updating Sudoc.js with sylvain's changes
This commit is contained in:
Matt Burton
parent
19ff243b92
commit
d4a7e5bd37
|
|
@ -2,7 +2,7 @@
|
||||||
"translatorID":"1b9ed730-69c7-40b0-8a06-517a89a3a278",
|
"translatorID":"1b9ed730-69c7-40b0-8a06-517a89a3a278",
|
||||||
"translatorType":4,
|
"translatorType":4,
|
||||||
"label":"Sudoc",
|
"label":"Sudoc",
|
||||||
"creator":"Sean Takats and Michael Berkowitz",
|
"creator":"Sean Takats and Michael Berkowitz, updated by Sylvain Machefert",
|
||||||
"target":"^http://www\\.sudoc\\.abes\\.fr",
|
"target":"^http://www\\.sudoc\\.abes\\.fr",
|
||||||
"minVersion":"1.0.0b3.r1",
|
"minVersion":"1.0.0b3.r1",
|
||||||
"maxVersion":"",
|
"maxVersion":"",
|
||||||
|
|
@ -11,42 +11,59 @@
|
||||||
"lastUpdated":"2008-05-19 17:30:00"
|
"lastUpdated":"2008-05-19 17:30:00"
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
function detectWeb(doc, url) {
|
function detectWeb(doc, url) {
|
||||||
var namespace = doc.documentElement.namespaceURI;
|
var namespace = doc.documentElement.namespaceURI;
|
||||||
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;
|
||||||
|
|
||||||
var xpath = '//table/tbody/tr/td[1][@class="preslabel"]/strong';
|
var multxpath = '/html/body/div[2]/div/span';
|
||||||
var multxpath = '//a[@id="InitialFocusPoint"]';
|
|
||||||
var elt;
|
|
||||||
|
|
||||||
if (elt = doc.evaluate(multxpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
if (elt = doc.evaluate(multxpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||||||
return "multiple";
|
var content = elt.textContent;
|
||||||
}
|
if ( (content == "Résultats") || (content == "Results") )
|
||||||
else if (elt = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext())
|
{
|
||||||
{
|
return "multiple";
|
||||||
var contenu = elt.textContent;
|
}
|
||||||
var numRegexp = /(Num.ro.de.notice|Record.number)/;
|
else if ( (content == "Notice complète") || (content == "title data") )
|
||||||
var m = numRegexp.exec(contenu);
|
{
|
||||||
if (m) {
|
var xpathimage = '/html/body/div[2]/div[4]/span/img';
|
||||||
// On a bien une notice d"ouvrage, on doit chercher limage
|
if (elt = doc.evaluate(xpathimage, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext())
|
||||||
// pour choisir le type de document
|
{
|
||||||
var imgXpath = '/html/body/table/tbody/tr/td[1]/p/img/@src';
|
var type = elt.getAttribute('src');
|
||||||
var imgsrc = doc.evaluate(imgXpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
if (type.indexOf('article.gif') > 0)
|
||||||
if (imgsrc){
|
{
|
||||||
if (imgsrc.indexOf("icon_per.gif") > 0){
|
return "journalArticle";
|
||||||
return "book";
|
}
|
||||||
} else if (imgsrc.indexOf("icon_books.gif") > 0){
|
else if (type.indexOf('book.gif') > 0)
|
||||||
return "book";
|
{
|
||||||
} else if (imgsrc.indexOf("icon_thesis.gif") > 0){
|
return "book";
|
||||||
return "thesis";
|
}
|
||||||
} else if (imgsrc.indexOf("icon_art.gif") > 0){
|
else if (type.indexOf('handwriting.gif') > 0)
|
||||||
return "journalArticle";
|
{
|
||||||
} else {
|
return "manuscript";
|
||||||
return "book";
|
}
|
||||||
}
|
else if (type.indexOf('sons.gif') > 0)
|
||||||
}
|
{
|
||||||
|
return "audioRecording";
|
||||||
|
}
|
||||||
|
else if (type.indexOf('sound.gif') > 0)
|
||||||
|
{
|
||||||
|
return "audioRecording";
|
||||||
|
}
|
||||||
|
else if (type.indexOf('thesis.gif') > 0)
|
||||||
|
{
|
||||||
|
return "thesis";
|
||||||
|
}
|
||||||
|
else if (type.indexOf('map.gif') > 0)
|
||||||
|
{
|
||||||
|
return "map";
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
return "book";
|
||||||
|
}
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
@ -56,105 +73,154 @@ function scrape(doc) {
|
||||||
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;
|
||||||
|
|
||||||
var rowXpath = '//tr[td[@class="preslabel"]]';
|
var zXpath = '/html/body/span[@class="Z3988"]';
|
||||||
var tableRows = doc.evaluate(rowXpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
var eltCoins = doc.evaluate(zXpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||||
var tableRow;
|
if (eltCoins = doc.evaluate(zXpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext())
|
||||||
|
|
||||||
var newItem = new Zotero.Item();
|
|
||||||
// TODO add other item types using detectWeb's icon checking code
|
|
||||||
newItem.itemType = "book";
|
|
||||||
var imgXpath = '/html/body/table/tbody/tr/td[1]/p/img/@src';
|
|
||||||
var imgsrc = doc.evaluate(imgXpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
|
||||||
if (imgsrc){
|
|
||||||
if (imgsrc.indexOf("icon_per.gif") > 0){
|
|
||||||
newItem.itemType = "book";
|
|
||||||
} else if (imgsrc.indexOf("icon_books.gif") > 0){
|
|
||||||
newItem.itemType = "book";
|
|
||||||
} else if (imgsrc.indexOf("icon_thesis.gif") > 0){
|
|
||||||
newItem.itemType = "thesis";
|
|
||||||
} else if (imgsrc.indexOf("icon_art.gif") > 0){
|
|
||||||
newItem.itemType = "journalArticle";
|
|
||||||
} else {
|
|
||||||
newItem.itemType = "book";
|
|
||||||
}
|
|
||||||
} else {
|
|
||||||
newItem.itemType = "book";
|
|
||||||
}
|
|
||||||
while (tableRow = tableRows.iterateNext())
|
|
||||||
{
|
{
|
||||||
var field = doc.evaluate('./td[1]', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
var coins = eltCoins.getAttribute('title');
|
||||||
var value = doc.evaluate('./td[2]', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
|
||||||
field = Zotero.Utilities.superCleanString(field);
|
var newItem = new Zotero.Item();
|
||||||
field = field.replace(/(\(s\))?\s*:\s*$/, "");
|
newItem.repository = false; // do not save repository
|
||||||
if (field == "Titre" || field == "Title"){
|
if(Zotero.Utilities.parseContextObject(coins, newItem))
|
||||||
Zotero.debug("title = " + value);
|
{
|
||||||
value = value.replace(/(\[[^\]]+\])/g,"");
|
if (newItem.title)
|
||||||
newItem.title = value.split(" / ")[0];
|
{
|
||||||
}
|
// We use the same method as in detectWeb to find
|
||||||
if (field.substr(0,6) == "Auteur" || field.substr(0,6) == "Author"){
|
// the real type of document
|
||||||
var authors = doc.evaluate('./td[2]/a', tableRow, nsResolver, XPathResult.ANY_TYPE, null);
|
var xpathimage = '/html/body/div[2]/div[4]/span/img';
|
||||||
var author;
|
if (elt = doc.evaluate(xpathimage, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext())
|
||||||
while (author = authors.iterateNext()){
|
{
|
||||||
|
var type = elt.getAttribute('src');
|
||||||
|
var ZoteroType = '';
|
||||||
|
if (type.indexOf('article.gif') > 0)
|
||||||
|
{
|
||||||
|
zoteroType = 'journalArticle';
|
||||||
|
}
|
||||||
|
else if (type.indexOf('book.gif') > 0)
|
||||||
|
{
|
||||||
|
zoteroType = 'book';
|
||||||
|
}
|
||||||
|
else if (type.indexOf('handwriting.gif') > 0)
|
||||||
|
{
|
||||||
|
zoteroType = 'manuscript';
|
||||||
|
}
|
||||||
|
else if (type.indexOf('sons.gif') > 0)
|
||||||
|
{
|
||||||
|
zoteroType = "audioRecording";
|
||||||
|
}
|
||||||
|
else if (type.indexOf('sound.gif') > 0)
|
||||||
|
{
|
||||||
|
zoteroType = "audioRecording";
|
||||||
|
}
|
||||||
|
else if (type.indexOf('thesis.gif') > 0)
|
||||||
|
{
|
||||||
|
zoteroType = "thesis";
|
||||||
|
}
|
||||||
|
else if (type.indexOf('map.gif') > 0)
|
||||||
|
{
|
||||||
|
zoteroType = "map";
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
zoteroType = "book";
|
||||||
|
}
|
||||||
|
newItem.itemType = zoteroType;
|
||||||
|
}
|
||||||
|
|
||||||
|
// We need to correct some informations where COinS is wrong
|
||||||
|
var rowXpath = '//tr[td[@class="rec_lable"]]';
|
||||||
|
var tableRows = doc.evaluate(rowXpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||||
|
var tableRow;
|
||||||
|
|
||||||
|
while (tableRow = tableRows.iterateNext())
|
||||||
|
{
|
||||||
|
var field = doc.evaluate('./td[1]', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
||||||
|
var value = doc.evaluate('./td[2]', tableRow, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
|
||||||
|
field = Zotero.Utilities.superCleanString(field);
|
||||||
|
field = field.replace(/(\(s\))?\s*:\s*$/, "");
|
||||||
|
|
||||||
|
// With COins, only one author is taken, changed.
|
||||||
|
if (field.substr(0,6) == "Auteur" || field.substr(0,6) == "Author")
|
||||||
|
{
|
||||||
|
var authors = doc.evaluate('./td[2]/div', tableRow, nsResolver, XPathResult.ANY_TYPE, null);
|
||||||
|
newItem.creators = new Array();
|
||||||
|
while (author = authors.iterateNext())
|
||||||
|
{
|
||||||
var authorText = author.textContent;
|
var authorText = author.textContent;
|
||||||
var authorParts = authorText.split(" (");
|
|
||||||
newItem.creators.push(Zotero.Utilities.cleanAuthor(authorParts[0], "author", true));
|
authorFunction = authorText.split(". ")[1];
|
||||||
|
authorText = authorText.split(". ")[0];
|
||||||
|
if (authorFunction)
|
||||||
|
{
|
||||||
|
authorFunction = Zotero.Utilities.superCleanString(authorFunction);
|
||||||
|
}
|
||||||
|
var zoteroFunction = '';
|
||||||
|
// TODO : Add other authotiry types
|
||||||
|
if (authorFunction == 'Traduction')
|
||||||
|
{
|
||||||
|
zoteroFunction = 'Translator';
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
zoteroFunction = 'Author';
|
||||||
|
}
|
||||||
|
newItem.creators.push(Zotero.Utilities.cleanAuthor(authorText, zoteroFunction, true));
|
||||||
|
}
|
||||||
}
|
}
|
||||||
}
|
// The serie isn't in COinS
|
||||||
if (field.substr(0,4) == "Date"){
|
else if (field.substr(0,5) == "Serie" || field.substr(0,10) == "Collection")
|
||||||
newItem.date = value;
|
{
|
||||||
}
|
newItem.series = value;
|
||||||
if (field.substr(0,7) == "Editeur" || field.substr(0,9) == "Publisher"){
|
|
||||||
var pubParts = value.split(" : ");
|
|
||||||
newItem.place = pubParts[0];
|
|
||||||
// needs error checking below to avoid error
|
|
||||||
if (pubParts[1] ) {
|
|
||||||
pubParts = pubParts[1].split(", ");
|
|
||||||
newItem.publisher = pubParts[0];
|
|
||||||
}
|
}
|
||||||
}
|
// When there's a subtitle, only main title is used !
|
||||||
if (field.substr(0,4) == "ISBN" || field.substr(0,4) == "ISSN"){
|
else if (field == "Titre" || field == "Title")
|
||||||
newItem.ISBN = value.split(" (")[0];
|
{
|
||||||
}
|
var title = '';
|
||||||
if (field == "Description") {
|
var titles = doc.evaluate('./td[2]/div/span', tableRow, nsResolver, XPathResult.ANY_TYPE, null);
|
||||||
var m = value.match(/([0-9]+) (?:[pP])/);
|
while (partTitle = titles.iterateNext())
|
||||||
if (m) {
|
{
|
||||||
newItem.pages = m[1];
|
partTitle = partTitle.textContent;
|
||||||
|
partTitle = partTitle.replace(/(\[[^\]]+\] ?)/g,"");
|
||||||
|
title = title + partTitle;
|
||||||
|
}
|
||||||
|
// Remove the author
|
||||||
|
title = title.split(" / ")[0];
|
||||||
|
newItem.title = title;
|
||||||
}
|
}
|
||||||
}
|
// Language not defined in COinS
|
||||||
if (field.substr(0,5) == "Serie" || field.substr(0,10) == "Collection"){
|
else if ( (field == "Langue") || (field == "Language") )
|
||||||
newItem.series = value;
|
{
|
||||||
}
|
newItem.language = value;
|
||||||
if (field.substr(0,6) == "Sujets" || field.substr(0,8) == "Subjects"){
|
|
||||||
var subjectElmts = doc.evaluate('./td[2]/a', tableRow, nsResolver, XPathResult.ANY_TYPE, null);
|
|
||||||
var subject;
|
|
||||||
var subjects;
|
|
||||||
while (subject = subjectElmts.iterateNext()){
|
|
||||||
subjects = subject.textContent.split(" -- ");
|
|
||||||
newItem.tags = newItem.tags.concat(subjects);
|
|
||||||
}
|
}
|
||||||
}
|
else if ( (field == "Résumé") || (field == "Abstract") )
|
||||||
if (field == "In" || field == "Dans"){
|
{
|
||||||
var jtitle = value.replace(/(\[[^\]]+\])/g,"");
|
if (newItem.abstractNote)
|
||||||
jtitle = jtitle.split(" / ")[0];
|
{
|
||||||
jtitle = jtitle.split(" - ")[0];
|
newItem.abstractNote = newItem.abstractNote + " " + value;
|
||||||
newItem.publicationTitle = jtitle;
|
}
|
||||||
//get page numbers
|
else
|
||||||
var m = value.match(/(?:[Pp]\. )([0-9\-]+)/);
|
{
|
||||||
if (m) {
|
newItem.abstractNote = value;
|
||||||
newItem.pages = m[1];
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
//get ISBN or ISSN
|
else if (field == "Notes")
|
||||||
m = value.match(/(?:ISSN|ISBN) ([0-9Xx\-]+)/);
|
{
|
||||||
if (m) {
|
if (newItem.abstractNote)
|
||||||
newItem.ISBN = m[1];
|
{
|
||||||
newItem.ISSN = m[1];
|
newItem.abstractNote = newItem.abstractNote + " " + value;
|
||||||
|
}
|
||||||
|
else
|
||||||
|
{
|
||||||
|
newItem.abstractNote = value;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
// publicationTitle, issue/volume
|
}
|
||||||
|
newItem.complete();
|
||||||
}
|
}
|
||||||
// TODO Pages, Notes, Description, Language, Annexes
|
}
|
||||||
}
|
}
|
||||||
newItem.complete();
|
|
||||||
}
|
}
|
||||||
|
|
||||||
function doWeb(doc, url) {
|
function doWeb(doc, url) {
|
||||||
|
|
@ -162,39 +228,44 @@ 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;
|
||||||
|
|
||||||
var multxpath = '//a[@id="InitialFocusPoint"]';
|
var multxpath = '/html/body/div[2]/div/span';
|
||||||
var elt;
|
|
||||||
|
|
||||||
if (elt = doc.evaluate(multxpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
if (elt = doc.evaluate(multxpath, doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
|
||||||
var newUrl = doc.evaluate('//base/@href', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
var content = elt.textContent;
|
||||||
var xpath = '//tr/td[3]/a';
|
if ( (content == "Résultats") || (content == "Results") )
|
||||||
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
{
|
||||||
var elmt = elmts.iterateNext();
|
var newUrl = doc.evaluate('//base/@href', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||||||
var links = new Array();
|
var xpath = '/html/body/div[2]/table/tbody/tr/td[3]/div/a';
|
||||||
var availableItems = new Array();
|
var elmts = doc.evaluate(xpath, doc, nsResolver, XPathResult.ANY_TYPE, null);
|
||||||
var i = 0;
|
var elmt = elmts.iterateNext();
|
||||||
do {
|
var links = new Array();
|
||||||
|
var availableItems = new Array();
|
||||||
|
var i = 0;
|
||||||
|
do {
|
||||||
var link = doc.evaluate('./@href', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
var link = doc.evaluate('./@href', elmt, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().nodeValue;
|
||||||
var searchTitle = elmt.textContent;
|
var searchTitle = elmt.textContent;
|
||||||
availableItems[i] = searchTitle;
|
availableItems[i] = searchTitle;
|
||||||
links[i] = link;
|
links[i] = link;
|
||||||
i++;
|
i++;
|
||||||
} while (elmt = elmts.iterateNext());
|
} while (elmt = elmts.iterateNext());
|
||||||
var items = Zotero.selectItems(availableItems);
|
var items = Zotero.selectItems(availableItems);
|
||||||
|
|
||||||
if(!items) {
|
if(!items) {
|
||||||
return true;
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
var uris = new Array();
|
||||||
|
for(var i in items) {
|
||||||
|
uris.push(newUrl + links[i]);
|
||||||
|
Zotero.debug(newUrl + links[i]);
|
||||||
|
}
|
||||||
|
Zotero.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
|
||||||
|
function() { Zotero.done(); }, null);
|
||||||
|
Zotero.wait();
|
||||||
}
|
}
|
||||||
var uris = new Array();
|
else if ( (content == "Notice complète") || (content == 'title data') )
|
||||||
for(var i in items) {
|
{
|
||||||
uris.push(newUrl + links[i]);
|
scrape(doc);
|
||||||
}
|
}
|
||||||
Zotero.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
|
|
||||||
function() { Zotero.done(); }, null);
|
|
||||||
Zotero.wait();
|
|
||||||
}
|
}
|
||||||
else {
|
}
|
||||||
scrape(doc);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user