Extract not all text
yanosh-igor opened this issue · 3 comments
yanosh-igor commented
From this html page
<HTML xmlns="http://www.w3.org/1999/xhtml"><HEAD><TITLE>Sales Associate</TITLE>
<META content=text/javascript http-equiv=Content-Script-Type>
<META content=text/css http-equiv=Content-Style-Type>
<META content="text/html; charset=UTF-8" http-equiv=Content-Type>
<META content=IE=EmulateIE7 http-equiv=X-UA-Compatible>
<SCRIPT type=text/javascript>
var deviceMode="desktop";
</SCRIPT>
<LINK rel=icon type=image/x-icon href="https://wfa.kronostm.com/static/core/images/favicon_blnk.ico"><LINK rel="shortcut icon" type=image/x-icon href="https://wfa.kronostm.com/static/core/images/favicon_blnk.ico"><!-- Dependencies -->
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/yui-2.7.0/build/yahoo/yahoo-min.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/yui-2.7.0/build/event/event-min.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/yui-2.7.0/build/dom/dom-min.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/yui-2.7.0/build/logger/logger-min.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/yui-2.7.0/build/element/element-min.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/yui-2.7.0/build/cookie/cookie-min.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/scripts/combined-4740157.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/scripts/validation_en_US-min-4740157.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/WebKitDetect-min.js"></SCRIPT>
<SCRIPT type=text/javascript>
var tbCloseLabel="Close";
</SCRIPT>
<LINK rel=stylesheet type=text/css href="https://wfa.kronostm.com/common/jsutils/thickbox/thickbox-min.css">
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/thickbox/jquery-1.4.4.min.js"></SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/thickbox/thickbox-min.js"></SCRIPT>
<SCRIPT type=text/javascript>
if ( (BrowserDetect.browser=="Opera") ||
(BrowserDetect.browser=="Netscape" && BrowserDetect.version<"7.2")
|| (BrowserDetect.browser=="Safari" && BrowserDetect.version>"48" && BrowserDetect.version<"420")
)
{
window.location = "browserError.jsp"
}
var ataoDebug = false;
function initLogger() {};
Deploy.events.clientEventData = {"SLOT_0_3_3_10":{"ISACTIVELOCATION":true,"ISACTIVEPOSTING":true},"SLOT_0_3_3_14_2":{"ISACTIVELOCATION":true,"APPLYLINK":"?LOCATION_ID=51516916603&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=returningMemberLoginOrRegister&POSTING_ID=46224061705","NAVIGATEREFERJOB":"?LOCATION_ID=51516916603&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=jobReferral&POSTING_ID=46224061705&sourceSeq=postingLocationDetails","ISACTIVEPOSTING":true},"SLOT_0_3_3_1_0":{"NAVIGATERETURNING":"?FROMJAF=false&INDEX=0&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=returningMembers","HMCHELPPREFIX":"/","NAVIGATEREGISTRATION":"?FROMJAF=false&INDEX=0&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=registration","SHOWEXPLICITREGISTRATIONMODE":true,"NAVIGATELOGOUT":"?logout=1&applicationName=SpecialtyRetailersNonReqExt&locale=en_US","ISGUEST":true},"SLOT_0_3_3_12_2":{"LOCATIONPOSTINGDETAILS":"true","NAVIGATETOLOCATIONJOBS":"?LOCATION_ID=51516916603&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=locationDetails&APPLYALLJOBS=true","POSTINGEXISTS":"true","NAVIGATETOANYJOBAPPLY":"?LOCATION_ID=51516916603&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=returningMemberLoginOrRegister&APPLYALLJOBS=true","OPENINGSENABLED":"false"}};
var initCompleteEvent = new YAHOO.util.CustomEvent("initCompleteEvent");
var compiledInit = function () {
initLogger();
YAHOO.util.Event.addListener(document.body, 'click', Deploy.eventHandler);
initializeThickBox();
if (initCompleteEvent != null) {initCompleteEvent.fire();}
};
YAHOO.util.Event.addListener(window, "load", compiledInit);
Deploy.globalText = {};
YAHOO.util.Event.onAvailable("messageContainer", populateMessages);
//-->
</SCRIPT>
<LINK rel=STYLESHEET type=text/css href="https://wfa.kronostm.com/styles/combined-4740157.css"><LINK rel=STYLESHEET type=text/css href="https://wfa.kronostm.com/styles/style_en_US-min-4740157.css"><LINK rel=STYLESHEET type=text/css href="https://wfa.kronostm.com/assets/SpecialtyRetailersNonReqExt_CIBranding/css/customer.css"><LINK rel=stylesheet type=text/css href="https://wfa.kronostm.com/styles/print-min-4740157.css" media=print><LINK rel=STYLESHEET type=text/css href="https://wfa.kronostm.com/styles/ie-4740157.css">
<SCRIPT language=JavaScript type=text/javascript>
var windowBeforeUnloadMsg = '';
setHookOnWindowBeforeUnload(false);
<!-- Begin Pre-loading the page *************
function clearPreloadDiv() { //DOM
if (document.getElementById('prePageDiv')) {
document.getElementById('prePageDiv').style.display='none';
}
}
if(/MSIE/.test(navigator.userAgent)){
YAHOO.util.Event.onDOMReady(clearPreloadDiv);
}
// End Pre-loading of the page ****************-->
</SCRIPT>
</HEAD>
<BODY id=DeployMainBody class=yui-skin-sam>
<DIV id=displayWait></DIV>
<DIV id=prePageDiv class=preLoadDiv style="DISPLAY: none"> </DIV><NOSCRIPT></NOSCRIPT>
<DIV id=header><!-- view div[jspviews/customerHeader.jsp] --><IFRAME id=customerHeader title="Customer Header" src="https://wfa.kronostm.com/static/SpecialtyRetailers/NonReqExt/Stage_Stores_Header.html" frameBorder=0 scrolling=no>
</IFRAME><!--
<img id="printLogo" src="https://wfa.kronostm.com/static/core/images/print_kronos.gif" alt="Logo for print version" />
--></DIV>
<DIV id=wrapper class=noFluid>
<DIV id=bodyContainer>
<DIV id=sidenav>
<DIV id=Slot_0_3_3_0_0><!-- view div[jspviews/customerSideNav.jsp] --><IFRAME id=customerLeftNav title="Customer Side Navigation" src="https://wfa.kronostm.com/static/core/core_leftnav.htm" frameBorder=0 scrolling=no>
</IFRAME></DIV></DIV>
<DIV id=navGroup class=fullCol>
<DIV id=loginnav><!-- view div[jspviews/loginNav.jsp] -->
<DIV id=member><A id=Div0 class=nav href="https://wfa.kronostm.com/?FROMJAF=false&INDEX=0&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=returningMembers"><SPAN><STRONG>Sign In</STRONG></SPAN></A> | Not a Member? <A id=Div2 class=nav href="https://wfa.kronostm.com/?FROMJAF=false&INDEX=0&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=registration"><SPAN>Join Now!</SPAN></A> </DIV></DIV>
<DIV id=nav><!-- view div[jspviews/nav.jsp] --><IFRAME id=shimIFrame title="Nav Menu Helper" style="HEIGHT: 22px; WIDTH: 120px; POSITION: absolute; LEFT: 0px; Z-INDEX: 1; DISPLAY: none; TOP: 0px" src="https://wfa.kronostm.com/common/IEFrameWarningBypass.htm" frameBorder=0 scrolling=no></IFRAME>
<DIV id=menuBar>
<DIV class=menuItemNoSub><A id=Div3 class=nav href="https://wfa.kronostm.com/?seq=home&applicationName=SpecialtyRetailersNonReqExt&locale=en_US"><SPAN>Home</SPAN></A> </DIV>
<DIV class=menuItemNoSub><A id=Div4 class=nav href="https://wfa.kronostm.com/?seq=allOpenJobs&applicationName=SpecialtyRetailersNonReqExt&locale=en_US&allOpenJobs=true"><SPAN>All Open Jobs</SPAN></A> </DIV>
<DIV class=menuItemNoSub><A id=Div5 class=nav href="https://wfa.kronostm.com/?seq=allLocations&applicationName=SpecialtyRetailersNonReqExt&locale=en_US&showAllLocations=true&EVENT=com.deploy.application.hourly.plugin.LocationSearch.doSearch"><SPAN>Jobs by Location</SPAN></A> </DIV>
<DIV class=menuItemNoSub><A id=Div6 class=nav href="https://wfa.kronostm.com/?seq=grand_opening&applicationName=SpecialtyRetailersNonReqExt&locale=en_US"><SPAN>Grand Openings</SPAN></A> </DIV></DIV></DIV></DIV>
<DIV id=Slot_0_3_3_10 class=fullCol><!-- view div[jspviews/positionTitle.jsp] -->
<H1>Sales Associate</H1>Location: <STRONG>Menomonie, WI (1501 N Broadway, Ste 1590)</STRONG>
<DIV id=messageContainer></DIV></DIV>
<DIV id=caSidebar>
<DIV id=Slot_0_3_3_12_2><!-- view div[jspviews/locationInfo.jsp] -->
<DIV class=sidebar>
<H3>Location Details </H3>
<DIV style="MARGIN: 4px"><LABEL class=inline><STRONG>Stage Stores (Bealls, Goody's, Palais Royal, Peebles & Stage)</STRONG> </LABEL><BR><SPAN class="field readOnly">1501 N Broadway, Ste 1590</SPAN><BR><SPAN class="field readOnly">Menomonie</SPAN>, <SPAN class="field readOnly">WI</SPAN> <SPAN class="field readOnly">54751</SPAN><BR>
<DIV class="emphasized label inline">P:</DIV><SPAN class="field readOnly">715-233-2038</SPAN> </DIV>
<P><SPAN class=pColor>»</SPAN> <A id=Div10 class="field readOnly" href="https://wfa.kronostm.com/?LOCATION_ID=51516916603&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=locationDetails&APPLYALLJOBS=true"><SPAN>See all jobs at this location</SPAN></A> </P></DIV></DIV>
<DIV id=Slot_0_3_3_12_4><!-- view div[jspviews/applyNow.jsp] --></DIV></DIV>
<DIV id=caMain>
<DIV id=Slot_0_3_3_14_2><!-- view div[jspviews/positionLocationDetails.jsp] -->
<DIV id=fullCol>
<DIV class=nonform>
<DIV>
<H4>
<DIV class=formRow>
<DIV class="h2Label inline"><LABEL class="h2Label inline">Job Description<IMG style="DISPLAY: none" src="https://pixel.appcast.io/kronost-te8/a31.png?e=366&t=1413902884" width=1 height=1> <IMG style="DISPLAY: none" src="https://pixel.appcast.io/kronost-te8/a31.png?e=394&t=1415396593" width=1 height=1> <IMG style="DISPLAY: none" src="https://pixel.appcast.io/kronost-te8/a31.png?e=393&t=1415396329" width=1 height=1></LABEL> </DIV> </DIV></H4>
<DIV class=formattedContent>
<P><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">REPORTS TO: </SPAN></SPAN><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Store Manager/Assistant Manager</SPAN></SPAN></P>
<P><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">OBJECTIVE: </SPAN></SPAN></P>
<P><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">To greet and assist customers with the selection of merchandise</SPAN></SPAN></P>
<P><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">RESPONSIBILITIES:</SPAN></SPAN></P>
<P><STRONG><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Customer Service</SPAN></SPAN></STRONG></P>
<UL>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Smile and greet each customer promptly</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Interrupt store tasks to greet, assist, and answer questions for customers</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Suggest additional merchandise to customers on sales floor, at wrap stations, and in fitting rooms</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Follow-up on customers in fitting rooms to see if they need additional service</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Thank the customer by name and invite them to come back at the close of each sale</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Handle all returns/ exchanges according to company policies/ procedures, including Always Say Yes</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Maintain the store and all wrap stations in a clean, neat, and organized manner</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Opt-In (telephone and email capture)</SPAN></SPAN> </LI></UL>
<P><STRONG><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Personal Productivity</SPAN></SPAN></STRONG></P>
<UL>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Sales</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Volume Per Hour (VPH)</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Units Per Transaction (UPT)</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">New Accounts</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Club 50</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Magazines</SPAN></SPAN>
<LI>Opt-In (telephone and email capture) </LI></UL>
<P><STRONG><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Loss Prevention</SPAN></SPAN></STRONG></P>
<UL>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Provide customer service</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Alert management of suspicious situations</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Follow store procedures</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Work with integrity</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Follow sensor tagging program (if applicable)</SPAN></SPAN> </LI></UL>
<P><STRONG><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Credit</SPAN></SPAN></STRONG></P>
<UL>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Ask every customer to open a new account </SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Open and activate a minimum of (1) one new account per month </SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Always suggest purchase using company charge card</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Communicate the Premier Rewards Program</SPAN></SPAN> </LI></UL>
<P><STRONG><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Merchandise Presentation</SPAN></SPAN></STRONG></P>
<UL>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Hang, Fold, Size, Sensor (where applicable), Sign and Steam (where applicable)</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Implement merchandising Floor Plans/guidelines</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Ensure featured merchandise is appropriately layered to suggest possible wardrobe ideas to the customer</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Follow "Folded Merchandise Guidelines"</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Create and maintain full, exciting displays</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Present clearance merchandise correctly</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">"Close to Open"</SPAN></SPAN> </LI></UL>
<P><STRONG><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Store Operations</SPAN></SPAN></STRONG></P>
<UL>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Set-up Sales Event prior to sale start date (to include signing)</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Complete Price Changes (PCA's) by close of business on the effective date</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Complete Transfers by close of business on the effective date</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Complete Damages by close of business on the effective date</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Merchandise counts </SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Process in-coming freight including hanging, folding, sensor-tagging, etc</SPAN></SPAN>
<LI><SPAN style="FONT-FAMILY: arial, sans-serif"><SPAN style="FONT-SIZE: 10pt">Housekeeping responsibilities including vacuuming, dusting, restrooms, etc</SPAN></SPAN> </LI></UL></DIV></DIV>
<DIV class=formRow>
<DIV class="emphasized label h2Label">Job Preview Video</DIV>
<DIV class=formattedContent><EMBED type=application/x-shockwave-flash height=390 width=640 src=https://www.youtube.com/v/22WFbDceaUM allowScriptAccess="always" allowfullscreen="true"> </DIV></DIV></DIV>
<DIV class="controlRow centered"><A id=Div11 class=largeButton href="https://wfa.kronostm.com/?LOCATION_ID=51516916603&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=returningMemberLoginOrRegister&POSTING_ID=46224061705"><SPAN>Apply Now</SPAN></A> </DIV>
<DIV class=controlRow><A id=Div12 class="iconMiniEmail icon-16 noline" href="https://wfa.kronostm.com/?LOCATION_ID=51516916603&locale=en_US&applicationName=SpecialtyRetailersNonReqExt&SEQ=jobReferral&POSTING_ID=46224061705&sourceSeq=postingLocationDetails"><SPAN>Refer This Job</SPAN></A> </DIV></DIV></DIV>
<DIV id=Slot_0_3_3_14_4><!-- view div[jspviews/applyNow.jsp] --></DIV></DIV>
<DIV id=caFooterGroup class=fullCol>
<DIV id=caFooter><!-- view div[jspviews/caFooter.jsp] -->
<DIV class=copyrightText><SPAN style="VERTICAL-ALIGN: top">Copyright © 2000 - 2015</SPAN> by Kronos Incorporated. All rights reserved. <SPAN style="VERTICAL-ALIGN: top"> | <A href="http://www.kronos.com/Privacy.htm" data-role="none">Privacy Policy</A></SPAN> </DIV>
<DIV class=patentsText><SPAN class=patents>U. S. Patents 7,080,057; 7,310,626; 7,558,767; 7,562,059;</SPAN> 7,472,097; 7,606,778; 8,086,558 and 8,046,251. </DIV>
<SCRIPT type=text/javascript>
var KronosUTMDomain = "kronostm.com"; // default SysVar value: "auto"
var KronosUTMGifPath = "https://wfsa-img.kronostm.com/__utm.gif"; // default SysVar value: "common/jsutils/urchin/__utm.gif"
</SCRIPT>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/common/jsutils/urchin/urchin.js"></SCRIPT>
<SCRIPT type=text/javascript>
// Urchin tracking (UTM)
urchinTracker();
</SCRIPT>
</DIV></DIV></DIV></DIV>
<DIV id=footer><!-- view div[jspviews/customerFooter.jsp] --><IFRAME id=customerFooter title="Customer Footer" src="https://wfa.kronostm.com/static/core/core_footer.htm" frameBorder=0 scrolling=no>
</IFRAME></DIV>
<DIV id=footer>
<SCRIPT type=text/javascript src="https://wfa.kronostm.com/scripts/tools-min-4740157.js"></SCRIPT>
</DIV>
<SCRIPT>window.alert = function mozendaDoNothing() {}</SCRIPT>
<SCRIPT>window.confirm = function mozendaReturnTrue() {return true;}</SCRIPT>
<SCRIPT>
if (!window.console)
window.console = {};
// union of Chrome, FF, IE, and Safari console methods
var m =
[
'log', 'info', 'warn', 'error', 'debug', 'trace', 'dir', 'group',
'groupCollapsed', 'groupEnd', 'time', 'timeEnd', 'profile', 'profileEnd',
'dirxml', 'assert', 'count', 'markTimeline', 'timeStamp', 'clear'
];
// define undefined methods to prevent errors
for (var i = 0; i < m.length; i++)
{
if (!window.console[m[i]])
window.console[m[i]] = function() {};
}
window.console.log = function (debugStatement) { window.external.Log(debugStatement); }
</SCRIPT>
<SCRIPT>window.open = function mozendaWindowOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModalDialog = function mozendaWindowShowModalDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModelessDialog = function mozendaWindowShowModlessDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>document.open = function mozendaDocumentOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
</BODY></HTML>
<HTML><HEAD><TITLE>Welcome to Stage Stores</TITLE>
<META http-equiv=Content-Type content="text/html; charset=iso-8859-1"></HEAD>
<BODY style="MARGIN: 0px"><IMG alt="Speciality Retailers" src="https://wfa.kronostm.com/images/Stage" Stores_CE.gif;pv99535325afb22125">
<SCRIPT>window.alert = function mozendaDoNothing() {}</SCRIPT>
<SCRIPT>window.confirm = function mozendaReturnTrue() {return true;}</SCRIPT>
<SCRIPT>
if (!window.console)
window.console = {};
// union of Chrome, FF, IE, and Safari console methods
var m =
[
'log', 'info', 'warn', 'error', 'debug', 'trace', 'dir', 'group',
'groupCollapsed', 'groupEnd', 'time', 'timeEnd', 'profile', 'profileEnd',
'dirxml', 'assert', 'count', 'markTimeline', 'timeStamp', 'clear'
];
// define undefined methods to prevent errors
for (var i = 0; i < m.length; i++)
{
if (!window.console[m[i]])
window.console[m[i]] = function() {};
}
window.console.log = function (debugStatement) { window.external.Log(debugStatement); }
</SCRIPT>
<SCRIPT>window.open = function mozendaWindowOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModalDialog = function mozendaWindowShowModalDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModelessDialog = function mozendaWindowShowModlessDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>document.open = function mozendaDocumentOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
</BODY></HTML>
<HTML><HEAD><TITLE>Untitled Document</TITLE>
<META http-equiv=Content-Type content="text/html; charset=iso-8859-1"></HEAD>
<BODY>Core Sidenav
<SCRIPT>window.alert = function mozendaDoNothing() {}</SCRIPT>
<SCRIPT>window.confirm = function mozendaReturnTrue() {return true;}</SCRIPT>
<SCRIPT>
if (!window.console)
window.console = {};
// union of Chrome, FF, IE, and Safari console methods
var m =
[
'log', 'info', 'warn', 'error', 'debug', 'trace', 'dir', 'group',
'groupCollapsed', 'groupEnd', 'time', 'timeEnd', 'profile', 'profileEnd',
'dirxml', 'assert', 'count', 'markTimeline', 'timeStamp', 'clear'
];
// define undefined methods to prevent errors
for (var i = 0; i < m.length; i++)
{
if (!window.console[m[i]])
window.console[m[i]] = function() {};
}
window.console.log = function (debugStatement) { window.external.Log(debugStatement); }
</SCRIPT>
<SCRIPT>window.open = function mozendaWindowOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModalDialog = function mozendaWindowShowModalDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModelessDialog = function mozendaWindowShowModlessDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>document.open = function mozendaDocumentOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
</BODY></HTML>
<HTML xmlns="http://www.w3.org/1999/xhtml"><HEAD></HEAD>
<BODY>
<SCRIPT>window.alert = function mozendaDoNothing() {}</SCRIPT>
<SCRIPT>window.confirm = function mozendaReturnTrue() {return true;}</SCRIPT>
<SCRIPT>
if (!window.console)
window.console = {};
// union of Chrome, FF, IE, and Safari console methods
var m =
[
'log', 'info', 'warn', 'error', 'debug', 'trace', 'dir', 'group',
'groupCollapsed', 'groupEnd', 'time', 'timeEnd', 'profile', 'profileEnd',
'dirxml', 'assert', 'count', 'markTimeline', 'timeStamp', 'clear'
];
// define undefined methods to prevent errors
for (var i = 0; i < m.length; i++)
{
if (!window.console[m[i]])
window.console[m[i]] = function() {};
}
window.console.log = function (debugStatement) { window.external.Log(debugStatement); }
</SCRIPT>
<SCRIPT>window.open = function mozendaWindowOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModalDialog = function mozendaWindowShowModalDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModelessDialog = function mozendaWindowShowModlessDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>document.open = function mozendaDocumentOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
</BODY></HTML>
<HTML><HEAD><TITLE>Untitled Document</TITLE>
<META http-equiv=Content-Type content="text/html; charset=iso-8859-1"></HEAD>
<BODY style="PADDING-BOTTOM: 10px; PADDING-TOP: 10px; PADDING-LEFT: 10px; MARGIN: 0px; PADDING-RIGHT: 10px; BACKGROUND-COLOR: #eee">Core Footer
<SCRIPT>window.alert = function mozendaDoNothing() {}</SCRIPT>
<SCRIPT>window.confirm = function mozendaReturnTrue() {return true;}</SCRIPT>
<SCRIPT>
if (!window.console)
window.console = {};
// union of Chrome, FF, IE, and Safari console methods
var m =
[
'log', 'info', 'warn', 'error', 'debug', 'trace', 'dir', 'group',
'groupCollapsed', 'groupEnd', 'time', 'timeEnd', 'profile', 'profileEnd',
'dirxml', 'assert', 'count', 'markTimeline', 'timeStamp', 'clear'
];
// define undefined methods to prevent errors
for (var i = 0; i < m.length; i++)
{
if (!window.console[m[i]])
window.console[m[i]] = function() {};
}
window.console.log = function (debugStatement) { window.external.Log(debugStatement); }
</SCRIPT>
<SCRIPT>window.open = function mozendaWindowOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModalDialog = function mozendaWindowShowModalDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>window.showModelessDialog = function mozendaWindowShowModlessDialog(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
<SCRIPT>document.open = function mozendaDocumentOpen(param1, param2, param3) { window.name = param2; if( param1 != null && param1 != "") window.location = param1; }</SCRIPT>
</BODY></HTML>
I'm geting only part of text:
| Not a Member?
» See all jobs at this location
To greet and assist customers with the selection of merchandise
Interrupt store tasks to greet, assist, and answer questions for customers
Suggest additional merchandise to customers on sales floor, at wrap stations, and in fitting rooms
Follow-up on customers in fitting rooms to see if they need additional service
Thank the customer by name and invite them to come back at the close of each sale
Handle all returns/ exchanges according to company policies/ procedures, including Always Say Yes
Maintain the store and all wrap stations in a clean, neat, and organized manner
Ask every customer to open a new account
Open and activate a minimum of (1) one new account per month
Hang, Fold, Size, Sensor (where applicable), Sign and Steam (where applicable)
Ensure featured merchandise is appropriately layered to suggest possible wardrobe ideas to the customer
Complete Price Changes (PCA's) by close of business on the effective date
Complete Transfers by close of business on the effective date
Complete Damages by close of business on the effective date
Could you please look into it.
ageitgey commented
Hi @yanosh-igor,
Thanks for filing this issue. I think the problem here is that the text you are trying to extract is mainly bulleted lists with lots of formatting. There's no big chunks of continuous text (like with an article or news story). So the library won't do a good job of finding and extracting the main text.
This library wasn't really designed to handle this kind of input and won't work well in this case. It's really designed for extracting news stories or other types of writing where there is multiple sentences of continuous text. I think unfluff just might not be the right tool for this job.
In your case, a more manual approach might be better.
For example, a simple jQuery function might work better here:
$(".formattedContent").text()
That would give you this output:
REPORTS TO: Store Manager/Assistant Manager
OBJECTIVE:
To greet and assist customers with the selection of merchandise
RESPONSIBILITIES:
Customer Service
Smile and greet each customer promptly
Interrupt store tasks to greet, assist, and answer questions for customers
Suggest additional merchandise to customers on sales floor, at wrap stations, and in fitting rooms
Follow-up on customers in fitting rooms to see if they need additional service
Thank the customer by name and invite them to come back at the close of each sale
Handle all returns/ exchanges according to company policies/ procedures, including Always Say Yes
Maintain the store and all wrap stations in a clean, neat, and organized manner
Opt-In (telephone and email capture)
Personal Productivity
Sales
Volume Per Hour (VPH)
Units Per Transaction (UPT)
New Accounts
Club 50
Magazines
Opt-In (telephone and email capture)
Loss Prevention
Provide customer service
Alert management of suspicious situations
Follow store procedures
Work with integrity
Follow sensor tagging program (if applicable)
Credit
Ask every customer to open a new account
Open and activate a minimum of (1) one new account per month
Always suggest purchase using company charge card
Communicate the Premier Rewards Program
Merchandise Presentation
Hang, Fold, Size, Sensor (where applicable), Sign and Steam (where applicable)
Implement merchandising Floor Plans/guidelines
Ensure featured merchandise is appropriately layered to suggest possible wardrobe ideas to the customer
Follow "Folded Merchandise Guidelines"
Create and maintain full, exciting displays
Present clearance merchandise correctly
"Close to Open"
Store Operations
Set-up Sales Event prior to sale start date (to include signing)
Complete Price Changes (PCA's) by close of business on the effective date
Complete Transfers by close of business on the effective date
Complete Damages by close of business on the effective date
Merchandise counts
Process in-coming freight including hanging, folding, sensor-tagging, etc
Housekeeping responsibilities including vacuuming, dusting, restrooms, etc
Thanks!
yanosh-igor commented
Thanks for explanations.
Xerillio commented
I think it would be relevant to describe this in the documentation/README. It's not apparent from the current description that it's not parsing pages with smaller chunks of text.