-
Notifications
You must be signed in to change notification settings - Fork 1
/
Bibliotheeque et Archives Nationales du Quebec.js
266 lines (215 loc) · 8.86 KB
/
Bibliotheeque et Archives Nationales du Quebec.js
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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
{
"translatorID":"59cce211-9d77-4cdd-876d-6229ea20367f",
"translatorType":4,
"label":"Bibliothèque et Archives Nationales du Québec",
"creator":"Adam Crymble",
"target":"^https?://catalogue\\.banq\\.qc\\.ca/",
"minVersion":"3.0",
"maxVersion":"",
"priority":100,
"browserSupport": "gcsibv",
"inRepository":true,
"lastUpdated":"2015-06-29 17:02:02"
}
function detectWeb(doc, url) {
if (doc.title.match("Search")) {
return "multiple";
} else if (doc.title.match("Recherche")) {
return "multiple";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("book")) {
return "book";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("mmusic")) {
return "book";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("manalytic")) {
return "book";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("msdisc")) {
return "audioRecording";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("msound")) {
return "audioRecording";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("mscas")) {
return "audioRecording";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("mvdisc")) {
return "videoRecording";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("mpaint")) {
return "artwork";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("mserial")) {
return "report";
} else if (doc.evaluate('//td[2]/a/img', doc, null, XPathResult.ANY_TYPE, null).iterateNext().src.match("mcomponent")) {
return "newspaperArticle";
}
}
//Bibliotheque et Archives National du Quebec. Code by Adam Crymble
function associateData (newItem, dataTags, field, zoteroField) {
if (dataTags[field]) {
newItem[zoteroField] = dataTags[field];
}
}
function scrape(doc, url) {
var namespace = doc.documentElement.namespaceURI;
var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null;
} : null;
var dataTags = new Object();
var fieldTitle;
var contents;
var descriptionField;
var tagsContent= new Array();
var inField = 0;
//determines media type
if (detectWeb(doc, url) == "book") {
var newItem = new Zotero.Item("book");
descriptionField = "pages";
} else if (detectWeb(doc, url) == "audioRecording") {
var newItem = new Zotero.Item("audioRecording");
descriptionField = "runningTime";
} else if (detectWeb(doc, url) == "videoRecording") {
var newItem = new Zotero.Item("videoRecording");
descriptionField = "runningTime";
} else if (detectWeb(doc, url) == "artwork") {
var newItem = new Zotero.Item("artwork");
descriptionField = "artworkSize";
} else if (detectWeb(doc, url) == "report") {
var newItem = new Zotero.Item("report");
descriptionField = "pages";
} else if (detectWeb(doc, url) == "newspaperArticle") {
var newItem = new Zotero.Item("newspaperArticle");
descriptionField = "pages"
}
//determines language
var lang = doc.evaluate('//td[2]/a/img', doc, nsResolver, XPathResult.ANY_TYPE, null);
var langCount = doc.evaluate('count (//td[2]/a/img)', doc, nsResolver, XPathResult.ANY_TYPE, null);
var lang1 = lang.iterateNext().src;
if (langCount.numberValue > 1) {
lang1 = lang.iterateNext().src;
if (lang1.match("lfre")) {
newItem.language = "French";
} else if (lang1.match("leng")) {
newItem.language = "English";
}
}
//scraping XPaths
var xPathHeadings = doc.evaluate('//td/table/tbody/tr/td[2]/b', doc, nsResolver, XPathResult.ANY_TYPE, null);
var xPathContents = doc.evaluate('//td[2]/table/tbody/tr/td/table/tbody/tr/td[4]', doc, nsResolver, XPathResult.ANY_TYPE, null);
var xPathCount = doc.evaluate('count (//td/table/tbody/tr/td[2]/b)', doc, nsResolver, XPathResult.ANY_TYPE, null);
if (doc.evaluate('//td/table/tbody/tr/td[2]/b', doc, nsResolver, XPathResult.ANY_TYPE, null)) {
for (i=0; i<xPathCount.numberValue; i++) {
fieldTitle = xPathHeadings.iterateNext().textContent.replace(/\s+/g, '');
contents = xPathContents.iterateNext().textContent;
if (contents.match("[*]") && fieldTitle!= "Publisher" && fieldTitle!= "Éditeur") {
var removeTagExcess = contents.indexOf("[");
contents = contents.substr(0, removeTagExcess);
}
if (fieldTitle == "Author" | fieldTitle == "Auteur") {
fieldTitle = "Author";
dataTags[fieldTitle] = (contents);
var authorName = dataTags["Author"].split(",");
authorName[0] = authorName[0].replace(/\s+/g, '');
dataTags["Author"] = (authorName[1] + (" ") + authorName[0]);
newItem.creators.push(Zotero.Utilities.cleanAuthor(dataTags["Author"], "author"));
//publishing info
} else if (fieldTitle == "Publisher" | fieldTitle == "Éditeur") {
fieldTitle = "Publisher";
dataTags["Publisher"] = (contents);
if (dataTags["Publisher"].match(":")) {
var place1 = dataTags["Publisher"].split(":");
dataTags["Place"] = place1[0].replace(/^\s*|\[|\]/g,'');
var publish = place1[1].split(",");
dataTags["Publish"] = (publish[0].replace(/^\s*|\[|\]/g,''));
place1[1] = place1[1].replace(/^\s*|\s*$|\[|\]/g, '');
if (place1[1].match("/?")) {
var dateLength = place1[1].length-5;
} else {
var dateLength = place1[1].length-4;
}
dataTags["Date"] = place1[1].substr(dateLength);
} else {
dataTags["Date"] = (contents);
}
//tags
} else if (fieldTitle == "Subjects" | fieldTitle == "Sujets") {
fieldTitle = "Subjects";
tagsContent = contents.split("\n");
//source
} else if (fieldTitle == "Source") {
dataTags[fieldTitle] = (contents.replace(/^\s*|\s*$/g, ''));
dataTags["Source"] = ("Source: " + dataTags["Source"]);
Zotero.debug(doc.title);
//normal
} else {
dataTags[fieldTitle] = (contents.replace(/^\s*|\s*$/g, ''));
}
}
//series
if (fieldTitle == "Series" | fieldTitle == "Collection") {
fieldTitle = "Series";
dataTags[fieldTitle] = (contents.replace(/\s\s\s*/g, ''));
}
//makes tags
for (i = 0; i < tagsContent.length; i++) {
if (tagsContent[i] != ("") && tagsContent[i] !=(" ")) {
newItem.tags[i] = tagsContent[i];
}
}
associateData (newItem, dataTags, "Description", descriptionField);
associateData (newItem, dataTags, "Title", "title");
associateData (newItem, dataTags, "Place", "place");
associateData (newItem, dataTags, "Publish", "publisher");
associateData (newItem, dataTags, "Date", "date");
associateData (newItem, dataTags, "Source", "extra");
associateData (newItem, dataTags, "ISBN", "ISBN");
associateData (newItem, dataTags, "Localinf.", "rights");
associateData (newItem, dataTags, "Series", "series");
associateData (newItem, dataTags, "Notes", "abstractNote");
associateData (newItem, dataTags, "Numbering", "reportNumber");
associateData (newItem, dataTags, "Titre", "title");
associateData (newItem, dataTags, "Numérotation", "reportNumber");
}
newItem.url = doc.location.href;
newItem.complete();
}
function doWeb(doc, url) {
var namespace = doc.documentElement.namespaceURI;
var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null;
} : null;
if (detectWeb(doc, url) == "multiple") {
var items = new Object();
var next_title = new Array();
var links1 = new Array();
var y = 0;
var next_title1 = new Array();
var titlesCount = doc.evaluate('count (//p/table/tbody/tr/td/b)', doc, nsResolver, XPathResult.ANY_TYPE, null);
var numAndTitle= doc.evaluate('//p/table/tbody/tr/td/b', doc, nsResolver, XPathResult.ANY_TYPE, null);
var links = doc.evaluate('//p/table/tbody/tr/td/a[img]', doc, nsResolver, XPathResult.ANY_TYPE, null);
var multipleTest = 0;
for (j=0; j < titlesCount.numberValue; j++) {
next_title[j] = numAndTitle.iterateNext().textContent;
next_title[j] = next_title[j].substr(0, next_title[j].length-1);
if (/^\d*$/.test(next_title[j])) {
multipleTest = 0;
} else if (multipleTest < 1) {
multipleTest++;
next_title1[y] = next_title[j];
y++;
Zotero.debug(next_title1[0]);
} else if (multipleTest > 1) {
multipleTest = 0;
}
}
for (j = 0; j < 10; j++) {
links1[j] = links.iterateNext().href;
//Zotero.debug(links1[0]);
items[links1] = next_title1[j];
}
Zotero.selectItems(items, function(items) {
if (!items) return true;
var articles = [];
for (var i in items) {
articles.push(i);
}
ZU.processDocuments(articles, scrape);
});
} else {
ZU.processDocuments([url], scrape);
}
}