📄 excite.java
字号:
/* * WebSPHINX web crawling toolkit * Copyright (C) 1998,1999 Carnegie Mellon University * * This library is free software; you can redistribute it * and/or modify it under the terms of the GNU Library * General Public License as published by the Free Software * Foundation, version 2. * * WebSPHINX homepage: http://www.cs.cmu.edu/~rcm/websphinx/ */package websphinx.searchengine; // ALB 12/97import websphinx.*;import java.net.URL;import java.net.URLEncoder;import java.net.MalformedURLException;/** * <A href="http://www.excite.com/">Excite</a> search engine. * @author Adam Berger */public class Excite implements SearchEngine { static Pattern patCount = new Regexp ( "<font size=-1 face=\"arial, helvetica\">(?:About )?<b>(\\d+)</b> documents? match your query."); static Pattern patNoHits = new Regexp ( "No documents match the query." ); static Pattern patResult = new Tagexp ( "<FONT COLOR=navy><B>(?{score})</B></FONT>" // score + "<B>(?{link}<a>(?{title})</a>)</B>" // title and main link + "<BR><B><I></I></B>" // URL + "<BR><B><I></I></B>(?{description})" // Summary + "<BR><B><I></I></B><a><p></a>" // More Like This ); static Pattern patMoreLink = new Tagexp ( "<INPUT TYPE=submit NAME=next VALUE=\"Next Results\">" ); /** * Classify a page. Sets the following labels: * <TABLE> * <TR><TH>Name <TH>Type <TH>Meaning * <TR><TD>searchengine.source <TD>Page label <TD>Excite object that labeled the page * <TR><TD>searchengine.count <TD>Page field <TD>Number of results on page * <TR><TD>searchengine.results <TD>Page fields <TD>Array of results. Each result region * contains subfields: score, title, description, and link. * <TR><TD>searchengine.more-results <TD>Link label <TD>Link to a page containing more results. * </TABLE> */ public void classify (Page page) { String title = page.getTitle (); if (title != null && (title.startsWith ("Excite Search Results"))) { page.setObjectLabel ("searchengine.source", this); Region count = patCount.oneMatch (page); if (count != null) page.setField ("searchengine.count", count.getField ("0")); Region[] results = patResult.allMatches (page); SearchEngineResult[] ser = new SearchEngineResult[results.length]; for (int i=0; i<results.length; ++i) ser[i] = new SearchEngineResult (results[i]); page.setFields ("searchengine.results", ser); PatternMatcher m = patMoreLink.match (page); while (m.hasMoreElements ()) { Link link = (Link)m.nextMatch (); link.setLabel ("searchengine.more-results"); link.setLabel ("hyperlink"); } } } /** * Priority of this classifier. */ public static final float priority = 0.0F; /** * Get priority of this classifier. * @return priority. */ public float getPriority () { return priority; } /** * Make a query URL for Excite. * @param keywords list of keywords, separated by spaces * @return URL that submits the keywords to Excite. */ public URL makeQuery (String keywords) { try { return new URL("http://www.excite.com/search.gw?trace=a&search=" + URLEncoder.encode(keywords)); } catch (MalformedURLException e) { throw new RuntimeException ("internal error"); } } /** * Get number of results per page for this search engine. * @return typical number of results per page */ public int getResultsPerPage () { return 10; } /** * Search Excite. * @param keywords list of keywords, separated by spaces * @return enumeration of SearchEngineResults returned by an Excite query constructed from the keywords. */ public static Search search (String keywords) { return new Search(new Excite(), keywords); } /** * Search Excite. * @param keywords list of keywords, separated by spaces * @param maxResults maximum number of results to return * @return enumeration of SearchEngineResults returned by an Excite query constructed from the keywords. * The enumeration yields at most maxResults objects. */ public static Search search (String keywords, int maxResults) { return new Search (new Excite(), keywords, maxResults); }}
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -