extraer campos del Boe formato pdf

boe.groovy

@Grab(group='org.apache.pdfbox', module='pdfbox', version='2.0.8')
import org.apache.pdfbox.pdmodel.PDDocument
import org.apache.pdfbox.text.*
import java.awt.Rectangle
margenright = 10   

def model=[:]

txtboe = new PDFTextStripper().getText( PDDocument.load( new URL("https://www.boe.es/boe/dias/2015/09/12/pdfs/BOE-A-2015-9803.pdf").bytes ) )
txtboe = txtboe.replaceAll('\n',' ')
//println txtboe

match = txtboe =~ /<E([0-9\.]+)\s+(.+?)>/
match.each{ token ->
     model[token[1]]=token[2]
}

match = txtboe =~ /<E([0-9\.:T]+)\s+(.+?)>/
match.each{ token ->
    model[token[1]]=token[2]
}

model.sort().each{
	println it.key +' '+it.value
}