htmlparser实现从网页上抓取数据（收集）
http://luoye1989hzx.blog.163.com/blog/static/1699218892010828364066/
本文引用自luoye1989《htmlparser实现从网页上抓取数据（收集）》
package 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 java.net.MalformedURLException;
import java.net.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("http://10.249.187.199:8083/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. http://bbs.hexiao.cn/thread.php?fid=6
Constructor Summary
Parser()
Parser(URLConnection connection)
Construct a parser using the provided URLConnection.
Method:
static Parser createParser(String html, String charset)
Creates the parser on an input string.
void visitAllNodesWith(NodeVisitor visitor)
Apply the given visitor to the current page.
HtmlPage(Parser parser)
NodeList
getBody()
TableTag[]
getTables()
String
getTitle()
void
setTitle(String title)
void
visitTag(Tag tag)
Called for each Tag visited.
Constructor Summary
NodeList()
NodeList(Node node)
Create a one element node list.
NodeList extractAllNodesThatMatch(NodeFilter filter)
Filter the list with the given filter non-recursively.
NodeList extractAllNodesThatMatch(NodeFilter filter, boolean recursive)
Filter the list with the given filter.
Node elementAt(int i)
1. html代码里面所有的链接地址和链接名称
package parser;
import org.htmlparser.Parser;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.TableTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.HtmlPage;
/**
* htmlparser取得一段html代码里面所有的链接地址和链接名称
*
* @author chenguoyong
*
*/
public class Testhtmlparser {
/**
* @param args
*/
public static void main(String[] args) {
String htmlcode = "<HTML><HEAD><TITLE>AAA</TITLE></HEAD><BODY>"
+ "<a href='http://topic.csdn.net/u/20080522/14/0ff402ef-c382-499a-8213-ba6b2f550425.html'>连接1</a>"
+ "<a href='http://topic.csdn.net'>连接2</a></BODY></HTML>";
// 创建Parser对象根据传给字符串和指定的编码
Parser parser = Parser.createParser(htmlcode, "GBK");
// 创建HtmlPage对象HtmlPage(Parser parser)
HtmlPage page = new HtmlPage(parser);
try {
// HtmlPage extends visitor,Apply the given visitor to the current
// page.
parser.visitAllNodesWith(page);
} catch (ParserException e1) {
e1 = null;
}
// 所有的节点
NodeList nodelist = page.getBody();
// 建立一个节点filter用于过滤节点
NodeFilter filter = new TagNameFilter("A");
// 得到所有过滤后，想要的节点
nodelist = nodelist.extractAllNodesThatMatch(filter, true);
for (int i = 0; i < nodelist.size(); i++) {
LinkTag link = (LinkTag) nodelist.elementAt(i);
// 链接地址
System.out.println(link.getAttribute("href") + "\n");
// 链接名称
System.out.println(link.getStringText());
}
}
}
结果如下：
http://topic.csdn.net/u/20080522/14/0ff402ef-c382-499a-8213-ba6b2f550425.html
连接1
http://topic.csdn.net
连接2
2. 使用HtmlParser抓去网页内容
package parser;
import org.htmlparser.Parser;
import org.htmlparser.beans.StringBean;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.parserapplications.StringExtractor;
import org.htmlparser.tags.BodyTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
/**
* 使用HtmlParser抓去网页内容: 要抓去页面的内容最方便的方法就是使用StringBean. 里面有几个控制页面内容的几个参数.
* 在后面的代码中会有说明. Htmlparser包中还有一个示例StringExtractor 里面有个直接得到内容的方法,
* 其中也是使用了StringBean . 另外直接解析Parser的每个标签也可以的.
*
* @author chenguoyong
*
*/
public class GetContent {
public void getContentUsingStringBean(String url) {
StringBean sb = new StringBean();
sb.setLinks(true); // 是否显示web页面的连接(Links)
// 为了取得页面的整洁美观一般设置上面两项为true , 如果要保持页面的原有格式, 如代码页面的空格缩进 可以设置为false
sb.setCollapse(true); // 如果是true的话把一系列空白字符用一个字符替代.
sb.setReplaceNonBreakingSpaces(true);// If true regular space
sb
.setURL("http://www.blogjava.net/51AOP/archive/2006/07/19/59064.html");
System.out.println("The Content is :\n" + sb.getStrings());
}
public void getContentUsingStringExtractor(String url, boolean link) {
// StringExtractor内部机制和上面的一样.做了一下包装
StringExtractor se = new StringExtractor(url);
String text = null;
try {
text = se.extractStrings(link);
System.out.println("The content is :\n" + text);
} catch (ParserException e) {
e.printStackTrace();
}
}
public void getContentUsingParser(String url) {
NodeList nl;
try {
Parser p = new Parser(url);
nl = p.parse(new NodeClassFilter(BodyTag.class));
BodyTag bt = (BodyTag) nl.elementAt(0);
System.out.println(bt.toPlainTextString()); // 保留原来的内容格式. 包含js代码
} catch (ParserException e) {
e.printStackTrace();
}
}
/**
* @param args
*/
public static void main(String[] args) {
String url = "http://www.blogjava.net/51AOP/archive/2006/07/19/59064.html";
//new GetContent().getContentUsingParser(url);
//--------------------------------------------------
new GetContent().getContentUsingStringBean(url);
}
}
3.将整个html内容保存到指定文件
package 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 java.net.MalformedURLException;
import java.net.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("http://www.google.cn/");
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();
}
}
}
4利用htmlparser提取网页纯文本的例子
package parser;
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 TestHTMLParser2 {
/**
* 读取目标html内容
*
*/
public static void testHtml() {
try {
String sCurrentLine;
String sTotalString;
sCurrentLine = "";
sTotalString = "";
java.io.InputStream l_urlStream;
java.net.URL l_url = new java.net.URL(
"http://10.249.187.199:8083/injs100/");
java.net.HttpURLConnection l_connection = (java.net.HttpURLConnection) l_url
.openConnection();
l_connection.connect();
l_urlStream = l_connection.getInputStream();
java.io.BufferedReader l_reader = new java.io.BufferedReader(
new java.io.InputStreamReader(l_urlStream));
while ((sCurrentLine = l_reader.readLine()) != null) {
sTotalString += sCurrentLine + "\r\n";
}
String testText = extractText(sTotalString);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 抽取纯文本信息
* @param inputHtml：html文本
* @return
* @throws Exception
*/
public static String extractText(String inputHtml) throws Exception {
StringBuffer text = new StringBuffer();
Parser parser = Parser.createParser(new String(inputHtml.getBytes(),
"GBK"), "GBK");
// 遍历所有的节点
NodeList nodes = parser.extractAllNodesThatMatch(new NodeFilter() {
public boolean accept(Node node) {
return true;
}
});
System.out.println(nodes.size());
for (int i = 0; i < nodes.size(); i++) {
Node nodet = nodes.elementAt(i);
//字符串的代表性节点:节点的描述
text.append(new String(nodet.toPlainTextString().getBytes("GBK"))
+ "\r\n");
}
return text.toString();
}
/**
* 读取文件的方式/utl 来分析内容. filePath也可以是一个Url.
* @param resource :文件/Url
* @throws Exception
*/
public static void test5(String resource) throws Exception {
Parser myParser = new Parser(resource);
myParser.setEncoding("GBK");
String filterStr = "table";
NodeFilter filter = new TagNameFilter(filterStr);
NodeList nodeList = myParser.extractAllNodesThatMatch(filter);
/*for(int i=0;i<nodeList.size();i++)
{
TableTag tabletag = (TableTag) nodeList.elementAt(i);
//标签名称
System.out.println(tabletag.getTagName());
System.out.println(tabletag.getText());
}*/
TableTag tabletag = (TableTag) nodeList.elementAt(1);
}
public static void main(String[] args) throws Exception {
test5("http://10.249.187.199:8083/injs100/");
//testHtml();
}
}
5.html解析table
package parser;
import org.apache.log4j.Logger;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.TableColumn;
import org.htmlparser.tags.TableRow;
import org.htmlparser.tags.TableTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import junit.framework.TestCase;
public class ParserTestCase extends TestCase {
private static final Logger logger = Logger.getLogger(ParserTestCase.class);
public ParserTestCase(String name) {
super(name);
}
/**
* 测试对<table>
* <tr>
* <td></td>
* </tr>
* </table>的解析
*/
public void testTable() {
Parser myParser;
NodeList nodeList = null;
myParser = Parser
.createParser(
"<body> "
+ "<table id=’table1′ >"
+ "<tr id='tro1'><td>1-11</td><td>1-12</td><td>1-13</td></tr>"
+ "<tr id='tro2'><td>1-21</td><td>1-22</td><td>1-23</td></tr>"
+ "<tr id='tro3'><td>1-31</td><td>1-32</td><td>1-33</td></tr></table>"
+ "<table id=’table2′ >"
+ "<tr id='tro4'><td>2-11</td><td>2-12</td><td>2-13</td></tr>"
+ "<tr id='tro5'><td>2-21</td><td>2-22</td><td>2-23</td></tr>"
+ "<tr id='tro6'><td>2-31</td><td>2-32</td><td>2-33</td></tr></table>"
+ "</body>", "GBK");
NodeFilter tableFilter = new NodeClassFilter(TableTag.class);
OrFilter lastFilter = new OrFilter();
lastFilter.setPredicates(new NodeFilter[] { tableFilter });
try {
nodeList = myParser.parse(lastFilter);
for (int i = 0; i <= nodeList.size(); i++) {
if (nodeList.elementAt(i) instanceof TableTag) {
TableTag tag = (TableTag) nodeList.elementAt(i);
TableRow[] rows = tag.getRows();
for (int j = 0; j < rows.length; j++) {
TableRow tr = (TableRow) rows[j];
System.out.println(tr.getAttribute("id"));
if (tr.getAttribute("id").equalsIgnoreCase("tro1")) {
TableColumn[] td = tr.getColumns();
for (int k = 0; k < td.length; k++) {
// logger.fatal("<td>" +
// td[k].toPlainTextString());
System.out.println("<td>"
+ td[k].toPlainTextString());
}
}
}
}
}
} catch (ParserException e) {
e.printStackTrace();
}
}
/**
* 得到目标数据
*
* @param url:目标url
* @throws Exception
*/
public static void getDatabyUrl(String url) throws Exception {
Parser myParser = new Parser(url);
NodeList nodeList = null;
myParser.setEncoding("gb2312");
NodeFilter tableFilter = new NodeClassFilter(TableTag.class);
OrFilter lastFilter = new OrFilter();
lastFilter.setPredicates(new NodeFilter[] { tableFilter });
try {
nodeList = myParser.parse(lastFilter);
// 可以从数据table的size:19-21开始到结束
for (int i = 15; i <= nodeList.size(); i++) {
if (nodeList.elementAt(i) instanceof TableTag) {
TableTag tag = (TableTag) nodeList.elementAt(i);
TableRow[] rows = tag.getRows();
for (int j = 0; j < rows.length; j++) {
TableRow tr = (TableRow) rows[j];
if (tr.getAttribute("id") != null
&& tr.getAttribute("id").equalsIgnoreCase(
"tr02")) {
TableColumn[] td = tr.getColumns();
// 对不起，没有你要查询的记录！
if (td.length == 1) {
System.out.println("对不起，没有你要查询的记录");
} else {
for (int k = 0; k < td.length; k++) {
System.out.println("<td>内容："
+ td[k].toPlainTextString().trim());
}
}
}
}
}
}
} catch (ParserException e) {
e.printStackTrace();
}
}
/**
* 测试已经得出有数据时table:22个，没有数据时table:19个
*
* @param args
*/
public static void main(String[] args) {
try {
// getDatabyUrl("http://gd.12530.com/user/querytonebytype.do?field=tonecode&condition=619505000000008942&type=1006&pkValue=619505000000008942");
getDatabyUrl("http://gd.12530.com/user/querytonebytype.do?field=tonecode&condition=619272000000001712&type=1006&pkValue=619272000000001712");
} catch (Exception e) {
e.printStackTrace();
}
}
}
6.html解析常用
package com.jscud.test;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.HtmlPage;
import org.htmlparser.visitors.TextExtractingVisitor;
import com.jscud.util.LogMan; //一个日志记录类
/**
* 演示了Html Parse的应用.
*
* @author scud http://www.jscud.com (http://www.jscud.com/)
*/
public class ParseHtmlTest
{
public static void main(String[] args) throws Exception
{
String aFile = "e:/jscud/temp/test.htm";
String content = readTextFile(aFile, "GBK");
test1(content);
System.out.println("====================================");
test2(content);
System.out.println("====================================");
test3(content);
System.out.println("====================================");
test4(content);
System.out.println("====================================");
test5(aFile);
System.out.println("====================================");
//访问外部资源,相对慢
test5("http://www.jscud.com (http://www.jscud.com/)");
System.out.println("====================================");
}
/**
* 读取文件的方式来分析内容.
* filePath也可以是一个Url.
*
* @param resource 文件/Url
*/
public static void test5(String resource) throws Exception
{
Parser myParser = new Parser(resource);
//设置编码
myParser.setEncoding("GBK");
HtmlPage visitor = new HtmlPage(myParser);
myParser.visitAllNodesWith(visitor);
String textInPage = visitor.getTitle();
System.out.println(textInPage);
}
/**
* 按页面方式处理.对一个标准的Html页面,推荐使用此种方式.
*/
public static void test4(String content) throws Exception
{
Parser myParser;
myParser = Parser.createParser(content, "GBK");
HtmlPage visitor = new HtmlPage(myParser);
myParser.visitAllNodesWith(visitor);
String textInPage = visitor.getTitle();
System.out.println(textInPage);
}
/**
* 利用Visitor模式解析html页面.
*
* 小优点:翻译了<>等符号
* 缺点:好多空格,无法提取link
*
*/
public static void test3(String content) throws Exception
{
Parser myParser;
myParser = Parser.createParser(content, "GBK");
TextExtractingVisitor visitor = new TextExtractingVisitor();
myParser.visitAllNodesWith(visitor);
String textInPage = visitor.getExtractedText();
System.out.println(textInPage);
}
/**
* 得到普通文本和链接的内容.
*
* 使用了过滤条件.
*/
public static void test2(String content) throws ParserException
{
Parser myParser;
NodeList nodeList = null;
myParser = Parser.createParser(content, "GBK");
NodeFilter textFilter = new NodeClassFilter(TextNode.class);
NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
//暂时不处理 meta
//NodeFilter metaFilter = new NodeClassFilter(MetaTag.class);
OrFilter lastFilter = new OrFilter();
lastFilter.setPredicates(new NodeFilter[] { textFilter, linkFilter });
nodeList = myParser.parse(lastFilter);
Node[] nodes = nodeList.toNodeArray();
for (int i = 0; i < nodes.length; i++)
{
Node anode = (Node) nodes[i];
String line = "";
if (anode instanceof TextNode)
{
TextNode textnode = (TextNode) anode;
//line = textnode.toPlainTextString().trim();
line = textnode.getText();
}
else if (anode instanceof LinkTag)
{
LinkTag linknode = (LinkTag) anode;
line = linknode.getLink();
//@todo ("") 过滤jsp标签:可以自己实现这个函数
//line = StringFunc.replace(line, "<%.*%>", "");
}
if (isTrimEmpty(line))
continue;
System.out.println(line);
}
}
/**
* 解析普通文本节点.
*
* @param content
* @throws ParserException
*/
public static void test1(String content) throws ParserException
{
Parser myParser;
Node[] nodes = null;
myParser = Parser.createParser(content, null);
nodes = myParser.extractAllNodesThatAre(TextNode.class); //exception could be thrown here
for (int i = 0; i < nodes.length; i++)
{
TextNode textnode = (TextNode) nodes[i];
String line = textnode.toPlainTextString().trim();
if (line.equals(""))
continue;
System.out.println(line);
}
}
/**
* 读取一个文件到字符串里.
*
* @param sFileName 文件名
* @param sEncode String
* @return 文件内容
*/
public static String readTextFile(String sFileName, String sEncode)
{
StringBuffer sbStr = new StringBuffer();
try
{
File ff = new File(sFileName);
InputStreamReader read = new InputStreamReader(new FileInputStream(ff),
sEncode);
BufferedReader ins = new BufferedReader(read);
String dataLine = "";
while (null != (dataLine = ins.readLine()))
{
sbStr.append(dataLine);
sbStr.append("\r\n");
}
ins.close();
}
catch (Exception e)
{
LogMan.error("read Text File Error", e);
}
return sbStr.toString();
}
/**
* 去掉左右空格后字符串是否为空
* @param astr String
* @return boolean
*/
public static boolean isTrimEmpty(String astr)
{
if ((null == astr) || (astr.length() == 0))
{
return true;
}
if (isBlank(astr.trim()))
{
return true;
}
return false;
}
/**
* 字符串是否为空:null或者长度为0.
* @param astr 源字符串.
* @return boolean
*/
public static boolean isBlank(String astr)
{
if ((null == astr) || (astr.length() == 0))
{
return true;
}
else
{
return false;
}
}
}
