needs to be done in
64 * order to make the element containing the regExp be actually
65 * rendered. It must accept a 'site' parameter.
67 * onEvent: used to delay the urlRegexp matching to a certain event like
68 * 'DOMNodeInserted' useful when the URL is added by some javascript
69 * library. It has two fields:
71 * evt: the event we want to wait for (e.g. 'DOMNodeInserted')
73 * targetElement: the element in the event handler we want the
74 * urlRegexp is performed on.
76 * processURL: a function to process the URL before adding the Direct
77 * Downdload Link to the page, it must accept a 'site' and a
78 * 'URL' parameters and dispatch the UrlFetched to pass the
79 * modified URL to _add_link().
82 var supported_sites = [
84 locationRegexp: /^http:\/\/video\.repubblica\.it\/.*$/,
85 urlContainerXPath: '//div[@id="contA"]',
86 urlRegexp: /[^\/]addParam\('format', '[^']*', '((http|mms):\/\/[^']*)'/,
87 linkDestXPath: '//div[@id="contA"]',
90 locationRegexp: /^http:\/\/tv\.repubblica\.it\/.*$/,
91 urlContainerXPath: '//div[@id="boxPlayer"]',
92 urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
93 linkDest: 'box_embed',
94 linkDestXPath: '//div[@id="box_embed"]',
97 locationRegexp: /^http:\/\/trovacinema\.repubblica\.it\/.*$/,
98 urlContainerXPath: '//div[@id="col-center"]',
99 urlRegexp: /'flvUrl', '((http|mms):\/\/[^']*)'/,
100 linkDestXPath: '//div[@id="col-center"]',
103 locationRegexp: /^http:\/\/www\.kataweb\.it\/tvzap\/.*$/,
104 urlContainerXPath: '//div[@id="contAB"]',
105 urlRegexp: /[^\/]addParam\('pcUrl', '((http|mms):\/\/[^']*)'/,
106 linkDestXPath: '//div[@id="contAB"]',
109 locationRegexp: /^http:\/\/www\.rai\.tv\/.*$/,
110 initCommand: function(site) {
111 unsafeWindow.Silverlight.isInstalled = function(version) {
115 urlContainerXPath: '//div[@id="silverlightControlHost" or @id="SilverlightPlayer"]',
116 urlRegexp: /mediaUri=(http:\/\/[^,"]*)/,
117 onEvent: { evt: 'DOMNodeInserted', targetElement: 'object' },
118 processURL: _rai_get_actual_url,
119 linkDestXPath: '//div[@id="silverlightControlHost" or @id="SilverlightPlayer"]',
122 locationRegexp: /^http:\/\/soundcloud.com\/.*$/,
123 urlContainerXPath: '//div[@id="main-content-inner"]',
124 urlRegexp: /"streamUrl":"([^"]*)"/,
125 linkDestXPath: '//div[@id="main-content-inner"]',
128 locationRegexp: /^http:\/\/www\.telecinco.es\/.*$/,
129 urlContainerXPath: '//video[@class="video-js"]',
130 urlRegexp: /src="([^"]*)"/,
131 linkDestXPath: '//div[@class="pg-bd"]',
134 locationRegexp: /^http:\/\/(www\.|)slideshare.net\/.*$/,
135 urlContainerXPath: '//script[@id="page-json"]',
136 urlRegexp: /"ppt_location":"([^"]*)"/,
137 processURL: function(site, object_id) {
138 var URL = 'http://s3.amazonaws.com/slideshare/' + object_id + '.xml';
139 var evt = document.createEvent('Event');
140 evt.initEvent('UrlFetched', true, true);
143 document.dispatchEvent(evt);
146 linkDestXPath: '//div[@class="playerWrapper"]',
150 /* Apply different rules to different sites */
151 for (i = 0; i < supported_sites.length; i++) {
152 var site = supported_sites[i];
154 var result = window.location.href.match(site.locationRegexp);
156 if (site.initCommand) {
157 site.initCommand(site);
159 direct_download_link_add(window.location.href, site);
163 function getElementByXPath(query, root) {
164 return document.evaluate(query, root || document, null, XPathResult.ANY_UNORDERED_NODE_TYPE, null).singleNodeValue;
167 /* from http://stackoverflow.com/questions/1912501 */
168 function htmlDecode(input){
169 var e = document.createElement('div');
171 return e.childNodes.length === 0 ? "" : e.childNodes[0].nodeValue;
175 * Add a Direct Download link on the page for the specified URL
177 * @param: a 'site' object described above.
179 * @return: null on error, true on success
181 function direct_download_link_add(pageURL, site) {
182 site.pageURL = pageURL;
183 var element = getElementByXPath(site.urlContainerXPath);
185 DDL_log('DirectDL (' + site.pageURL + '): Cannot find the element ' + site.urlContainerXPath + ' containing the URL.');
189 document.addEventListener('UrlFetched', _add_link, true);
191 // This is used for sites adding the URL to the DOM after DOMContentLoaded,
192 // for example by some javascript library (like Silverlight.js on rai.tv).
194 element.addEventListener(site.onEvent.evt, function(e) {
195 if (site.onEvent.targetElement &&
196 e.target.tagName.toLowerCase() != site.onEvent.targetElement) {
197 DDL_log('DirectDL (' + site.pageURL + '): skipping element ' + e.target.tagName);
200 _get_URL(site, element);
205 _get_URL(site, element);
208 function _get_URL(site, element) {
209 var content = element.innerHTML;
211 DDL_log('DirectDL (' + site.pageURL + '): content is null, cannot find URL.');
215 var matches = content.match(site.urlRegexp);
216 if (!matches || matches.length < 2 || !matches[1]) {
217 DDL_log('DirectDL (' + site.pageURL + '): URL not found, check the urlRegexp');
220 var URL = matches[1];
222 DDL_log('DirectDL (' + site.pageURL + '): cannot get the URL.');
226 if (site.processURL) {
227 site.processURL(site, URL);
231 var evt = document.createEvent('Event');
232 evt.initEvent('UrlFetched', true, true);
234 evt.URL = htmlDecode(URL);
235 document.dispatchEvent(evt);
238 function _add_link(e) {
242 var destination = getElementByXPath(site.linkDestXPath);
244 DDL_log('DirectDl (' + site.pageURL + '): Cannot add the direct download link.');
248 // Check if we added the link already, if so just update the href attribute.
249 // This is useful when _get_URL() is called on async events.
250 var download_link = document.getElementById('GM_direct_downaload_link');
252 download_link.setAttribute('href', URL);
254 download_link = document.createElement('a');
255 download_link.textContent = 'Direct Link';
256 download_link.setAttribute('id', 'GM_direct_downaload_link');
257 download_link.setAttribute('href', URL);
258 var style = 'background-color: white; color: blue;';
259 style += ' border: 2px solid red;'
260 style += ' float: right; font-size: large;';
261 style += ' padding: .5em; margin: 1em;'
262 style += ' position: relative; z-index: 1000;'
263 download_link.setAttribute('style', style);
265 destination.insertBefore(download_link, destination.firstChild);
269 function DDL_log(message) {
278 function _rai_get_actual_url(site, URL) {
280 // SmoothStreaming manifest files get added without processing, for now:
281 if (URL.match(/.*\.csm$/)) {
282 var evt = document.createEvent('Event');
283 evt.initEvent('UrlFetched', true, true);
286 document.dispatchEvent(evt);
290 // http://www.neaveru.com/wordpress/index.php/2008/05/09/greasemonkey-bug-domnodeinserted-event-doesnt-allow-gm_xmlhttprequest/
291 setTimeout( function() {
294 // XXX A custom header. This is the "clever" trick Rai uses to ensure
295 // the content is accessed by www.rai.tv only...
296 headers: {'viaurl': 'www.rai.tv'},
298 onload: function(response) {
299 text = response.responseText;
300 text = text.replace(/&/g, '&')
301 parser = new DOMParser();
302 xmlDoc = parser.parseFromString(text, "text/xml");
305 elems = xmlDoc.getElementsByTagName('REF');
306 if (elems.length > 0) {
307 href = elems[0].getAttribute('HREF');;
309 var evt = document.createEvent('Event');
310 evt.initEvent('UrlFetched', true, true);
313 document.dispatchEvent(evt);
315 // SmoothStreaming streams
316 elems = xmlDoc.getElementsByTagName('playListItem');
317 if (elems.length > 0) {
318 href = elems[0].getAttribute('mediaSource');;
320 var evt = document.createEvent('Event');
321 evt.initEvent('UrlFetched', true, true);
324 document.dispatchEvent(evt);