Download all Vukajlija posters from first 20 pages

DownloadVukajlijaImagesGPars.groovy

package vukajlija

@Grab(group='org.codehaus.gpars', module='gpars', version='0.11')

import java.text.Normalizer
import java.util.regex.Pattern
import java.util.concurrent.atomic.AtomicInteger
import groovyx.gpars.GParsExecutorsPool

def final MAX_PAGE = 20
def final targetDir = "d:/temp/_3"
def final REGEX_IMAGE = ~'src="([^"]+)"'

def list = new ArrayList()

def calc(processName, closure) {
    println "\nStarting process [$processName]"
    def begin = System.currentTimeMillis()
    closure()
    println "Process [$processName] done in ${System.currentTimeMillis() - begin}ms"
}

def String clean(String str) {
    String nfdNormalizedString = Normalizer.normalize(str, Normalizer.Form.NFD);
    Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");
    String retValue = pattern.matcher(nfdNormalizedString).replaceAll("");
    retValue = retValue.toLowerCase().replaceAll(' ', '-').replaceAll('[,.\\?/\\(\\)„“\\!«»’"]', '-')
    return retValue.replaceAll('-+','-').replaceAll('-+$','')
}

calc("filling up") {
    // filler
    def out = new StringWriter()
    GParsExecutorsPool.withPool(10) {
        (1..MAX_PAGE).eachParallel { strana ->
            def url = "http://vukajlija.com/zabava/posteri?strana=$strana"
            println "Fetching image URLs from page $url"
            out << new URL(url).openStream()
            out.close()

            String text = out.toString()
            text.eachMatch(REGEX_IMAGE) { image, imageFound ->
                if (imageFound.indexOf('/posters/') != -1) {
                    list << imageFound
                }
            }
        }
    }
}

list = new ArrayList(list.unique())
println "Unique Link count: ${list.size()}"

AtomicInteger newId = new AtomicInteger(0)

// instantiating workers
calc("downloading") {
    GParsExecutorsPool.withPool (10) {
        list.toArray().eachParallel { imageFound ->
            if (!Thread.currentThread().name.startsWith("Worker"))
                Thread.currentThread().name = "Worker${newId.incrementAndGet()}"
            if (!imageFound)
                return
            def filename ="${targetDir}/${clean(imageFound.tokenize('/')[-1])}.jpg"
            println "Thread ${Thread.currentThread().name} is working on $filename (original is $imageFound)"
            if (new File(filename).exists())
                return
            def file, buff
            try {
                file = new FileOutputStream(filename)
                println "Downloading ${filename}"
                buff = new BufferedOutputStream(file)
                buff << new URL(imageFound).openStream()
            } finally {
                file?.close()
                buff?.close()
            }

            println "Downloaded ${filename}"
        }
    }
}

println "Gotovo"