New version by Tim Sherratt

This commit is contained in:
Avram Lyon 2010-08-15 10:32:24 +00:00
parent a0ecb645a8
commit f4d759ebf4

View file

@ -1,19 +1,19 @@
{ {
"translatorID":"50a4cf3f-92ef-4e9f-ab15-815229159b16", "translatorID":"50a4cf3f-92ef-4e9f-ab15-815229159b16",
"translatorType":4,
"label":"National Archives of Australia", "label":"National Archives of Australia",
"creator":"Tim Sherratt", "creator":"Tim Sherratt",
"target":"^http://[^/]*naa.gov.au/", "target":"^http://[^/]*naa\\.gov\\.au/",
"minVersion":"1.0", "minVersion":"1.0",
"maxVersion":"", "maxVersion":"",
"priority":90, "priority":100,
"inRepository":false, "inRepository":yes,
"lastUpdated":"2009-12-17 09:35:00" "translatorType":4,
"lastUpdated":"2010-08-12 15:38:20"
} }
function detectWeb(doc, url) { function detectWeb(doc, url) {
//RecordSearch - items and series - or Photosearch results //RecordSearch - items and series - or Photosearch results
if (url.match(/Series_listing.asp/i) || url.match(/Items_listing.asp/i) || url.match(/PhotoSearchSearchResults.asp/i)) { if (url.match(/SeriesListing.asp/i) || url.match(/ItemsListing.asp/i) || url.match(/PhotoSearchSearchResults.asp/i)) {
return "multiple"; return "multiple";
} else if (url.match(/SeriesDetail.asp/i) || url.match(/ItemDetail.asp/i) || url.match(/PhotoSearchItemDetail.asp/i) || url.match(/imagine.asp/i)) { } else if (url.match(/SeriesDetail.asp/i) || url.match(/ItemDetail.asp/i) || url.match(/PhotoSearchItemDetail.asp/i) || url.match(/imagine.asp/i)) {
return "manuscript"; return "manuscript";
@ -24,33 +24,39 @@ function doWeb(doc, url) {
var nsResolver = namespace ? function(prefix) { var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null; if (prefix == 'x') return namespace; else return null;
} : null; } : null;
// If it's a single page of a digitised file, then send it to be processed directly.
// To avoid cross domain errors make sure links match current sub-domain // This is because digitised pages, after the first, are retrieved via POST, thus if you feed the url to processDocuments
if (url.match(/naa12/i)) { // you'll only ever get the first page.
baseURL = "http://naa12.naa.gov.au/scripts/"; if (url.match(/imagine.asp/i)) {
} else if (url.match(/recordsearch/i)) { processFolio(doc);
baseURL = "http://recordsearch.naa.gov.au/scripts/"; Zotero.done();
} // Everything else can be handled normally.
} else {
// To avoid cross domain errors find baseurl
var baseURL = doc.location.href.match(/(http:\/\/[a-z0-9]+\.naa\.gov\.au)/)[1];
var records = new Array(); var records = new Array();
var titles, links, title, link; var titles, links, title, link;
if (detectWeb(doc, url) == "multiple") { if (detectWeb(doc, url) == "multiple") {
var items = new Object(); var items = new Object();
// Files // Files
if (url.match(/Items_listing.asp/i)) { if (url.match(/ItemsListing.asp/i)) {
titles = doc.evaluate('//td[b="Title"]', doc, nsResolver, XPathResult.ANY_TYPE, null); titles = doc.evaluate('//td[4][@title="Go to Item details"]', doc, nsResolver, XPathResult.ANY_TYPE, null);
links = doc.evaluate('//td[b="Control symbol"]/a', doc, nsResolver, XPathResult.ANY_TYPE, null); links = doc.evaluate('//td[4][@title="Go to Item details"]/@onclick', doc, nsResolver, XPathResult.ANY_TYPE, null);
// Photos // Photos
} else if (url.match(/PhotoSearchSearchResults.asp/i)) { } else if (url.match(/PhotoSearchSearchResults.asp/i)) {
titles = doc.evaluate('//td[b="Title :"]/a[1]', doc, nsResolver, XPathResult.ANY_TYPE, null); titles = doc.evaluate('//td[b="Title :"]/a[1]', doc, nsResolver, XPathResult.ANY_TYPE, null);
links = doc.evaluate('//td[b="Title :"]/a[1]', doc, nsResolver, XPathResult.ANY_TYPE, null); links = doc.evaluate('//td[b="Title :"]/a[1]', doc, nsResolver, XPathResult.ANY_TYPE, null);
//Series //Series
} else if (url.match(/Series_listing.asp/i)) { } else if (url.match(/SeriesListing.asp/i)) {
titles = doc.evaluate('//td[b="Title"]', doc, nsResolver, XPathResult.ANY_TYPE, null); titles = doc.evaluate('//td[3][@title="Go to Series details"]', doc, nsResolver, XPathResult.ANY_TYPE, null);
links = doc.evaluate('//td[b="Series number"]/a', doc, nsResolver, XPathResult.ANY_TYPE, null); links = doc.evaluate('//td[3][@title="Go to Series details"]/@onclick', doc, nsResolver, XPathResult.ANY_TYPE, null);
} }
while ((title = titles.iterateNext()) && (link = links.iterateNext())) { while ((title = titles.iterateNext()) && (link = links.iterateNext())) {
if (url.match(/PhotoSearchSearchResults.asp/i)) {
items[link.href] = Zotero.Utilities.trimInternal(title.lastChild.textContent); items[link.href] = Zotero.Utilities.trimInternal(title.lastChild.textContent);
Zotero.debug(title.lastChild.textContent); } else {
items[baseURL + '/SearchNRetrieve/Interface' + link.textContent.match(/window\.location = '\.\.(.+?)'/)[1]] = Zotero.Utilities.trimInternal(title.firstChild.textContent);
}
} }
items = Zotero.selectItems(items); items = Zotero.selectItems(items);
for (var i in items) { for (var i in items) {
@ -59,146 +65,187 @@ function doWeb(doc, url) {
} else { } else {
records = [url]; records = [url];
} }
var setupCallback = function () { Zotero.Utilities.processDocuments(records, scrape, function(){Zotero.done();});
if (records.length) { Zotero.wait();
}
}
function processFolio(doc) {
var namespace = doc.documentElement.namespaceURI;
var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null;
} : null;
// To avoid cross-domain problems, find the base url
var baseURL = doc.location.href.match(/(http:\/\/[a-z0-9]+\.naa\.gov\.au)/)[1];
var item = new Zotero.Item("manuscript"); var item = new Zotero.Item("manuscript");
item.repository = "National Archives of Australia"; item.archive = "National Archives of Australia";
var record = records.shift(); item.libraryCatalog = "RecordSearch";
Zotero.debug(record); var barcode, page, numPages;
var postString; // Using my Greasemonkey interface
// Scrape digital image - ie a single folio - details
if (record.match(/Imagine.asp/i)) {
// You're using my Greasemonkey script to view images
var b, i, c;
if (doc.body.innerHTML.match(/Digital copy of NAA:/)) { if (doc.body.innerHTML.match(/Digital copy of NAA:/)) {
doc.evaluate('//img[@id="fileimage"]/@src', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent.match(/B=(\d+)&S=(\d+)&/); doc.evaluate('//img[@id="fileimage"]/@src', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent.match(/B=(\d+)&S=(\d+)&/);
b = RegExp.$1; barcode = RegExp.$1;
i = RegExp.$2; page = RegExp.$2;
c = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="printto"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent); numPages = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="printto"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
// You're using the original RS interface // Using the original RS interface
} else { } else {
b = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="Hidden1"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent); barcode = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="Hidden1"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
i = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="Text1"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent); page = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="Text1"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
c = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="Hidden3"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent); numPages = Zotero.Utilities.trimInternal(doc.evaluate('//input[@id="Hidden3"]/@value', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
} }
postString = "B=" + b + "&C=" + c + "&F=1&I=" + i + "&L=Y&M=R&MX=Y&S=Y&SE=1&X=N";
Zotero.Utilities.HTTP.doPost(record, postString, function (text) {
// This is a digital image -- ie a folio
var barcode = text.match(/Digital copy of item with barcode\s+(\d+)/)[1];
Zotero.debug(barcode);
item.pages = text.match(/NAME="I" VALUE="(\d+)"/)[1];
item.numPages = text.match(/NAME="C" VALUE="(\d+)"/)[1];
item.url = "http://naa16.naa.gov.au/rs_images/ShowImage.php?B=" + barcode + "&S=" + item.pages + "&T=P";
var itemURL = baseURL + "ItemDetail.asp?M=0&B=" + barcode;
item.manuscriptType = 'folio'; item.manuscriptType = 'folio';
Zotero.Utilities.processDocuments(itemURL, function(itemDoc) { item.pages = page;
var series = Zotero.Utilities.trimInternal(itemDoc.evaluate('//td[b="Series number"]', itemDoc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent); item.numPages = numPages;
var control = Zotero.Utilities.trimInternal(itemDoc.evaluate('//td[b="Control symbol"]', itemDoc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent); // The link to the image file - there's no way to link to the image in the context of the file
item.url = 'http://recordsearch.naa.gov.au/NaaMedia/ShowImage.asp?B=' + barcode + '&S=' + item.pages + '&T=P';
// Retrieve file details and extract reference details
var itemURL = baseURL + '/SearchNRetrieve/Interface/DetailsReports/ItemDetail.aspx?Barcode=' + barcode;
var itemDoc = Zotero.Utilities.retrieveDocument(itemURL);
var series = Zotero.Utilities.trimInternal(itemDoc.evaluate('//td[@class="field"][. ="Series number"]/following-sibling::td/a', itemDoc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var control = Zotero.Utilities.trimInternal(itemDoc.evaluate('//td[@class="field"][. ="Control symbol"]/following-sibling::td', itemDoc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var refNumber = series + ", " + control; var refNumber = series + ", " + control;
item.title = 'Page ' + page + ' of NAA: ' + refNumber;
item.archiveLocation = refNumber; item.archiveLocation = refNumber;
item.title = "Page " + item.pages + " of NAA: "+refNumber; // Save a copy of the image
item.shortTitle = "NAA: " + refNumber; item.attachments = [{url:item.url, title:'Digital copy of NAA: ' + refNumber + ', p. ' + page, mimeType:"image/jpeg" }];
item.attachments = [{url:item.url, title:"Digital image of NAA: " + refNumber + ", page " + item.pages, mimeType:"image/jpeg" }]; // MACHINE TAGS
// The file of which this page is a part.
item.tags.push('dcterms:isPartOf="http://www.naa.gov.au/cgi-bin/Search?O=I&Number=' + barcode + '"');
// Citation
item.tags.push('dcterms:bibliographicCitation="NAA: ' + refNumber + ', p. ' + page + '"');
item.tags.push('xmlns:dcterms="http://purl.org/dc/terms/"');
item.complete(); item.complete();
setupCallback(); Zotero.wait();
});
});
// Scrape photo details
} else if (record.match(/PhotoSearchItemDetail.asp/)) {
Zotero.Utilities.HTTP.doGet(record, function (text) {
// Clean up unpredictable linebreaks and tabs
text = text.replace(/\n/gm, "");
text = text.replace(/\r/gm, "");
text = text.replace(/\t/gm, "");
item.title = Zotero.Utilities.trimInternal(text.match(/<b>Title :<\/b>(.*?)<br/)[1]);
item.date = Zotero.Utilities.trimInternal(text.match(/<b>Date :<\/b>(.*?)<br/)[1]);
item.archiveLocation = Zotero.Utilities.trimInternal(text.match(/<b>Image no. :<\/b>(.*?)<br/)[1]);
var barcode = Zotero.Utilities.trimInternal(text.match(/<b>Barcode : <\/b>(.*?)<br/)[1]);
var location = Zotero.Utilities.trimInternal(text.match(/<b>Location : <\/b>(.*?)<br/)[1]);
if (!text.match(/<b>Primary subject :<\/b>.*?Not Assigned/)) { var tag1 = text.match(/<b>Primary subject :<\/b>.*?<a href.*?>(.*?)<\/a>/)[1]};
if (!text.match(/<b>Secondary subject :<\/b>.*?Not Assigned/)) { var tag2 = text.match(/<b>Secondary subject :<\/b>.*?<a href.*?>(.*?)<\/a>/)[1]};
if (tag1) { item.tags.push(Zotero.Utilities.trimInternal(tag1).toLowerCase()) };
if (tag2) { item.tags.push(Zotero.Utilities.trimInternal(tag2).toLowerCase()) };
var imgURL = "http://naa16.naa.gov.au/rs_images/ShowImage.php?B=" + barcode + "&T=P&S=1";
item.url = "http://www.naa.gov.au/cgi-bin/Search?O=PSI&Number=" + barcode;
item.manuscriptType = "photograph";
Zotero.debug(item.tags);
// Save a copy of the photo
item.attachments = [{url:imgURL, title:"Digital image of NAA: "+ item.archiveLocation, mimeType:"image/jpeg" }];
item.complete();
setupCallback();
});
// Scrape series details
} else if (record.match(/SeriesDetail.asp/i)) {
Zotero.Utilities.processDocuments(record, function (doc) {
item.title = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Title"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
item.archiveLocation = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Series number"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
item.date = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Accumulation dates"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var location = doc.evaluate('//td[b="Quantity and location"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
if (location) {
location = location.textContent.replace(/Quantity and location/i, "").replace(/\s([\w]+)([\d]+\.*\d*)/gi, " $1; $2");
} }
Zotero.debug(location); function scrape(doc) {
var agencies = doc.evaluate('//td[b="Agency / person recording"]/table/tbody/tr/td[2]', doc, nsResolver, XPathResult.ANY_TYPE, null); var namespace = doc.documentElement.namespaceURI;
var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null;
} : null;
// To avoid cross-domain problems, find the base url
var baseURL = doc.location.href.match(/(http:\/\/[a-z0-9]+\.naa\.gov\.au)/)[1];
var item = new Zotero.Item("manuscript");
item.archive = "National Archives of Australia";
// Photosearch item
if (doc.location.href.match(/PhotoSearchItemDetail.asp/i)) {
var tags = new Array();
item.libraryCatalog = "PhotoSearch";
item.title = Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Title :"]/following-sibling::text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
item.manuscriptType = "photograph";
var barcode = Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Barcode : "]/following-sibling::text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
var series = Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Find other items in this series :"]/following-sibling::a/text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
var refNumber = Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Image no. :"]/following-sibling::text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
item.archiveLocation = refNumber;
item.url = "http://www.naa.gov.au/cgi-bin/Search?O=PSI&Number=" + barcode;
if (doc.evaluate('//b[. ="Date :"]/following-sibling::text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue != null) {
item.date = Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Date :"]/following-sibling::text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
}
if (doc.evaluate('//b[. ="Location : "]/following-sibling::text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue != null) {
item.place = Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Location : "]/following-sibling::text()[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
}
// Save subjects as tags
subjects = new Array();
subjects.push(Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Primary subject :"]/following-sibling::*[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent).toLowerCase());
subjects.push(Zotero.Utilities.trimInternal(doc.evaluate('//b[. ="Secondary subject :"]/following-sibling::*[1]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent).toLowerCase());
for (var i in subjects) {
if (subjects[i] != '') {
item.tags.push(subjects[i]);
}
}
// Citation
item.tags.push('dcterms:bibliographicCitation="NAA: ' + refNumber + '"');
// Save barcode as identifier
item.tags.push('dcterms:identifier="' + barcode + '"');
// Series of which this is a member
item.tags.push('dcterms:isPartOf="http://www.naa.gov.au/cgi-bin/Search?Number=' + series + '"');
// Same file in RecordSearch
item.tags.push('owl:sameAs="http://www.naa.gov.au/cgi-bin/Search?O=I&Number=' + barcode + '"');
// Namespace declarations
item.tags.push('xmlns:dcterms="http://purl.org/dc/terms/"');
item.tags.push('xmlns:owl="http://www.w3.org/2002/07/owl#"');
// Attach copy of photo as attachment
var imgURL = "http://recordsearch.naa.gov.au/NaaMedia/ShowImage.asp?B=" + barcode + "&S=1&T=P";
item.attachments = [{url:imgURL, title:"Digital image of NAA: "+ item.archiveLocation, mimeType:"image/jpeg" }];
} else if (doc.location.href.match(/SeriesDetail.asp/i)) {
item.libraryCatalog = "RecordSearch";
item.title = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Title"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var refNumber = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Series number"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
item.archiveLocation = refNumber;
item.manuscriptType = "series";
// Link into RecordSearch
item.url = "http://www.naa.gov.au/cgi-bin/Search?Number=" + refNumber;
// Contents dates
item.date = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Contents dates "]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
// Agencies recording into this series
var agencies = doc.evaluate('//div[@id="provenanceRecording"]/ul/li/div[@class="linkagesInfo"]', doc, nsResolver, XPathResult.ANY_TYPE, null);
while (agency = agencies.iterateNext()) { while (agency = agencies.iterateNext()) {
item.creators.push({lastName: agency.textContent, creatorType: "creator"}); item.creators.push({lastName: agency.textContent, creatorType: "creator"});
} }
item.url = "http://www.naa.gov.au/cgi-bin/Search?Number=" + item.archiveLocation; // Save series note as abstract
item.manuscriptType = "series"; if (doc.evaluate('//div[@id="notes"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue != null) {
// Find out how many items from this series have been described on RecordSearch item.abstractNote = Zotero.Utilities.cleanTags(Zotero.Utilities.trimInternal(doc.evaluate('//div[@id="notes"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent));
var itemsURL = baseURL + "SearchOF.asp?DP=2&Q=SER_SERIES_NO=QT" + item.archiveLocation + "QT";
Zotero.Utilities.processDocuments(itemsURL, function(itemDoc) {
var numItems = Zotero.Utilities.trimInternal(itemDoc.evaluate('//tr[2]/td[2]', itemDoc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
Zotero.debug(numItems);
if (numItems == "No records found") {
numItems = "none";
} }
item.extra = "Quantity and location: " + location + "\nNumber of items described: " + numItems; // MACHINE TAGS
item.complete(); // Format
setupCallback(); if (doc.evaluate('//td[@class="field"][div="Predominant physical format"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ANY_TYPE, null) != null) {
}); item.tags.push('dcterms:format="' + Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][div="Predominant physical format"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent) + '"');
});
// Scrape file details
} else if (record.match(/ItemDetail.asp/i)) {
Zotero.Utilities.processDocuments(record, function (doc) {
item.title = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Title"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var series = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Series number"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var control = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Control symbol"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
item.date = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Contents date range"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var access = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Access status"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var location = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Location"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var barcode = Zotero.Utilities.trimInternal(doc.evaluate('//td[b="Barcode"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
// Has the file been digitised?
if (doc.body.innerHTML.match("View digital copy")) {
var digitised = "yes";
} else {
var digitised = "no";
} }
// Number of items described on RecordSearch
if (doc.evaluate('//td[@class="field"][. ="Items in this series on RecordSearch"]/following-sibling::td/a', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent != '') {
item.tags.push('dcterms:extent="' + Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Items in this series on RecordSearch"]/following-sibling::td/a', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent) + ' items described"');
}
// Quantities and locations
var quantities = doc.evaluate('//td[@class="field"][. ="Quantity and location"]/following-sibling::td/ul/li', doc, nsResolver, XPathResult.ANY_TYPE, null);
while (quantity = quantities.iterateNext()) {
item.tags.push('dcterms:extent="' +quantity.textContent + '"');
}
// Citation
item.tags.push('dcterms:bibliographicCitation="NAA: ' + refNumber + '"');
// Declare dcterms namespace
item.tags.push('xmlns:dcterms="http://purl.org/dc/terms/"');
} else if (doc.location.href.match(/ItemDetail.asp/i)) {
item.manuscriptType = 'file';
item.libraryCatalog = "RecordSearch";
item.title = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Title"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var series = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Series number"]/following-sibling::td/a', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var control = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Control symbol"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
var refNumber = series + ', ' + control;
item.archiveLocation = refNumber;
var barcode = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Item barcode"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
// Link into RecordSearch
item.url = "http://www.naa.gov.au/cgi-bin/Search?O=I&Number=" + barcode; item.url = "http://www.naa.gov.au/cgi-bin/Search?O=I&Number=" + barcode;
item.archiveLocation = series + ", " + control; // Contents dates
item.manuscriptType = "file"; item.date = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Contents date range"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
item.extra = "Location: " + location + "\nAccess: " + access + "\nDigitised: " + digitised; // Location
// If it's digitised find out how many pages in the digitised file if (doc.evaluate('//td[@class="field"][. ="Location"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue != null) {
itemURL = baseURL + "imagine.asp?B=" + barcode + "&I=1&SE=1"; item.place = Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Location"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent);
if (digitised == "yes") { }
Zotero.Utilities.processDocuments(itemURL, function(itemDoc) { // Save item note as abstract
var pages = Zotero.Utilities.trimInternal(itemDoc.evaluate('//input[@id="Hidden3"]/@value', itemDoc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent); if (doc.evaluate('//div[@id="notes"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue != null) {
item.numPages = "1-" + pages; item.abstractNote = Zotero.Utilities.cleanTags(Zotero.Utilities.trimInternal(doc.evaluate('//div[@id="notes"]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent));
item.pages = "1-" + pages; }
// MACHINE TAGS
// The series this item belongs to
item.tags.push('dcterms:isPartOf="http://www.naa.gov.au/cgi-bin/Search?Number=' + series + '"');
// Citation
item.tags.push('dcterms:bibliographicCitation="NAA: ' + refNumber + '"');
// Save the barcode as an identifier
item.tags.push('dcterms:identifier="' + barcode + '"');
// Access status
item.tags.push('dcterms:accessRights="' + Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][. ="Access status"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent) + '"');
// Format
if (doc.evaluate('//td[@class="field"][div="Physical format"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue != null) {
item.tags.push('dcterms:format="' + Zotero.Utilities.trimInternal(doc.evaluate('//td[@class="field"][div="Physical format"]/following-sibling::td', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.lastChild.textContent) + '"');
}
// Is there a digital copy? - if so find the number of pages in the digitised file
if (doc.evaluate('//a[. ="View digital copy "]', doc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue != null) {
itemURL = baseURL + "/scripts/Imagine.asp?B=" + barcode;
// Retrieve the digitised file
itemDoc = Zotero.Utilities.retrieveDocument(itemURL);
item.numPages =Zotero.Utilities.trimInternal(itemDoc.evaluate('//input[@id="Hidden3"]/@value', itemDoc, nsResolver, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue.textContent);
}
// Declare dcterms namespace
item.tags.push('xmlns:dcterms="http://purl.org/dc/terms/"');
}
item.complete(); item.complete();
setupCallback();
});
} else {
item.complete();
setupCallback();
}
});
}
} else {
Zotero.done();
}
}
setupCallback();
Zotero.wait();
} }