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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
|
{
"translatorID": "c3edb423-f267-47a1-a8c2-158c247f87c2",
"label": "Common-Place",
"creator": "Frederick Gibbs",
"target": "^https?://(www\\.)?(common-place\\.org/vol-.*/no-.*/.|historycooperative\\.org/journals/cp)",
"minVersion": "1.0.0b4.r5",
"maxVersion": "",
"priority": 100,
"inRepository": true,
"translatorType": 4,
"browserSupport": "gcsibv",
"lastUpdated": "2012-01-30 22:51:17"
}
function detectWeb(doc, url) {
if(doc.title.indexOf("Previous Issues") != -1 || doc.title.indexOf("Search Site") != -1 ) {
return "multiple";
} else {
return "journalArticle";
}
}
function scrape(doc) {
var namespace = doc.documentElement.namespaceURI;
var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null;
} : null;
var newItem = new Zotero.Item("journalArticle");
newItem.publicationTitle = "Common-Place";
newItem.url = doc.location.href;
//get issue year and month
//these will determine what xpaths we use for title and author
var pubDate;
var dateRe = /<a href="\/vol-[0-9]{2}\/no-[0-9]{2}\/">(.*)<\/a><\/b>/;
var m = dateRe.exec(Zotero.Utilities.trimInternal(doc.getElementsByTagName("body")[0].innerHTML));
if(m) {
//newItem.title = Zotero.Utilities.trimInternal(Zotero.Utilities.unescapeHTML(m[1]));
pubDate = m[1];
} else {
pubDate = doc.evaluate('//div[@id="container"]/div[@id="top"]/p/b/a[2]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
}
var d;
//Zotero.debug(pubDate);
pubDateVolRE = /vol. (.*) · no. /;
d = pubDateVolRE.exec(pubDate);
newItem.volume = d[1];
pubDateVolRE = /no. (.*) ·/;
d = pubDateVolRE.exec(pubDate);
newItem.issue = d[1];
pubDateVolRE = /no. [0-9] · (.*)/;
d = pubDateVolRE.exec(pubDate);
newItem.date = d[1];
//usually the page begins with the article title or book title (of reviewed book)
//some pages have an image just before them, so we need to skip it if it's there.
var pLevel;
var m=doc.evaluate('//div[@id="content"]/p[1]/img', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
//if there is an image here, offset the xpath
if (m == null) {
pLevel = '//div[@id="content"]/p[1]';
} else {
pLevel = '//div[@id="content"]/p[2]';
}
//issues before 2004 have a table based layout, so a totally different xpath.
//check to see if we have anything, then try again if we don't.
var author;
var title;
author = doc.evaluate(pLevel+'/span[1]', doc, nsResolver, XPathResult.ANY_TYPE, null);
author = author.iterateNext();
if (author != null) {
//Zotero.debug("au"+author+"au");
var title = doc.evaluate(pLevel+'/span[2]', doc, nsResolver, XPathResult.ANY_TYPE, null);
//Zotero.debug("ti"+title+"ti");
title = title.iterateNext().textContent;
//determine if we have a book review
// if so, get the publication information
if (author.textContent.indexOf("Review by") != -1 ) {
newItem.title = String.concat("Review of ", title);
newItem.author = author.textContent.substring(10);
} else {
newItem.author = author.textContent;
newItem.title = title;
}
}
else { //we have older issue
//check if we are on a review
var review = doc.evaluate('/html/body/table/tbody/tr/td[2]/p[2]', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
var temp = review.textContent;
if (temp.indexOf("Review") != -1) {
title = doc.evaluate('/html/body/table/tbody/tr/td[2]/p/i', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
title = "Review of " + title;
author = review.textContent.substring(10);
} else { //for articles
title = doc.evaluate('/html/body/table/tbody/tr/td[2]/p/b', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext().textContent;
author = doc.evaluate('/html/body/table/tbody/tr/td[2]/p[1]', doc, null, XPathResult.ANY_TYPE, null).iterateNext().textContent.split(/\n/)[1];
//Zotero.debug(author);
}
newItem.author = author;
newItem.title = title;
}
newItem.attachments.push({document:doc, title:doc.title});
newItem.complete();
}
function doWeb(doc, url) {
var type = detectWeb(doc, url);
if (type == "multiple") {
var namespace = doc.documentElement.namespaceURI;
var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null;
} : null;
//create list of items
//what about home page (current issue table of contents?)
//for search result links: /html/body/table[2]/tbody/tr/td[2]/li[3]/a
//for previous issues: //tr/td/p/a/b (but we need to strip out volume links (starts with 'Volume')
var link;
var title;
var items = new Object();
var searchLinks = doc.evaluate('/html/body/table[2]/tbody/tr/td[2]/li/a', doc, nsResolver, XPathResult.ANY_TYPE, null);
while (elmt = searchLinks.iterateNext()) {
Zotero.debug(elmt.textContent);
title = elmt.textContent;
link = elmt.href;
if (title && link){
items[link] = title;
}
}
items = Zotero.selectItems(items);
if(!items) {
return true;
}
var uris = new Array();
for(var i in items) {
uris.push(i);
}
Zotero.Utilities.processDocuments(uris, function(doc) { scrape(doc) },
function() { Zotero.done(); }, null);
Zotero.wait();
} else {
scrape(doc);
}
}/** BEGIN TEST CASES **/
var testCases = [
{
"type": "web",
"url": "http://www.common-place.org/vol-12/no-01/tales/",
"items": [
{
"itemType": "journalArticle",
"creators": [],
"notes": [],
"tags": [],
"seeAlso": [],
"attachments": [
{
"document": {
"location": {}
},
"title": "Common-place: Tales from the Vault"
}
],
"publicationTitle": "Common-Place",
"url": "http://www.common-place.org/vol-12/no-01/tales/",
"volume": "12",
"issue": "1",
"date": "October 2011",
"author": "Megan Kate Nelson",
"title": "Looking for Limbs in all the Right Places",
"libraryCatalog": "Common-Place",
"accessDate": "CURRENT_TIMESTAMP"
}
]
}
]
/** END TEST CASES **/
|
