Java verwendet HTMLParser, um einfache Textbeispiele für Webseiten zu extrahieren

复制代码代码如下::

Paket com.test;

import org.htmlparser.node;

import org.htmlparser.nodeFilter;

import org.htmlparser.parser;

import org.htmlparser.filters.tagnameFilter;

import org.htmlparser.tags.tabletag;

import org.htmlparser.util.nodelist;

/**

* 标题: 利用 htmlParser 提取网页纯文本的例子

*/

public class testhtmlparser {

public static void testhtml () {

versuchen {

String -Skurrentline;

String Stotalstring;

scurrentline = "";

stotalstring = "";

java.io.inputstream l_urlstream;

java.net.url l_url = new java.net.url ("http://www.ideagrace.com/html/doc/2006/07/04/00929.html");

java.net.httpurlConnection l_connection = (java.net.httpurlConnection) l_url.openconnection ();

l_connection.connect ();

l_urlstream = l_connection.getInputStream ();

java.io.bufufferedReader l_reader = new Java.io.buffenedReader (new java.io.inputStreamReader (l_urlstream));

while ((scurrentline = l_reader.readline ())! = null) {

stotalstring += scurrentline +"/r/n";

// system.out.println (stotalstring);

}

String testText = extractText (StotalString);

System.out.println (testtext);

} catch (Ausnahme e) {

E. printstacktrace ();

}

}

public static String extractText (String Inputhtml) löst Ausnahme {aus {

StringBuffer text = new StringBuffer ();

Parser Parser = Parser.CreateParser (neuer String (inputhtml.getBytes (), "gbk"), "gbk");

// 遍历所有的节点

Nodelist nodes = parser.extractAllnodesthatMatch (new nodeFilter () {

public boolean Accept (Knotenknoten) {

zurückkehren;

}

});

System.out.println (nodes.size ()); // 打印节点的数量

für (int i = 0; i <nodes.size (); i ++) {

Node nodet = nodes.elementat (i);

//System.out.println (nodet.getText ());

text.Append (neuer String (nodet.toplaintextstring (). getBytes ("gbk"))+"/r/n");

}

return text.toString ();

}

public static void test5 (String Resource) löst Ausnahme {aus {

Parser myparser = neuer Parser (Ressource);

MyParser.SetenCoding ("GBK");

String filterstr = "table";

NodeFilter filter = new TagNameFilter (filterstr);

Nodelist nodelist = myparser.extractAllnodesthatMatch (Filter);

Tabletag Tabletag = (Tabletag) nodelist.elementat (11);

}

public static void main (String [] args) löst Ausnahme {aus {

// test5 ("http://www.google.com");

testhtml ();

}

}