+++ /dev/null
-package org.wamblee.crawler.impl;
-
-import java.io.File;
-import java.io.FileInputStream;
-import java.io.InputStream;
-
-import org.apache.commons.httpclient.HttpClient;
-import org.apache.commons.httpclient.NameValuePair;
-import org.dom4j.Element;
-import org.wamblee.crawler.Action;
-import org.wamblee.crawler.Configuration;
-import org.wamblee.crawler.Crawler;
-import org.wamblee.crawler.Page;
-import org.wamblee.crawler.PageException;
-import org.wamblee.xml.XslTransformer;
-
-/*
- * Copyright 2005 the original author or authors.
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-/**
- * Test application which uses the crawler.
- *
- * @author Erik Brakkee
- */
-public final class App {
-
- /**
- * Disabled constructor.
- *
- */
- private App() {
- // Empty
- }
-
- /**
- * Runs a test program.
- *
- * @param aArgs
- * Arguments. First argument is the crawler config file name and
- * second argument is the start url.
- * @throws Exception
- * In case of problems.
- */
- public static void main(String[] aArgs) throws Exception {
- String configFileName = aArgs[0];
- String starturl = aArgs[1];
-
- ConfigurationParser parser = new ConfigurationParser(new XslTransformer());
- InputStream configFile = new FileInputStream(new File(configFileName));
- Configuration config = parser.parse(configFile);
-
- HttpClient client = new HttpClient();
- // client.getHostConfiguration().setProxy("localhost", 3128);
-
- Crawler crawler = new CrawlerImpl(client, config);
-
- System.out.println("Retrieving: " + starturl);
- Page page = crawler.getPage(starturl, new NameValuePair[0]);
- showPage(page);
- page = page.getAction("channels-favorites").execute();
- recordInterestingShows(page);
- showPage(page);
- page = page.getAction("Nederland 1").execute();
- showPage(page);
- page = page.getAction("right-now").execute();
- showPage(page);
- page = page.getAction("Het elfde uur").execute();
- showPage(page);
- }
-
- /**
- * @param starturl
- * @param crawler
- */
- private static void showPage(Page aPage) {
- Action[] links = aPage.getActions();
- for (Action link : links) {
- System.out.println("Link found '" + link.getName() + "'");
- }
- Element element = aPage.getContent();
- System.out.println("Retrieved content: " + element.asXML());
- }
-
- private static void recordInterestingShows(Page page) throws PageException {
- Action[] channels = page.getActions();
- for (Action channel : channels) {
- examineChannel(channel.getName(), channel.execute().getAction(
- "right-now").execute());
- }
- }
-
- private static void examineChannel(String aChannel, Page aPage)
- throws PageException {
- Action[] programs = aPage.getActions();
- for (Action program : programs) {
- System.out.println(aChannel + " - " + program.getName());
- if (program.getName().toLowerCase().matches(".*babe.*")) {
- Page programPage = program.execute();
- Action record = programPage.getAction("record");
- System.out.println("Recording possible: " + record != null);
- }
- }
- }
-
-}