mirrors/zotero
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity Actions

New version of The Times translator by Andrew Brown.

Browse source
This commit is contained in:
Avram Lyon 2010-08-15 10:51:07 +00:00
parent f4d759ebf4
commit be5f7baca3
1 changed files with 105 additions and 96 deletions
Download patch file Download diff file Expand all files Collapse all files

117
translators/The Times UK.js
View file

@ -1,24 +1,27 @@
{ {
"translatorID":"53f8d182-4edc-4eab-b5a1-141698a10101", "translatorID":"53f8d182-4edc-4eab-b5a1-141698a10101",
"translatorType":4, "label":"The Times and Sunday Times",
"label":"The Times UK", "creator":"Will Smith",
"creator":"William Smith", "creator":"Andrew Brown",
"target":"timesonline\\.co\\.uk/tol/.+ece$", "target":"^http://www\\.thetimes\\.co\\.uk/.+ece$",
"minVersion":"1.0.0b4.r5", "minVersion":"1.0",
"maxVersion":"", "maxVersion":"",
"priority":100, "priority":100,
"inRepository":true, "inRepository":true,
"lastUpdated":"2010-06-05 20:35:00" "translatorType":4,
"lastUpdated":"2010-08-11 17:23:03"
} }
/**/
// TimesOnline.co.uk translator. // TimesOnline.co.uk translator.
// Version 1.00 // Version 1.5
// By William Smith, see http://www.willsmith.org/contactme/ // Original by William Smith, see http://www.willsmith.org/contactme/
// extensively tweaked by Andrew Brown to cope with the paywalled structure
function detectWeb(doc, url) { function detectWeb(doc, url) {
return "newspaperArticle"; return "newspaperArticle" ;
} }
@ -35,62 +38,68 @@ function getMeta (doc, field) {
function getXPath (doc, field) { function getXPath (doc, field) {
xpath=field; xpath=field;
return doc.evaluate(xpath, doc, null, XPathResult.ANY_TYPE, null); return doc.evaluate(xpath, doc, null, XPathResult.ANY_TYPE, null);
} }
/*
function getXPathInstance (doc,field) {
xpath=field;
return doc.evaluate(xpath, doc, null, XPathResult.ANY_TYPE, null).iterateNext();
}
*/
function doWeb(doc, url){ function doWeb(doc, url){
var item = new Zotero.Item("newspaperArticle"); var item = new Zotero.Item("newspaperArticle");
// These fields are easy... //Could be daily or Sunday Times
//The ISSN seems to be the same for both:
item.issn="0140-0460";
item.publicationTitle = 'The Times (UK)'; if (url.search(/\/tto\//)!=-1){
item.abstractNote = getMeta(doc, "Description"); item.publicationTitle = 'The Times (London)';
item.title = doc.title.replace(/.?-.?Times Online/, ""); item.title = doc.title.replace("| The Times", "");
}
if(url.search(/\/sto\//)!=-1){
item.publicationTitle = 'The Sunday Times (London)';
item.title = doc.title.replace("| The Sunday Times", "");
}
//Now we have the paper, what section is it in?
var section=url.match(/\/[ts]to\/([^\/]+)/);
// Zotero.debug(section[1]);
// Then print it pretty
item.section=section[1].substr(0,1).toUpperCase() + section[1].substr(1);
// These next fields are easy...
item.url = url; item.url = url;
item.date=getMeta(doc,"dashboard_published_date");
// Author is a pain to get. item.place="London";
item.abstractNote = getMeta(doc, "description");
var authors = getXPath(doc, '//span[@class="byline"]'); // alternative, better, way follows
var standfirstXpath=doc.evaluate('//div[@class="cf "]//p[@class="f-standfirst"]',doc,null,XPathResult.ANY_TYPE,null);
while (author = authors.iterateNext()) { // note space after cf in class name, haha, Murdoch really got value from those Times designers
auc = author.textContent; if(standfirstXpath.iterateNext()!=null){
if (auc.length > 0) { item.abstractNote=standfirstXpath.iterateNext().textContent;
Zotero.debug('authors: ' , auc);
auc = auc.split(/:|,|and/);
for each (var aut in auc) {
aut = aut.trim();
if (aut.length > 0 && (!aut.match(/(Editor|Times|Correspondent)/))) {
Zotero.debug('author: <' + aut + '>');
item.creators.push(Zotero.Utilities.cleanAuthor(aut, "author"));
}
}
}
}
// Date is also a pain to get.
var pagetext = doc.documentElement.innerHTML;
if (pagetext) {
try {
date = pagetext.match(/Article Published Date : (.{10,15}) \d\d:\d\d/);
if (date[1]){
Zotero.debug('date: ' + date[1]);
item.date = date[1];
}
} catch(e){
// do nothing
} }
// extract authors who may be in an array
var authorXpath=doc.evaluate('//div[@class="cf "]//strong[@class="f-author"]',doc, null, XPathResult.ANY_TYPE, null);
var hack;
while (hack=authorXpath.iterateNext()){
var hacks= new Array();
hacks=hack.textContent.split(/and|,/);
// Zotero.debug("hacks: " +hack.textContent.split(/and/));
if (hacks.length > 1){
for (var h in hacks){
item.creators.push(Zotero.Utilities.cleanAuthor(hacks[h],"author"));
}
}
else {
item.creators.push(Zotero.Utilities.cleanAuthor(hack.textContent,"author"));
}
} }
//ATTACH A SNAPSHOT
item.attachments.push({url:url, title:"The Times (UK) Snapshot", mimeType:"text/html"}); item.attachments.push({url:url, title:item.title, mimeType:"text/html"});
item.complete(); item.complete();
} }