1 /* 2 * Copyright 1999,2004 The Apache Software Foundation. 3 * 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 7 * 8 * http://www.apache.org/licenses/LICENSE-2.0 9 * 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. 15 */ 16 17 package org.apache.commons.feedparser.locate.blogservice; 18 19 import java.net.*; 20 import java.util.regex.Matcher; 21 import java.util.regex.Pattern; 22 23 import org.apache.commons.feedparser.FeedParserException; 24 import org.apache.commons.feedparser.locate.*; 25 26 /** 27 * Models the Xanga blog service, encapsulating whether a given weblog 28 * is this type of service and where it usually keeps its feeds. 29 * 30 * @author Brad Neuberg, bkn3@columbia.edu 31 */ 32 public class Xanga extends BlogService { 33 34 /** 35 * A regex to extract the user from a Xanga URL 36 */ 37 private static Pattern xangaURLPattern = Pattern.compile(".*user=(\\w*)"); 38 39 /** Returns whether we can trust the results of this blog service's 40 * autodiscovery links. For example, TextAmerica returns invalid 41 * autodiscovery results. 42 */ 43 public boolean hasValidAutoDiscovery() { 44 return true; 45 } 46 47 /** Returns whether we should follow HTTP redirects for this blog service. 48 * Some services don't implement HTTP redirects correctly, while others, 49 * like Xanga, require it. 50 */ 51 public boolean followRedirects() { 52 return true; 53 } 54 55 /** Determines if the weblog at the given resource and with the given 56 * content is this blog service. 57 * @param resource A full URI to this resource, such as 58 * "http://www.codinginparadise.org". 59 * @param content The full HTML content at the resource's URL. 60 * @throws FeedParserException Thrown if an error occurs while 61 * determining the type of this weblog. 62 */ 63 public boolean isThisService(String resource, String content) 64 throws FeedParserException { 65 boolean results = false; 66 67 results = containsDomain(resource, "xanga.com"); 68 69 return results; 70 } 71 72 /** 73 * Returns an array of FeedReferences that contains information on the 74 * usual locations this blog service contains its feed. The feeds should 75 * be ordered by quality, so that higher quality feeds come before lower 76 * quality ones (i.e. you would want to have an Atom FeedReference 77 * object come before an RSS 0.91 FeedReference object in this list). 78 * @param resource A URL to the given weblog that might be used to build 79 * up where feeds are usually located. 80 * @param content The full content of the resource URL, which might 81 * be useful to determine where feeds are usually located. This can be 82 * null. 83 * @throws FeedParserException Thrown if an error occurs while trying 84 * to determine the usual locations of feeds for this service. 85 */ 86 public FeedReference[] getFeedLocations(String resource, 87 String content) 88 throws FeedParserException { 89 // Xanga feeds have to be handled specially since they put their 90 // feeds at the location: http://www.xanga.com/rss.aspx?user=username 91 String user = getXangaUser(resource); 92 FeedReference xangaLocations[] = 93 { new FeedReference("rss.aspx?user=" + user, 94 FeedReference.RSS_MEDIA_TYPE) }; 95 96 return xangaLocations; 97 } 98 99 /** Xanga's feed locations are dependent on the 'user' attribute in a 100 * Xanga URI. This method helps extract the user element from an 101 * existing URI, such as http://www.xanga.com/home.aspx?user=wdfphillz. 102 */ 103 protected String getXangaUser(String resource) { 104 Matcher xangaMatcher = xangaURLPattern.matcher(resource); 105 xangaMatcher.matches(); 106 107 return xangaMatcher.group(1); 108 } 109 }