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
26 // @include http://video.repubblica.it/*
27 // @include http://tv.repubblica.it/*
28 // @include http://trovacinema.repubblica.it/*
29 // @include http://www.kataweb.it/tvzap/*
30 // @include http://www.rai.tv/*
31 // @include http://soundcloud.com/*
32 // @include http://www.telecinco.es/*
38 * - find a way to use the same string as in the @include lines to match the
39 * current window.location. Look for something like GM_testUrl() which builds
40 * the regexp starting from a glob line.
41 * - use jquery, like shown in http://a32.me/2009/11/greasemonkey/
42 * - Support the "download" attribute for anchors:
43 * http://www.whatwg.org/specs/web-apps/current-work/multipage/links.html#downloading-resources
46 /* Fields supported by the "site" object.
49 * locationRegExp: the regexp describing the URL of the page we are modifying
50 * urlContainerXPath: the XPath of the element containing the URL to link
51 * urlRegexp: the regular expression for finding the URL, the first
52 * sub-pattern is taken as the URL
53 * linkDestXPath: the XPath of the element where to place the Direct Download link
58 * initCommand: a function called before the regExp is matched, this can
59 * be useful in cases when some action needs to be done in
60 * order to make the element containing the regExp be actually
61 * rendered. It must accept a 'site' parameter.
63 * onEvent: used to delay the urlRegexp matching to a certain event like
64 * 'DOMNodeInserted' useful when the URL is added by some javascript
65 * library. It has two fields:
67 * evt: the event we want to wait for (e.g. 'DOMNodeInserted')
69 * targetElement: the element in the event handler we want the
70 * urlRegexp is performed on.
72 * processURL: a function to process the URL before adding the Direct
73 * Downdload Link to the page, it must accept a 'site' and a
74 * 'URL' parameters and dispatch the UrlFetched to pass the
75 * modified URL to _add_link().
78 var supported_sites = [
80 locationRegexp: /^http:\/\/video\.repubblica\.it\/.*$/,
81 urlContainerXPath: '//div[@id="contA"]',
82 urlRegexp: /[^\/]addParam\('format', '[^']*', '((http|mms):\/\/[^']*)'/,
83 linkDestXPath: '//div[@id="contA"]',
86 locationRegexp: /^http:\/\/tv\.repubblica\.it\/.*$/,
87 urlContainerXPath: '//div[@id="boxPlayer"]',
88 urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
89 linkDest: 'box_embed',
90 linkDestXPath: '//div[@id="box_embed"]',
93 locationRegexp: /^http:\/\/trovacinema\.repubblica\.it\/.*$/,
94 urlContainerXPath: '//div[@id="col-center"]',
95 urlRegexp: /'flvUrl', '((http|mms):\/\/[^']*)'/,
96 linkDestXPath: '//div[@id="col-center"]',
99 locationRegexp: /^http:\/\/www\.kataweb\.it\/tvzap\/.*$/,
100 urlContainerXPath: '//div[@id="tvzap_video"]',
101 urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
102 linkDestXPath: '//div[@id="tvzap_video"]',
105 locationRegexp: /^http:\/\/www\.rai\.tv\/.*$/,
106 initCommand: function(site) {
107 unsafeWindow.Silverlight.isInstalled = function(version) {
111 urlContainerXPath: '//div[@id="silverlightControlHost" or @id="SilverlightPlayer"]',
112 urlRegexp: /mediaUri=(http:\/\/[^,]*)/,
113 onEvent: { evt: 'DOMNodeInserted', targetElement: 'object' },
114 processURL: _rai_get_actual_url,
115 linkDestXPath: '//div[@id="silverlightControlHost" or @id="SilverlightPlayer"]',
118 locationRegexp: /^http:\/\/soundcloud.com\/.*$/,
119 urlContainerXPath: '//div[@id="main-content-inner"]',
120 urlRegexp: /"streamUrl":"([^"]*)"/,
121 linkDestXPath: '//div[@id="main-content-inner"]',
124 locationRegexp: /^http:\/\/www\.telecinco.es\/.*$/,
125 urlContainerXPath: '//video[@class="video-js"]',
126 urlRegexp: /src="([^"]*)"/,
127 linkDestXPath: '//div[@class="pg-bd"]',
131 /* Apply different rules to different sites */
132 for (i = 0; i < supported_sites.length; i++) {
133 var site = supported_sites[i];
135 var result = window.location.href.match(site.locationRegexp);
137 if (site.initCommand) {
138 site.initCommand(site);
140 direct_download_link_add(window.location.href, site);
144 function getElementByXPath(query, root) {
145 return document.evaluate(query, root || document, null, XPathResult.ANY_UNORDERED_NODE_TYPE, null).singleNodeValue;
148 /* from http://stackoverflow.com/questions/1912501 */
149 function htmlDecode(input){
150 var e = document.createElement('div');
152 return e.childNodes.length === 0 ? "" : e.childNodes[0].nodeValue;
156 * Add a Direct Download link on the page for the specified URL
158 * @param: a 'site' object described above.
160 * @return: null on error, true on success
162 function direct_download_link_add(pageURL, site) {
163 site.pageURL = pageURL;
164 var element = getElementByXPath(site.urlContainerXPath);
166 DDL_log('DirectDL (' + site.pageURL + '): Cannot find the element ' + site.urlContainerXPath + ' containing the URL.');
170 document.addEventListener('UrlFetched', _add_link, true);
172 // This is used for sites adding the URL to the DOM after DOMContentLoaded,
173 // for example by some javascript library (like Silverlight.js on rai.tv).
175 element.addEventListener(site.onEvent.evt, function(e) {
176 if (site.onEvent.targetElement &&
177 e.target.tagName.toLowerCase() != site.onEvent.targetElement) {
178 DDL_log('DirectDL (' + site.pageURL + '): skipping element ' + e.target.tagName);
181 _get_URL(site, element);
186 _get_URL(site, element);
189 function _get_URL(site, element) {
190 var content = element.innerHTML;
192 DDL_log('DirectDL (' + site.pageURL + '): content is null, cannot find URL.');
196 var matches = content.match(site.urlRegexp);
197 if (!matches || matches.length < 2 || !matches[1]) {
198 DDL_log('DirectDL (' + site.pageURL + '): URL not found, check the urlRegexp');
201 var URL = matches[1];
203 DDL_log('DirectDL (' + site.pageURL + '): cannot get the URL.');
207 if (site.processURL) {
208 site.processURL(site, URL);
212 var evt = document.createEvent('Event');
213 evt.initEvent('UrlFetched', true, true);
215 evt.URL = htmlDecode(URL);
216 document.dispatchEvent(evt);
219 function _add_link(e) {
223 var destination = getElementByXPath(site.linkDestXPath);
225 DDL_log('DirectDl (' + site.pageURL + '): Cannot add the direct download link.');
229 // Check if we added the link already, if so just update the href attribute.
230 // This is useful when _get_URL() is called on async events.
231 var download_link = document.getElementById('GM_direct_downaload_link');
233 download_link.setAttribute('href', URL);
235 download_link = document.createElement('a');
236 download_link.textContent = 'Direct Link';
237 download_link.setAttribute('id', 'GM_direct_downaload_link');
238 download_link.setAttribute('href', URL);
239 var style = 'background-color: white; color: blue;';
240 style += ' border: 2px solid red;'
241 style += ' float: right; font-size: large;';
242 style += ' padding: .5em; margin: 1em;'
243 style += ' position: relative; z-index: 1000;'
244 download_link.setAttribute('style', style);
246 destination.insertBefore(download_link, destination.firstChild);
250 function DDL_log(message) {
259 function _rai_get_actual_url(site, URL) {
261 // SmoothStreaming manifest files get added without processing, for now:
262 if (URL.match(/.*\.csm$/)) {
263 var evt = document.createEvent('Event');
264 evt.initEvent('UrlFetched', true, true);
267 document.dispatchEvent(evt);
271 // http://www.neaveru.com/wordpress/index.php/2008/05/09/greasemonkey-bug-domnodeinserted-event-doesnt-allow-gm_xmlhttprequest/
272 setTimeout( function() {
275 // XXX A custom header. This is the "clever" trick Rai uses to ensure
276 // the content is accessed by www.rai.tv only...
277 headers: {'viaurl': 'www.rai.tv'},
279 onload: function(response) {
280 text = response.responseText;
281 text = text.replace(/&/g, '&')
282 parser = new DOMParser();
283 xmlDoc = parser.parseFromString(text, "text/xml");
286 elems = xmlDoc.getElementsByTagName('REF');
287 if (elems.length > 0) {
288 href = elems[0].getAttribute('HREF');;
290 var evt = document.createEvent('Event');
291 evt.initEvent('UrlFetched', true, true);
294 document.dispatchEvent(evt);
296 // SmoothStreaming streams
297 elems = xmlDoc.getElementsByTagName('playListItem');
298 if (elems.length > 0) {
299 href = elems[0].getAttribute('mediaSource');;
301 var evt = document.createEvent('Event');
302 evt.initEvent('UrlFetched', true, true);
305 document.dispatchEvent(evt);