parser中文API以及 示例.docxVIP

中文APIpackage parser;import java.io.BufferedReader;import java.io.BufferedWriter;import java.io.FileWriter;import java.io.IOException;import java.io.InputStream;import java.io.InputStreamReader;import .MalformedURLException;import .URL;/** * 基本能实现网页抓取，不过要手动输入URL 将整个html内容保存到指定文件 * * @author chenguoyong * */public class ScrubSelectedWeb {private final static String CRLF = System.getProperty(line.separator);/** * @param args */public static void main(String[] args) {try {URL ur = new URL(99:8083/injs100/);InputStream instr = ur.openStream();String s, str;BufferedReader in = new BufferedReader(new InputStreamReader(instr));StringBuffer sb = new StringBuffer();BufferedWriter out = new BufferedWriter(new FileWriter(D:/outPut.txt));while ((s = in.readLine()) != null) {sb.append(s + CRLF);}System.out.println(sb);str = new String(sb);out.write(str);out.close();in.close();} catch (MalformedURLException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();}}}基本能实现网页抓取，不过要手动输入URL，此外没有重构。只是一个简单的思路。1.htmlparser 使用htmlparser是一个纯的java写的html解析的库，htmlparser不依赖于其它的java库，htmlparser主要用于改造或提取html。htmlparser能超高速解析html，而且不会出错。毫不夸张地说，htmlparser就是目前最好的html解析和分析的工具。无论你是想抓取网页数据还是改造html的内容，用了htmlparser绝对会忍不住称赞。由于htmlparser 结构设计精良，所以扩展htmlparser 非常便利。Htmlparser中文论坛.??/thread.php?fid=6Constructor SummaryParser()Parser(URLConnection?connection)??????????Construct a parser using the provided URLConnection.Method:static?ParsercreateParser(String?html, String?charset)??????????Creates the parser on an input string.?voidvisitAllNodesWith(NodeVisitor?visitor)??????????Apply the given visitor to the current page.HtmlPage(Parser?parser)?NodeListgetBody()????????????TableTag[]getTables()????????????StringgetTitle()????????????voidsetTitle(String?title)????????????voidvisitTag(Tag?tag)??????????Called for each Tag visited.?Constructor SummaryNodeList()???????????NodeList(Node?node)??????????Create a one element node list.??NodeListextractAllNodesThatMatch(NodeFilter?filter)??????????Filte