1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
|
{
"translatorID": "53f8d182-4edc-4eab-b5a1-141698a10101",
"label": "The Times and Sunday Times",
"creator": "Andrew Brown",
"target": "^https?://www\\.thetimes\\.co\\.uk/.+ece$",
"minVersion": "1.0",
"maxVersion": "",
"priority": 100,
"inRepository": true,
"translatorType": 4,
"browserSupport": "g",
"lastUpdated": "2014-04-04 10:00:38"
}
/**/
// TimesOnline.co.uk translator.
// Version 1.5
// 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) {
return "newspaperArticle" ;
}
function getMeta (doc, field) {
field='//meta[@name="' + field + '"]/@content';
content = getXPath(doc, field).iterateNext();
if (content) {
return content.value;
}
}
function getXPath (doc, field) {
xpath=field;
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){
var item = new Zotero.Item("newspaperArticle");
//Could be daily or Sunday Times
//The ISSN seems to be the same for both:
item.issn="0140-0460";
if (url.search(/\/tto\//)!=-1){
item.publicationTitle = 'The Times (London)';
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.date=getMeta(doc,"dashboard_published_date");
item.place="London";
item.abstractNote = getMeta(doc, "description");
// alternative, better, way follows
var standfirstXpath=doc.evaluate('//div[@class="cf "]//p[@class="f-standfirst"]',doc,null,XPathResult.ANY_TYPE,null);
// note space after cf in class name, haha, Murdoch really got value from those Times designers
if(standfirstXpath.iterateNext()!=null){
item.abstractNote=standfirstXpath.iterateNext().textContent;
}
// 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:item.title, mimeType:"text/html"});
item.complete();
}
|
