Hi, In fact, you have to launch the OCR before runing the script.
On your invoices, sometime there is a space between "No." and the ":" symbol and sometime there is no space.
I modifyed a bit the script for catching both configurations and I found 60 invoices separated from your original example. Please check if this number is correct!
Here is the script:
console.show();
console.clear();
d0=new Date();
debut=util.printd("dd-mm HH:MM",d0);
laDate=util.printd("dd-mm-yy",d0);
var invoices=[];
for (var p=0; p<this.numPages; p++) {
console.clear();
console.println("Process Starting: "+debut);
console.println("––––––––––––––");
console.println("Invoice number searching on page "+(p+1));
console.println(invoices.length+" invoices found");
var nbWords=this.getPageNumWords(p);
for (var i=0; i<nbWords-1; i++) {
if (this.getPageNthWord(p, i, false).indexOf("No.:")==0 && !isNaN(this.getPageNthWord(p, i+1, true)) && this.getPageNthWord(p, i+1, true).length==6) {
invoices.push([p,this.numPages-1,this.getPageNthWord(p, i+1, true)]);
if (invoices.length>1) invoices[(invoices.length-2)][1]=(p-1);
break;
} else if (this.getPageNthWord(p, i, false).indexOf("No.")==0 && this.getPageNthWord(p, i+1, false).indexOf(":")==0 && !isNaN(this.getPageNthWord(p, i+2, true)) && this.getPageNthWord(p, i+2, true).length==6) {
invoices.push([p,this.numPages-1,this.getPageNthWord(p, i+2, true)]);
if (invoices.length>1) invoices[(invoices.length-2)][1]=(p-1);
break;
}
}
}
var newPath=this.path.replace(this.documentFileName,"New Documents/");
for (var i=0; i<invoices.length; i++) {
console.clear();
console.println("Process Starting: "+debut);
console.println("––––––––––––––");
console.println("Extracting invoice number "+invoices[i][2]);
this.extractPages({
nStart: invoices[i][0],
nEnd: invoices[i][1],
cPath: newPath+invoices[i][2]+".pdf"
})
}
df=new Date();
fin=util.printd("dd-mm HH:MM",df);
temps=(df.valueOf()-d0.valueOf())/1000/60;
var lesMinutes=parseInt(temps);
var lesSecondes=(temps-lesMinutes)*60;
var lesSecondes=parseInt(lesSecondes*10)/10;
var leTemps="";
if (lesMinutes>0) {
if (lesMinutes==1) {
var leTemps="1 minute";
} else {
var leTemps=lesMinutes+" minutes";
}
}
if (lesSecondes>0) {
if (lesSecondes<2) {
var leTemps=leTemps+" "+lesSecondes+" second"
} else {
var leTemps=leTemps+" "+lesSecondes+" seconds"
}
}
var leTemps=leTemps.replace(/^\s+|\s+$/gm,"");
console.clear();
console.println("Process Starting: "+debut);
console.println("Process Ending: "+fin);
console.println("––––––––––––––");
console.println("Process Duration: "+leTemps);
console.println(invoices.length+" invoices extracted.");
I'll send you by e-mail the file after the OCR, which one I worked with...
@+
... View more
AdChoices