2 * Copyright 2005 the original author or authors.
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
8 * http://www.apache.org/licenses/LICENSE-2.0
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
17 package org.wamblee.crawler.impl;
19 import org.apache.commons.httpclient.HttpClient;
20 import org.apache.commons.logging.Log;
21 import org.apache.commons.logging.LogFactory;
22 import org.dom4j.Element;
23 import org.dom4j.io.DOMReader;
24 import org.w3c.dom.Document;
25 import org.wamblee.crawler.Configuration;
26 import org.wamblee.crawler.Crawler;
27 import org.wamblee.crawler.Page;
28 import org.wamblee.crawler.PageException;
29 import org.wamblee.crawler.PageRequest;
30 import org.wamblee.crawler.PageType;
33 * Crawler implementation.
35 public class CrawlerImpl implements Crawler {
37 private static final Log LOG = LogFactory.getLog(CrawlerImpl.class);
39 private static final int MAX_DELAY = 5000;
41 private HttpClient _client;
43 private Configuration _config;
46 * Constructs the crawler.
53 public CrawlerImpl(HttpClient aClient, Configuration aConfig) {
61 * @see org.wamblee.crawler.Crawler#getPage(java.lang.String)
63 public Page getPage(String aUrl) throws PageException {
64 LOG.info("Getting page: url = '" + aUrl + "'");
65 PageRequest request = _config.getRequest(aUrl);
66 Document content = request.execute(aUrl, _client);
67 return transformToDom4jDoc(content);
73 * @see org.wamblee.crawler.Crawler#getPage(java.lang.String,
76 public Page getPage(String aUrl, PageType aType) throws PageException {
77 LOG.info("Getting page: url = '" + aUrl + "', type = '" + aType + "'");
78 PageRequest request = _config.getRequest(aType);
79 Document content = request.execute(aUrl, _client);
80 return transformToDom4jDoc(content);
84 * Converts a w3c DOM document to a page object.
85 * @param content DOM document.
88 private Page transformToDom4jDoc(Document content) {
89 DOMReader reader = new DOMReader();
90 org.dom4j.Document dom4jDoc = reader.read(content);
91 Element root = dom4jDoc.getRootElement();
92 dom4jDoc.remove(root);
94 return new PageImpl(this, replaceReferencesWithContent(root));
98 * Perform crawling. Find references in the retrieved content and replace
99 * them by the content they refer to by retrieving the appropriate pages as
103 * Content which must be made complete.
104 * @return Fully processed content.
106 private Element replaceReferencesWithContent(Element content) {
107 return content; // TODO implement.