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/*
40 * - find a way to use the same string as in the @include lines to match the
41 * current window.location. Look for something like GM_testUrl() which builds
42 * the regexp starting from a glob line.
43 * - use jquery, like shown in http://a32.me/2009/11/greasemonkey/
44 * - Support the "download" attribute for anchors:
45 * http://www.whatwg.org/specs/web-apps/current-work/multipage/links.html#downloading-resources
48 /* Fields supported by the "site" object.
51 * locationRegExp: the regexp describing the URL of the page we are modifying
52 * urlContainerXPath: the XPath of the element containing the URL to link
53 * urlRegexp: the regular expression for finding the URL, the first
54 * sub-pattern is taken as the URL
55 * linkDestXPath: the XPath of the element where to place the Direct Download link
60 * initCommand: a function called before the regExp is matched, this can
61 * be useful in cases when some action needs to be done in
62 * order to make the element containing the regExp be actually
63 * rendered. It must accept a 'site' parameter.
65 * onEvent: used to delay the urlRegexp matching to a certain event like
66 * 'DOMNodeInserted' useful when the URL is added by some javascript
67 * library. It has two fields:
69 * evt: the event we want to wait for (e.g. 'DOMNodeInserted')
71 * targetElement: the element in the event handler we want the
72 * urlRegexp is performed on.
74 * processURL: a function to process the URL before adding the Direct
75 * Downdload Link to the page, it must accept a 'site' and a
76 * 'URL' parameters and dispatch the UrlFetched to pass the
77 * modified URL to _add_link().
80 var supported_sites = [
82 locationRegexp: /^http:\/\/video\.repubblica\.it\/.*$/,
83 urlContainerXPath: '//div[@id="contA"]',
84 urlRegexp: /[^\/]addParam\('format', '[^']*', '((http|mms):\/\/[^']*)'/,
85 linkDestXPath: '//div[@id="contA"]',
88 locationRegexp: /^http:\/\/tv\.repubblica\.it\/.*$/,
89 urlContainerXPath: '//div[@id="boxPlayer"]',
90 urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
91 linkDest: 'box_embed',
92 linkDestXPath: '//div[@id="box_embed"]',
95 locationRegexp: /^http:\/\/trovacinema\.repubblica\.it\/.*$/,
96 urlContainerXPath: '//div[@id="col-center"]',
97 urlRegexp: /'flvUrl', '((http|mms):\/\/[^']*)'/,
98 linkDestXPath: '//div[@id="col-center"]',
101 locationRegexp: /^http:\/\/www\.kataweb\.it\/tvzap\/.*$/,
102 urlContainerXPath: '//div[@id="tvzap_video"]',
103 urlRegexp: /'pcUrl', '((http|mms):\/\/[^']*)'/,
104 linkDestXPath: '//div[@id="tvzap_video"]',
107 locationRegexp: /^http:\/\/www\.rai\.tv\/.*$/,
108 initCommand: function(site) {
109 unsafeWindow.Silverlight.isInstalled = function(version) {
113 urlContainerXPath: '//div[@id="silverlightControlHost" or @id="SilverlightPlayer"]',
114 urlRegexp: /mediaUri=(http:\/\/[^,]*)/,
115 onEvent: { evt: 'DOMNodeInserted', targetElement: 'object' },
116 processURL: _rai_get_actual_url,
117 linkDestXPath: '//div[@id="silverlightControlHost" or @id="SilverlightPlayer"]',
120 locationRegexp: /^http:\/\/soundcloud.com\/.*$/,
121 urlContainerXPath: '//div[@id="main-content-inner"]',
122 urlRegexp: /"streamUrl":"([^"]*)"/,
123 linkDestXPath: '//div[@id="main-content-inner"]',
126 locationRegexp: /^http:\/\/www\.telecinco.es\/.*$/,
127 urlContainerXPath: '//video[@class="video-js"]',
128 urlRegexp: /src="([^"]*)"/,
129 linkDestXPath: '//div[@class="pg-bd"]',
133 /* Apply different rules to different sites */
134 for (i = 0; i < supported_sites.length; i++) {
135 var site = supported_sites[i];
137 var result = window.location.href.match(site.locationRegexp);
139 if (site.initCommand) {
140 site.initCommand(site);
142 direct_download_link_add(window.location.href, site);
146 function getElementByXPath(query, root) {
147 return document.evaluate(query, root || document, null, XPathResult.ANY_UNORDERED_NODE_TYPE, null).singleNodeValue;
150 /* from http://stackoverflow.com/questions/1912501 */
151 function htmlDecode(input){
152 var e = document.createElement('div');
154 return e.childNodes.length === 0 ? "" : e.childNodes[0].nodeValue;
158 * Add a Direct Download link on the page for the specified URL
160 * @param: a 'site' object described above.
162 * @return: null on error, true on success
164 function direct_download_link_add(pageURL, site) {
165 site.pageURL = pageURL;
166 var element = getElementByXPath(site.urlContainerXPath);
168 DDL_log('DirectDL (' + site.pageURL + '): Cannot find the element ' + site.urlContainerXPath + ' containing the URL.');
172 document.addEventListener('UrlFetched', _add_link, true);
174 // This is used for sites adding the URL to the DOM after DOMContentLoaded,
175 // for example by some javascript library (like Silverlight.js on rai.tv).
177 element.addEventListener(site.onEvent.evt, function(e) {
178 if (site.onEvent.targetElement &&
179 e.target.tagName.toLowerCase() != site.onEvent.targetElement) {
180 DDL_log('DirectDL (' + site.pageURL + '): skipping element ' + e.target.tagName);
183 _get_URL(site, element);
188 _get_URL(site, element);
191 function _get_URL(site, element) {
192 var content = element.innerHTML;
194 DDL_log('DirectDL (' + site.pageURL + '): content is null, cannot find URL.');
198 var matches = content.match(site.urlRegexp);
199 if (!matches || matches.length < 2 || !matches[1]) {
200 DDL_log('DirectDL (' + site.pageURL + '): URL not found, check the urlRegexp');
203 var URL = matches[1];
205 DDL_log('DirectDL (' + site.pageURL + '): cannot get the URL.');
209 if (site.processURL) {
210 site.processURL(site, URL);
214 var evt = document.createEvent('Event');
215 evt.initEvent('UrlFetched', true, true);
217 evt.URL = htmlDecode(URL);
218 document.dispatchEvent(evt);
221 function _add_link(e) {
225 var destination = getElementByXPath(site.linkDestXPath);
227 DDL_log('DirectDl (' + site.pageURL + '): Cannot add the direct download link.');
231 // Check if we added the link already, if so just update the href attribute.
232 // This is useful when _get_URL() is called on async events.
233 var download_link = document.getElementById('GM_direct_downaload_link');
235 download_link.setAttribute('href', URL);
237 download_link = document.createElement('a');
238 download_link.textContent = 'Direct Link';
239 download_link.setAttribute('id', 'GM_direct_downaload_link');
240 download_link.setAttribute('href', URL);
241 var style = 'background-color: white; color: blue;';
242 style += ' border: 2px solid red;'
243 style += ' float: right; font-size: large;';
244 style += ' padding: .5em; margin: 1em;'
245 style += ' position: relative; z-index: 1000;'
246 download_link.setAttribute('style', style);
248 destination.insertBefore(download_link, destination.firstChild);
252 function DDL_log(message) {
261 function _rai_get_actual_url(site, URL) {
263 // SmoothStreaming manifest files get added without processing, for now:
264 if (URL.match(/.*\.csm$/)) {
265 var evt = document.createEvent('Event');
266 evt.initEvent('UrlFetched', true, true);
269 document.dispatchEvent(evt);
273 // http://www.neaveru.com/wordpress/index.php/2008/05/09/greasemonkey-bug-domnodeinserted-event-doesnt-allow-gm_xmlhttprequest/
274 setTimeout( function() {
277 // XXX A custom header. This is the "clever" trick Rai uses to ensure
278 // the content is accessed by www.rai.tv only...
279 headers: {'viaurl': 'www.rai.tv'},
281 onload: function(response) {
282 text = response.responseText;
283 text = text.replace(/&/g, '&')
284 parser = new DOMParser();
285 xmlDoc = parser.parseFromString(text, "text/xml");
288 elems = xmlDoc.getElementsByTagName('REF');
289 if (elems.length > 0) {
290 href = elems[0].getAttribute('HREF');;
292 var evt = document.createEvent('Event');
293 evt.initEvent('UrlFetched', true, true);
296 document.dispatchEvent(evt);
298 // SmoothStreaming streams
299 elems = xmlDoc.getElementsByTagName('playListItem');
300 if (elems.length > 0) {
301 href = elems[0].getAttribute('mediaSource');;
303 var evt = document.createEvent('Event');
304 evt.initEvent('UrlFetched', true, true);
307 document.dispatchEvent(evt);