suzanne.soy/zotero
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Modified Old Bailey translator to support saving search results as item

Browse Source
This commit is contained in:
Fred Gibbs 2011-01-10 16:44:59 +00:00
parent f2bcb72fde
commit ffdb3fb095
1 changed files with 66 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

73
translators/Old Bailey Online.js
View File

@ -8,7 +8,7 @@
"maxVersion":"", "maxVersion":"",
"priority":100, "priority":100,
"inRepository":true, "inRepository":true,
"lastUpdated":"2008-08-11 20:40:00" "lastUpdated":"2011-01-10 20:40:00"
} }
function detectWeb(doc, url) { function detectWeb(doc, url) {
@ -19,8 +19,6 @@ function detectWeb(doc, url) {
} }
} }
//Old Bailey Online translator. Code by Adam Crymble
function scrape(doc, url) { function scrape(doc, url) {
var namespace = doc.documentElement.namespaceURI; var namespace = doc.documentElement.namespaceURI;
@ -65,14 +63,14 @@ function scrape(doc, url) {
if (fieldTitle != "ReferenceNumber:") { if (fieldTitle != "ReferenceNumber:") {
tagsContent.push(contentsArray[j]); tagsContent.push(contentsArray[j]);
} else { } else {
newItem.extra = contentsArray[j]; refNum = contentsArray[j];
newItem.extra = refNum;
} }
j++; j++;
} }
} else { } else {
if (oneHeader.match("Reference")) { if (oneHeader.match("Reference")) {
newItem.extra = contents; newItem.extra = contents;
} else { } else {
newItem.tags = contents; newItem.tags = contents;
@ -99,6 +97,7 @@ function doWeb(doc, url) {
} : null; } : null;
var articles = new Array(); var articles = new Array();
var onlyResultSet = false;
if (detectWeb(doc, url) == "multiple") { if (detectWeb(doc, url) == "multiple") {
var items = new Object(); var items = new Object();
@ -109,22 +108,76 @@ function doWeb(doc, url) {
while (next_title = titles.iterateNext()) { while (next_title = titles.iterateNext()) {
items[next_title.href] = next_title.textContent; items[next_title.href] = next_title.textContent;
} }
// add option to save search URL as single item
items["resultSet"] = "Save search URL as item";
items = Zotero.selectItems(items); items = Zotero.selectItems(items);
for (var i in items) { for (var i in items) {
articles.push(i); articles.push(i);
} }
} else if (doc.evaluate('//div[@id="main2"]/p/a', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) { // if option to save result set is selected
if (items["resultSet"]) {
if (articles.length == 1) {
onlyResultSet = true;
}
var newItem = new Zotero.Item("case");
newItem.title = 'Old Bailey Search Result Set';
var searchURL = doc.location.href;
newItem.url = searchURL;
// define dictionary for easier reading
var defs = {
"_divs_fulltext": "Keywords",
"_persNames_surname": "Surname",
"_persNames_given": "Given name",
"_persNames_alias": "Alias",
"_offences_offenceCategory_offenceSubcategory": "Offence",
"_verdicts_verdictCategory_verdictSubcategory": "Verdicts",
"_punishments_punishmentCategory_punishmentSubcategory": "Punishment",
"_divs_div0Type_div1Type": "Corpus",
"fromMonth": "From month",
"fromYear": "From year",
"toMonth": "To month",
"toYear": "To year"
};
// parse URL into human-readable elements
var noteText = '<b>Search Parameters</b><br/>';
var re = /(?:\?|&(?:amp;)?)([^=]+)=?([^&]*)?/g;
var match;
var key='';
while (match = re.exec(searchURL)) {
if (defs[match[1]] != null) {
key = defs[match[1]];
noteText += key + ": " + unescape(match[2]) + "<br/>";
}
}
// save them in the notes field
newItem.notes.push({note: noteText});
newItem.complete();
// remove dummy url for result set from articles list
articles.pop();
}
}
else if (doc.evaluate('//div[@id="main2"]/p/a', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext()) {
var xmlOrText = doc.evaluate('//div[@id="main2"]/p/a', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext(); var xmlOrText = doc.evaluate('//div[@id="main2"]/p/a', doc, nsResolver, XPathResult.ANY_TYPE, null).iterateNext();
if (xmlOrText.textContent.match("Text")) { if (xmlOrText.textContent.match("Text")) {
articles = [xmlOrText.href]; articles = [xmlOrText.href];
}
} else { else {
articles = [url]; articles = [url];
} }
} }
Zotero.Utilities.processDocuments(articles, scrape, function() {Zotero.done();}); if (!onlyResultSet) {
Zotero.wait(); Zotero.Utilities.processDocuments(articles, scrape, function() {Zotero.done();});
Zotero.wait();
}
} }