im trying to parse url generated by Bootstrap`s Bootpage.js which looks like https://example.com/#page-2 but JSOUP cant parse it and showing main url. how to get normal link from Bootpage or how to make JSOUP to parse it.
Parsing code:
Jsoup.connect("https://example.com/#page-2").followRedirects(true).get();
(See UPDATE below, first/accepted solution didn't met the android requirement, but is left for reference.)
Desktop Solution
HtmlUnit doesn't seem able to handle this site (often the case, lately). So I don't have a plain java solution either, but you could use PhantomJS: download the binary for your os, create a script file, start the process from within your java code and parse the output with a dom parser like jsoup.
Script file (here called simple.js):
var page = require('webpage').create();
var fs = require('fs');
var system = require('system');
var url = "";
var fileName = "output";
// first parameter: url
// second parameter: filename for output
console.log("args length: " + system.args.length);
if (system.args.length > 1) {
url=system.args[1];
}
if (system.args.length > 2){
fileName=system.args[2];
}
if(url===""){
phantom.exit();
}
page.settings.userAgent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.120 Safari/537.36';
page.settings.loadImages = false;
page.open(url, function(status) {
console.log("Status: " + status);
if(status === "success") {
var path = fileName+'.html';
fs.write(path, page.content, 'w');
}
phantom.exit();
});
Java code (example to get title and cover-url):
try {
//change path to phantomjs binary and your script file
String outputFileName = "srulad";
String phantomJSPath = "phantomjs" + File.separator + "bin" + File.separator + "phantomjs";
String scriptFile = "simple.js";
String urlParameter = "http://srulad.com/#page-2";
new File(outputFileName+".html").delete();
Process process = Runtime.getRuntime().exec(phantomJSPath + " " + scriptFile + " " + urlParameter + " " + outputFileName);
process.waitFor();
Document doc = Jsoup.parse(new File(outputFileName + ".html"),"UTF-8"); // output.html is created by phantom.js, same path as page.js
Elements elements = doc.select("#list_page-2 > div");
for (Element element : elements) {
System.out.println(element.select("div.l-description.float-left > div:nth-child(1) > a").first().attr("title"));
System.out.println(element.select("div.l-image.float-left > a > img.lazy").first().attr("data-original"));
}
} catch (IOException | InterruptedException e) {
e.printStackTrace();
}
Output:
სიყვარული და მოწყალება / Love & Mercy
http://srulad.com/assets/uploads/42410_Love_and_Mercy.jpg
მუზა / The Muse
http://srulad.com/assets/uploads/43164_large_qRzsimNz0eDyFLFJcbVLIxlqii.jpg
...
Parsing of websites with javascript based dynamic content in Android is possible using WebView and jsoup. The following example app uses a javascript enabled WebView to render a Javascript dependent website. With a JavascriptInterface the html source is returned, parsed with jsoup and as a proof of concept the titles and the urls to the cover-images are used to populate a ListView. The buttons decrement or increment the page number triggering an update of the ListView. Note: tested on an Android 5.1.1/API 22 device.
add internet permission to your AndroidManifest.xml
<uses-permission android:name="android.permission.INTERNET" />
activity_main.xml
<?xml version="1.0" encoding="utf-8"?>
<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
android:orientation="vertical"
android:layout_width="match_parent"
android:layout_height="match_parent">
<LinearLayout
android:orientation="horizontal"
android:layout_width="match_parent"
android:layout_height="wrap_content">
<Button
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:text="@string/page_down"
android:id="@+id/buttonDown"
android:layout_weight="0.5" />
<Button
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:text="@string/page_up"
android:id="@+id/buttonUp"
android:layout_weight="0.5" />
</LinearLayout>
<ListView
android:layout_width="match_parent"
android:layout_height="0dp"
android:id="@+id/listView"
android:layout_gravity="bottom"
android:layout_weight="0.5" />
</LinearLayout>
MainActivity.java
public class MainActivity extends AppCompatActivity {
private final Handler uiHandler = new Handler();
private ArrayAdapter<String> adapter;
private ArrayList<String> entries = new ArrayList<>();
private ProgressDialog progressDialog;
private class JSHtmlInterface {
@android.webkit.JavascriptInterface
public void showHTML(String html) {
final String htmlContent = html;
uiHandler.post(
new Runnable() {
@Override
public void run() {
Document doc = Jsoup.parse(htmlContent);
Elements elements = doc.select("#online_movies > div > div");
entries.clear();
for (Element element : elements) {
String title = element.select("div.l-description.float-left > div:nth-child(1) > a").first().attr("title");
String imgUrl = element.select("div.l-image.float-left > a > img.lazy").first().attr("data-original");
entries.add(title + "\n" + imgUrl);
}
adapter.notifyDataSetChanged();
}
}
);
}
}
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
ListView listView = (ListView) findViewById(R.id.listView);
adapter = new ArrayAdapter<>(this, android.R.layout.simple_list_item_1, android.R.id.text1, entries);
listView.setAdapter(adapter);
progressDialog = ProgressDialog.show(this, "Loading","Please wait...", true);
progressDialog.setCancelable(false);
try {
final WebView browser = new WebView(this);
browser.setVisibility(View.INVISIBLE);
browser.setLayerType(View.LAYER_TYPE_NONE,null);
browser.getSettings().setJavaScriptEnabled(true);
browser.getSettings().setBlockNetworkImage(true);
browser.getSettings().setDomStorageEnabled(false);
browser.getSettings().setCacheMode(WebSettings.LOAD_NO_CACHE);
browser.getSettings().setLoadsImagesAutomatically(false);
browser.getSettings().setGeolocationEnabled(false);
browser.getSettings().setSupportZoom(false);
browser.addJavascriptInterface(new JSHtmlInterface(), "JSBridge");
browser.setWebViewClient(
new WebViewClient() {
@Override
public void onPageStarted(WebView view, String url, Bitmap favicon) {
progressDialog.show();
super.onPageStarted(view, url, favicon);
}
@Override
public void onPageFinished(WebView view, String url) {
browser.loadUrl("javascript:window.JSBridge.showHTML('<html>'+document.getElementsByTagName('html')[0].innerHTML+'</html>');");
progressDialog.dismiss();
}
}
);
findViewById(R.id.buttonDown).setOnClickListener(new View.OnClickListener() {
@Override
public void onClick(View view) {
uiHandler.post(new Runnable() {
@Override
public void run() {
int page = Integer.parseInt(browser.getUrl().split("-")[1]);
int newPage = page > 1 ? page-1 : 1;
browser.loadUrl("http://srulad.com/#page-" + newPage);
browser.loadUrl(browser.getUrl()); // not sure why this is needed, but doesn't update without it on my device
if(getSupportActionBar()!=null) getSupportActionBar().setTitle(browser.getUrl());
}
});
}
});
findViewById(R.id.buttonUp).setOnClickListener(new View.OnClickListener() {
@Override
public void onClick(View view) {
uiHandler.post(new Runnable() {
@Override
public void run() {
int page = Integer.parseInt(browser.getUrl().split("-")[1]);
int newPage = page+1;
browser.loadUrl("http://srulad.com/#page-" + newPage);
browser.loadUrl(browser.getUrl()); // not sure why this is needed, but doesn't update without it on my device
if(getSupportActionBar()!=null) getSupportActionBar().setTitle(browser.getUrl());
}
});
}
});
browser.loadUrl("http://srulad.com/#page-1");
if(getSupportActionBar()!=null) getSupportActionBar().setTitle(browser.getUrl());
} catch (Exception e) {
e.printStackTrace();
}
}
}