Wall_Street_Journal.js.in

{
    "translatorID"   : "fd0556d5-4c99-43d2-96d2-479284a0ae31",
    "translatorType" : 4,
    "label"          :"Wall Street Journal",
    "creator"        :"Erik Hetzner, based on work by Matt Burton",
    "target"         :"http://online\\.wsj\\.com/article/",
    "minVersion"     :"2.0",
    "maxVersion"     :"",
    "priority"       :100,
    "inRepository"   :true,
    "lastUpdated"    :"2010-06-24 08:20:02"
}

//@framework@

function detectWeb(doc, url) { return FW.detectWeb(doc, url); }

function doWeb(doc, url) { return FW.doWeb(doc, url); }

FW.Scraper({ 
  itemType         : 'newspaperArticle',
  publicationTitle : "wsj.com",
  creators         : FW.PageText().match(/authors:'(.*?)'(?=,|})/, 1).
                       replace("+", " ", "g").
                       unescapeHTML().
                       unescape().
                       split(/,/).
                       cleanAuthor("author"),
  abstractNote     : FW.PageText().match(/bodyText:'(.*?)'(?=,|})/, 1).
                       replace("+", " ", "g").
                       unescapeHTML().
                       unescape(),
  date             : FW.PageText().match(/publicationDate:'(.*?)'(?=,|})/, 1).
                       replace("+", " ", "g").
                       unescapeHTML().
                       unescape(),
  title            : FW.PageText().match(/articleHeadline:'(.*?)'(?=,|})/, 1).
                       replace("+", " ", "g").
                       unescapeHTML().
                       unescape().
                       replace(/\\/, ""),
  section          : FW.PageText().match(/articleType:'(.*?)'(?=,|})/, 1).
                       replace("+", " ", "g").
                       unescapeHTML().
                       unescape(),
  attachments      : {
    url            : FW.Url(),
    type           : "text/html",
    title          : "Wall Street Journal Snapshot"
  }
});