Adding himura's patches and fixed author handling code.

This commit is contained in:
Matt Burton 2009-12-31 20:54:41 +00:00
parent d08bc12b69
commit 4189fe618e

View file

@ -8,13 +8,13 @@
"maxVersion":"",
"priority":100,
"inRepository":true,
"lastUpdated":"2009-01-08 08:19:07"
"lastUpdated":"2009-12-31 08:19:07"
}
function detectWeb(doc, url) {
if (doc.title.match(/search result/) || doc.title.match(/Table of Contents/)) {
return "multiple";
} else if (url.match(/getarticle\?/)) {
} else if (url.match(/getarticle\?/) || url.match(/link\?/)) {
return "journalArticle";
}
}
@ -47,27 +47,37 @@ function doWeb(doc, url) {
}
Zotero.Utilities.processDocuments(arts, function(doc) {
var item = new Zotero.Item("journalArticle");
item.ISSN = '0033-068X';
item.title = Zotero.Utilities.trimInternal(doc.evaluate('//h2[@class="title"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent);
if (doc.evaluate('//h2[@class="subtitle"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext()) {
item.title = item.title + ": " + Zotero.Utilities.trimInternal(doc.evaluate('//h2[@class="subtitle"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent);
}
item.abstractNote = Zotero.Utilities.trimInternal(doc.evaluate('//p[@class="abstract"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent);
var authors = Zotero.Utilities.unescapeHTML(Zotero.Utilities.trimInternal(doc.evaluate('/html/body/p[@class="author"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent));
authors = authors.replace(/[*()]+/g, "").split(/(,\s+|\band\b)/);
for each (var aut in authors) {
if (!aut.match(/(,|and)/)) {
item.creators.push(Zotero.Utilities.cleanAuthor(aut, "author"));
}
var authors = doc.evaluate("//p[@class='author']/a", doc, null, XPathResult.ANY_TYPE, null);
var aut;
while(aut = authors.iterateNext()) {
item.creators.push(Zotero.Utilities.cleanAuthor(aut.textContent, "author"));
}
var info = Zotero.Utilities.trimInternal(doc.evaluate('//h4[@class="info"]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent);
info = info.match(/Vol\.\s+(\d+)\s+No\.\s+(\d+)\s+\((\d+)\)\s+pp\.\s+([\d-]+)\s+URL\s+:\s+(.*)\s+DOI\s+:\s+(.*)$/);
item.volume = info[1];
item.issue = info[2];
item.date = info[3];
item.pages = info[4];
item.url = info[5];
item.DOI = info[6];
if (m = info.match(/Vol\.\s+(\d+)\s+No\.\s+(\d+)\s+\((\d+)\)\s+pp\.\s+([\d-]+)\s+URL\s+:\s+(.*)\s+DOI\s+:\s+(.*)$/)){
item.ISSN = '0033-068X';
item.publicationTitle = "Progress of Theoretical Physics";
item.journalAbbreviation = "Prog. Theor. Phys.";
item.volume = m[1];
item.issue = m[2];
item.date = m[3];
item.pages = m[4];
item.url = m[5];
item.DOI = m[6];
} else if (m = info.match(/Supplement\s+No\.\s+(\d+)\s+\((\d+)\)\s+pp\.\s+([\d-]+)\s+URL\s+:\s+(.*)\s+DOI\s+:\s+(.*)$/)){
item.ISSN = '0375-9687';
item.publicationTitle = "Progress of Theoretical Physics Supplement";
item.journalAbbreviation = "Prog. Theor. Phys. Suppl.";
item.volume = m[1];
item.date = m[2];
item.pages = m[3];
item.url = m[4];
item.DOI = m[5];
}
var pdfurl = doc.evaluate('//a[contains(text(), "PDF")]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().href;
item.attachments = [
{url:item.url, title:"PTP Snapshot", mimeType:"text/html"},