CODEWITHSUNDEEP
javaandroidjsoup
Adrian Ivasku
Adrian Ivasku

Reputation: 1118

Jsoup Android parsing

I am parsing a web page ... and now when I am done... I see I am doing something incredibly stupid, so if anyone can point that out to me please :) and what would be the right direction.

I have a Android app that uses Jsoup and it works great, but it is terribly slow! I know the reason why... because basically onCreate I have 20,30 Jsoup getElement requests...

 private class Task extends AsyncTask<Void, Void, Void>{
    String linkText;
    @Override
    protected Void doInBackground(Void... params) {
        Initdata();

        return null;
    }
    @Override
    protected void onPostExecute(Void param) {

        mProgressBarHandler.hide();           

        redraw();
        inflatedView.invalidate();
    }

    @Override
    protected void onPreExecute() {
        super.onPreExecute();
        mProgressBarHandler.show();
    }
}

In the Initdata() method I have that 20-30 Jsoup requests. Even with AsyncTask it is very slow, the only diference now is that I am not blocking the UI thread,... and that is great but I need to "optimize" somehow the parsing of this elements.

private void Initdata(){

    loadImages();
    players = new String[] {util.GetElement("div.item-2:first-child", "http://www.istinomer.rs/", 0),
            util.GetElement("div.item-2:nth-child(2)", "http://www.istinomer.rs/", 0),
            util.GetElement("div.item-2:nth-child(3)", "http://www.istinomer.rs/", 0),
            util.GetElement("div.item-2:nth-child(4)","http://www.istinomer.rs/",0),
            util.GetElement("div.item-2:nth-child(5)","http://www.istinomer.rs/",0),
            util.GetElement("div.item-2:nth-child(6)","http://www.istinomer.rs/",0),
            util.GetElement("div.item-2:nth-child(7)","http://www.istinomer.rs/",0),
            util.GetElement("div.item-2:nth-child(8)","http://www.istinomer.rs/",0),
            util.GetElement("div.item-2:nth-child(9)","http://www.istinomer.rs/",0),
            util.GetElement("div.item-2:nth-child(10)","http://www.istinomer.rs/",0)
    };
 vestiDescription1 = util.GetElement("div.item-big h2", "http://www.istinomer.rs/", 0) + System.getProperty("line.separator")
            + util.GetElement("div.item-big h3","http://www.istinomer.rs/",0);

    vestiDescription2 = util.GetElement("div.grid-8 h2 a", "http://www.istinomer.rs/", 0) + System.getProperty("line.separator")
            + util.GetElement2("div.grid-8 h3","http://www.istinomer.rs/",0);

    vestiDescription3 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(4) > div:nth-child(1) > div:nth-child(4) > div:nth-child(2) > h3:nth-child(2)", "http://www.istinomer.rs/", 0);

    vestiDescription4 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(4) > div:nth-child(1) > div:nth-child(5) > div:nth-child(2) > h3:nth-child(2)", "http://www.istinomer.rs/", 0);

    vestiDescription5 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(4) > div:nth-child(1) > div:nth-child(6) > div:nth-child(2) > h3:nth-child(2)", "http://www.istinomer.rs/", 0);

    vestiDescription6 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(5) > div:nth-child(1) > div:nth-child(2) > h2:nth-child(4)", "http://www.istinomer.rs/", 0) + System.getProperty("line.separator")
            + util.GetElement2("div.gd-container-1:nth-child(6) > div:nth-child(5) > div:nth-child(1) > div:nth-child(2) > h3:nth-child(5)","http://www.istinomer.rs/",0);

    vestiDescription7 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(5) > div:nth-child(1) > div:nth-child(3) > div:nth-child(2) > h3:nth-child(2)", "http://www.istinomer.rs/", 0);

    vestiDescription8 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(5) > div:nth-child(1) > div:nth-child(4) > div:nth-child(2) > h3:nth-child(2)", "http://www.istinomer.rs/", 0);

    vestiDescription9 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(5) > div:nth-child(1) > div:nth-child(5) > div:nth-child(2) > h3:nth-child(2)", "http://www.istinomer.rs/", 0);

    vestiDescription10 = util.GetElement(
            "div.gd-container-1:nth-child(6) > div:nth-child(5) > div:nth-child(1) > div:nth-child(6) > div:nth-child(2) > h3:nth-child(2)", "http://www.istinomer.rs/", 0);
currency = new String[]{
            vestiDescription1,
            vestiDescription2,
            vestiDescription3,
            vestiDescription4,
            vestiDescription5,
            vestiDescription6,
            vestiDescription7,
            vestiDescription8,
            vestiDescription9,
            vestiDescription10
    };

public String GetElement(String Element, String site, int mode) {
    try {

        Elements newsHeadlines = null;

        if (mode == 0) {
            Document doc = Jsoup.connect(site).timeout(600000).get();
            newsHeadlines = doc.select(Element);
        }
        //1 gets link from class
        else if (mode == 1) {
            Document doc = Jsoup.connect(site).timeout(600000).get();
            String link = doc.select(Element).toString();
            return link;
        }

        //Log.d("TMS", "Data is " + html2text(newsHeadlines.toString()));

        String returnData = html2text(newsHeadlines.toString());
        return returnData;
    }
    catch (Exception e) {
        Log.d("TMS", "EXCEPTION GetElement: " + Element);
        e.printStackTrace();
        return "Error";
    }

Any idea how can I speed up?

Upvotes: 1

Views: 128

Answers (1)

Doug Stevenson
Doug Stevenson

Reputation: 317382

You're requesting the same document to parse repeatedly on each call to GetElement! Of course it's slow!

Instead, make ONE call to JSoup to fetch the document, then use the Document object it returns for all the queries against that document.

Upvotes: 1

Related Questions