From 004d5d9b069c64f199d5a2d0474c7ad292abb496 Mon Sep 17 00:00:00 2001
From: Michael Berkowitz <michael.berkowitz@gmail.com>
Date: Thu, 17 Apr 2008 16:51:00 +0000
Subject: [PATCH] -Adds OAIster translator.

---
 scrapers.sql | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 75 insertions(+), 1 deletion(-)

diff --git a/scrapers.sql b/scrapers.sql
index db99f54b2..86d562762 100644
--- a/scrapers.sql
+++ b/scrapers.sql
@@ -22,7 +22,7 @@
 
 
 -- Set the following timestamp to the most recent scraper update date
-REPLACE INTO version VALUES ('repository', STRFTIME('%s', '2008-04-17 15:15:00'));
+REPLACE INTO version VALUES ('repository', STRFTIME('%s', '2008-04-17 17:00:00'));
 
 REPLACE INTO translators VALUES ('96b9f483-c44d-5784-cdad-ce21b984fe01', '1.0.0b4.r1', '', '2008-03-21 20:00:00', '1', '100', '4', 'Amazon.com', 'Sean Takats and Michael Berkowitz', '^https?://(?:www\.)?amazon', 
 'function detectWeb(doc, url) { 
@@ -1087,6 +1087,80 @@ REPLACE INTO translators VALUES ('88915634-1af6-c134-0171-56fd198235ed', '1.0.0b
 	Zotero.wait();
 }');
 
+REPLACE INTO translators VALUES ('4afb932d-9211-4c0b-a31c-cfa984d62b66', '1.0.0b4.r5', '', '2008-04-17 17:00:00', '0', '100', '4', 'OAIster', 'Michael Berkowitz', 'http://quod.lib.umich.edu/cgi/b/', 
+'function detectWeb(doc, url) {
+	if (doc.title.indexOf("OAIster") != -1) {
+		return "multiple";
+	}
+}', 
+'function doWeb(doc, url) {
+	var items = new Array();
+	var titlex = ''/html/body/table/tbody/tr/td[2]/table/tbody/tr/td/table/tbody/tr[1]/td[4]/font'';
+	var titles = doc.evaluate(titlex, doc, null, XPathResult.ANY_TYPE, null);
+	var title;
+	while (title = titles.iterateNext()) {
+		items.push(Zotero.Utilities.trimInternal(title.textContent));
+	}
+	items = Zotero.selectItems(items);
+	titles = new Array();
+	for each (var title in items) {
+		titles.push(title);
+	}
+	Zotero.debug(titles);
+	var xpath = ''//table/tbody/tr/td/table/tbody//table/tbody[tr/td[4]]'';
+	var arts = doc.evaluate(xpath, doc, null, XPathResult.ANY_TYPE, null);
+	var art;
+	while (art = arts.iterateNext()) {
+		var data = new Object();
+		var rows = doc.evaluate(''./tr[td[4]]'', art, null, XPathResult.ANY_TYPE, null);
+		var row;
+		while (row = rows.iterateNext()) {
+			var tag = Zotero.Utilities.trimInternal(doc.evaluate(''./td[2]'', row, null, XPathResult.ANY_TYPE, null).iterateNext().textContent);
+			var value = Zotero.Utilities.trimInternal(doc.evaluate(''./td[4]'', row, null, XPathResult.ANY_TYPE, null).iterateNext().textContent);
+			if (tag == "Note") {
+				if (!data[''Note'']) {
+					data[tag] = Zotero.Utilities.unescapeHTML(value);
+				}
+			} else {
+				data[tag] = Zotero.Utilities.unescapeHTML(value);
+			}
+			
+		}
+		var item = new Zotero.Item();
+		if (data[''Resource Type'']) {
+			var itemType = data[''Resource Type''];
+		} else {
+			var itemType = "journalArticle";
+		}
+		if (itemType == "journalArticle" || itemType.match(/(A|a)rticle/) || itemType.match(/text/)) {
+			item.itemType = "journalArticle";
+		} else if (itemType.match(/(T|t)hesis/)) {
+			item.itemType = "thesis";
+		}
+		item.title = data[''Title''];
+		var authors = data[''Author/Creator''].split(/;/);
+		for each (var aut in authors) {
+			if (aut.match(/,/)) {
+				aut = aut.split(/,\s+/);
+				aut = aut[1] + " " + aut[0];
+			}
+			item.creators.push(Zotero.Utilities.cleanAuthor(aut, "author"));
+		}
+		item.date = data[''Year''].match(/\d{4}\-\d{2}\-\d{2}/)[0];
+		item.url = data[''URL''];
+		if (data[''Note'']) item.abstractNote = Zotero.Utilities.trimInternal(data[''Note'']);
+		if (data[''Subject'']) {
+			var keys = data[''Subject''].split(/;/);
+			for each (var kw in keys) {
+				if (kw.match(/\w+/)) item.tags.push(kw);
+			}
+		}
+		for (var i in titles) {
+			if (item.title == titles[i]) item.complete();
+		}
+	}
+}');
+
 REPLACE INTO translators VALUES ('675306d2-fca9-466f-b33d-1e3cc1bfd091', '1.0.0b4.r5', '', '2008-04-17 15:15:00', '0', '100', '4', 'Universiteit van Amsterdam', 'Michael Berkowitz', 'http://opc.uva.nl:8080/', 
 'function detectWeb(doc, url) {
 	if (doc.evaluate(''//td[3][@class="hit"]/a'', doc, null, XPathResult.ANY_TYPE, null).iterateNext()) {