www

commit 7eb0781be46324c415ab4a31074a08180f727cd7
parent 23cae9a3edafa2efc9abb93c161f763ada3c9790
Author: Avram Lyon <ajlyon@gmail.com>
Date:   Thu, 10 Mar 2011 18:13:46 +0000

Trans: Quick rewrite of Reuters


Diffstat:
M
translators/Reuters.js
 | 
93
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---------------------

1 file changed, 68 insertions(+), 25 deletions(-)
diff --git a/translators/Reuters.js b/translators/Reuters.js
@@ -1,18 +1,42 @@
 {
-	"translatorID":"83979786-44af-494a-9ddb-46654e0486ef",
-	"translatorType":4,
-	"label":"Reuters",
-	"creator":"Michael Berkowitz",
-	"target":"http://(www\\.)?reuters.com/",
-	"minVersion":"1.0.0b4.r5",
-	"maxVersion":"",
-	"priority":100,
-	"inRepository":true,
-	"lastUpdated":"2008-07-07 14:50:00"
+        "translatorID": "83979786-44af-494a-9ddb-46654e0486ef",
+        "label": "Reuters",
+        "creator": "Avram Lyon, Michael Berkowitz",
+        "target": "^https?://(www\\.)?reuters\\.com/",
+        "minVersion": "2.0",
+        "maxVersion": "",
+        "priority": 100,
+        "inRepository": "1",
+        "translatorType": 4,
+        "lastUpdated": "2011-03-10 21:05:59"
 }
 
+/*
+   Reuters Translator
+   Copyright (C) 2011 Avram Lyon, ajlyon@gmail.com
+
+   This program is free software: you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation, either version 3 of the License, or
+   (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+/*
+   Translator for Reuters. This is a minimal translator just to get Reuters back working after a redesign.
+   Future versions should implement multiple item saving and attend to the nits that this translator has
+   probably missed. 
+*/
+
 function detectWeb(doc, url) {
-	if (url.match(/article/)) {
+	if (url.match(/^https?:\/\/(www\.)?reuters\.com\/article/)) {
 		return "newspaperArticle";
 	}	
 }
@@ -20,18 +44,38 @@ function detectWeb(doc, url) {
 function doWeb(doc, url) {
 	var item = new Zotero.Item("newspaperArticle");
 
-	item.title = Zotero.Utilities.trimInternal(doc.evaluate('//div[@class="article primaryContent"]/h1', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent);
-	item.date = doc.evaluate('//div[@class="timestampHeader"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent.match(/^.*\d{4}/)[0];
-	var byline = doc.evaluate('//div[@id="resizeableText"]/p[1]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent;
-	if (byline.match(/^By/)) {
-		var authors = byline.substr(3).split(',');
-		for each (var aut in authors) {
-			item.creators.push(Zotero.Utilities.cleanAuthor(aut, "author"));
-		}
-		item.abstractNote = doc.evaluate('//div[@id="resizeableText"]/p[2]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent.match(/\-\s+(.*)$/)[1];
-	} else {
-		item.abstractNote = byline.match(/\-\s+(.*)$/)[1];
+	item.title = doc.evaluate('//meta[@property="og:title"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().content;
+	item.date = doc.evaluate('//meta[@name="REVISION_DATE"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().content;
+	item.place = doc.evaluate('//div[@id="articleInfo"]//span[@class="location"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent;
+	var byline = doc.evaluate('//div[@id="articleInfo"]//p[@class="byline"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent;
+	var authors = byline.substr(3).split(',');
+	for each (var aut in authors) {
+		item.creators.push(authorFix(aut));
 	}
-	item.url = url;
+	item.abstractNote = doc.evaluate('//span[@class="focusParagraph"]/p', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent.replace(/^.*\(Reuters\)\s+-\s+/,"");
+	item.url = doc.evaluate('//link[@rel="canonical"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().href;
+	item.publicationTitle = "Reuters";
+	if (item.place == item.place.toUpperCase())
+	 item.place = Zotero.Utilities.capitalizeTitle(item.place.toLowerCase(),true);
 	item.complete();
-}
-\ No newline at end of file
+}
+
+function authorFix(author) {
+	// Sometimes we have "By Author"
+	if(author.substr(0, 3).toLowerCase() == "by ") {
+		author = author.substr(3);
+	}
+	var cleaned = Zotero.Utilities.cleanAuthor(author, "author");
+	// If we have only one name, set the author to one-name mode
+	if (cleaned.firstName == "") {
+		cleaned["fieldMode"] = true;
+	} else {
+		// We can check for all lower-case and capitalize if necessary
+		// All-uppercase is handled by cleanAuthor
+		cleaned.firstName = (cleaned.firstName == cleaned.firstName.toLowerCase()) ?
+			Zotero.Utilities.capitalizeTitle(cleaned.firstName, true) : cleaned.firstName;
+		cleaned.lastName = (cleaned.lastName == cleaned.lastName.toLowerCase()) ?
+			Zotero.Utilities.capitalizeTitle(cleaned.lastName, true) : cleaned.lastName;
+	}
+	return cleaned;
+}