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

Updated and pushed Wall Street Journal

Browse source 
- Removed unused namespace stuff
- Remove extra comments
- Remove item.accessed line, since access date is added automatically
- Add snapshot
This commit is contained in:
Dan Stillman 2009-07-31 11:14:15 +00:00
parent 8e63dd5a4a
commit 5d14581ca5
1 changed files with 7 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
translators/wsj.js
View file

@ -8,28 +8,19 @@
"maxVersion":"",
"priority":100,
"inRepository":true,
"lastUpdated":"2008-07-29 19:40:00"
"lastUpdated":"2009-07-31 11:15:00"
}
function detectWeb(doc, url){
return "newspaperArticle"
}
function getDatum(text, key){
Zotero.debug(key);
var reg = new RegExp(key+":'(.*?)'(?=,|})");
return unescape(Zotero.Utilities.unescapeHTML(reg.exec(text)[1].replace("+"," ", "g")));
}
function doWeb(doc, url){
var namespace = doc.documentElement.namespaceURI;
var nsResolver = namespace ? function(prefix) {
if (prefix == 'x') return namespace; else return null;
} : null;
var text = doc.documentElement.innerHTML;
var item = new Zotero.Item("newspaperArticle");
var metadata = text.match(/AT_VARS=({[^}]*})/)[1];
@ -38,12 +29,12 @@ function doWeb(doc, url){
item.creators.push(Zotero.Utilities.cleanAuthor(aut, "author"));
}
item.publicationTitle = Zotero.Utilities.unescapeHTML(metadata.match(/publicationName:'([^'][^,]*)'/)[1]);
item.date = getDatum(text, "publicationDate"); //Zotero.Utilities.unescapeHTML(metadata.match(/publicationDate:'([^']*[^,]*)'/)[1]);
item.abstractNote = getDatum(text, "bodyText"); //Zotero.Utilities.unescapeHTML(metadata.match(/bodyText:'([^']*[^,]*)'/)[1]).replace("+"," ", "g");
item.title = getDatum(text, "articleHeadline").replace("\\",""); //Zotero.Utilities.unescapeHTML(metadata.match(/articleHeadline:'([^']*[^,]*)'/)[1]).replace("\\","");
item.date = getDatum(text, "publicationDate");
item.abstractNote = getDatum(text, "bodyText");
item.title = getDatum(text, "articleHeadline").replace("\\","");
item.url = url;
item.accessed = Date();
item.section = getDatum(text, "articleType"); //Zotero.Utilities.unescapeHTML(metadata.match(/articleType:'([^']*[^,]*)'/)[1]).replace("+"," ", "g");
item.complete();
item.section = getDatum(text, "articleType");
item.attachments.push({url:url, title:"Wall Street Journal Snapshot", mimeType:"text/html"});
item.complete();
}