1、以EMAIL为例:(以这个网页为例http://www.qunar.com/site/zh/Cooperate_4.shtml)
package extract;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
public class extracthtmllinkemail {
/**
* @param args
*/
public static String getText(String f){
StringBuffer sb=new StringBuffer();
try {
Parser parser=new Parser(f);
parser.setEncoding("UTF-8");
NodeFilter filter=new NodeClassFilter(){
public boolean accept(Node node){
return (LinkTag.class.isAssignableFrom(node.getClass())&&((LinkTag)node).isMailLink());
}
};
NodeList links=new NodeList();
for (NodeIterator e=parser.elements();e.hasMoreNodes();){
e.nextNode().collectInto(links, filter);
}
for (int i=0;i<links.size();i++){
LinkTag linktag=(LinkTag)links.elementAt(i);
sb.append("\n|"+linktag.getLinkText()+"|=>"+linktag.getLink());
}
} catch (ParserException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return sb.toString();
}
public static void main(String[] args) {
// TODO Auto-generated method stub
String s=getText("./htmls/Qunar_com.htm");
System.out.print(s);
}
}
效果如下:
|Adservice@qunar.com|=>adservice@qunar.com
|adservice@qunar.com|=>adservice@qunar.com
2、以(www.hao123.com)为例,提取js链接
代码
package extract;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
public class extracthtmllinkemail {
/**
* @param args
*/
public static String getText(String f){
StringBuffer sb=new StringBuffer();
try {
Parser parser=new Parser(f);
parser.setEncoding("GB2312");
NodeFilter filter=new NodeClassFilter(){
public boolean accept(Node node){
return (LinkTag.class.isAssignableFrom(node.getClass())&&((LinkTag)node).isJavascriptLink());
}
};
NodeList links=new NodeList();
for (NodeIterator e=parser.elements();e.hasMoreNodes();){
e.nextNode().collectInto(links, filter);
}
for (int i=0;i<links.size();i++){
LinkTag linktag=(LinkTag)links.elementAt(i);
sb.append("\n|"+linktag.getLinkText()+"|=>"+linktag.getLink());
}
} catch (ParserException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return sb.toString();
}
public static void main(String[] args) {
// TODO Auto-generated method stub
String s=getText("./htmls/hao123.htm");
System.out.print(s);
}
}
效果如下:
|我的hao123|=>void(0);
|我喜欢的网站:|=>void(0)
|我定制的网站:|=>void(0)
分享到:
相关推荐
赠送jar包:lucene-analyzers-smartcn-7.7.0.jar; 赠送原API文档:lucene-analyzers-smartcn-7.7.0-javadoc.jar; 赠送源代码:lucene-analyzers-smartcn-7.7.0-sources.jar; 赠送Maven依赖信息文件:lucene-...
lucene-core-2.9.4,lucene-core-3.0.2,lucene-core-3.0.3,lucene-core-3.4.0
赠送jar包:lucene-core-7.7.0.jar; 赠送原API文档:lucene-core-7.7.0-javadoc.jar; 赠送源代码:lucene-core-7.7.0-sources.jar; 赠送Maven依赖信息文件:lucene-core-7.7.0.pom; 包含翻译后的API文档:lucene...
赠送jar包:lucene-analyzers-common-6.6.0.jar; 赠送原API文档:lucene-analyzers-common-6.6.0-javadoc.jar; 赠送源代码:lucene-analyzers-common-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-...
赠送jar包:lucene-core-7.2.1.jar; 赠送原API文档:lucene-core-7.2.1-javadoc.jar; 赠送源代码:lucene-core-7.2.1-sources.jar; 赠送Maven依赖信息文件:lucene-core-7.2.1.pom; 包含翻译后的API文档:lucene...
赠送jar包:lucene-suggest-6.6.0.jar; 赠送原API文档:lucene-suggest-6.6.0-javadoc.jar; 赠送源代码:lucene-suggest-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-suggest-6.6.0.pom; 包含翻译后的API...
赠送jar包:lucene-backward-codecs-7.3.1.jar; 赠送原API文档:lucene-backward-codecs-7.3.1-javadoc.jar; 赠送源代码:lucene-backward-codecs-7.3.1-sources.jar; 赠送Maven依赖信息文件:lucene-backward-...
赠送jar包:lucene-core-6.6.0.jar; 赠送原API文档:lucene-core-6.6.0-javadoc.jar; 赠送源代码:lucene-core-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-core-6.6.0.pom; 包含翻译后的API文档:lucene...
赠送jar包:lucene-analyzers-smartcn-7.7.0.jar; 赠送原API文档:lucene-analyzers-smartcn-7.7.0-javadoc.jar; 赠送源代码:lucene-analyzers-smartcn-7.7.0-sources.jar; 赠送Maven依赖信息文件:lucene-...
赠送jar包:lucene-spatial-extras-7.3.1.jar; 赠送原API文档:lucene-spatial-extras-7.3.1-javadoc.jar; 赠送源代码:lucene-spatial-extras-7.3.1-sources.jar; 赠送Maven依赖信息文件:lucene-spatial-extras...
赠送jar包:lucene-memory-6.6.0.jar; 赠送原API文档:lucene-memory-6.6.0-javadoc.jar; 赠送源代码:lucene-memory-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-memory-6.6.0.pom; 包含翻译后的API文档...
赠送jar包:lucene-suggest-7.7.0.jar; 赠送原API文档:lucene-suggest-7.7.0-javadoc.jar; 赠送源代码:lucene-suggest-7.7.0-sources.jar; 赠送Maven依赖信息文件:lucene-suggest-7.7.0.pom; 包含翻译后的API...
赠送jar包:lucene-spatial-extras-7.2.1.jar; 赠送原API文档:lucene-spatial-extras-7.2.1-javadoc.jar; 赠送源代码:lucene-spatial-extras-7.2.1-sources.jar; 赠送Maven依赖信息文件:lucene-spatial-extras...
赠送jar包:lucene-sandbox-7.2.1.jar; 赠送原API文档:lucene-sandbox-7.2.1-javadoc.jar; 赠送源代码:lucene-sandbox-7.2.1-sources.jar; 赠送Maven依赖信息文件:lucene-sandbox-7.2.1.pom; 包含翻译后的API...
赠送jar包:lucene-spatial-extras-6.6.0.jar; 赠送原API文档:lucene-spatial-extras-6.6.0-javadoc.jar; 赠送源代码:lucene-spatial-extras-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-spatial-extras...
赠送jar包:lucene-spatial-6.6.0.jar; 赠送原API文档:lucene-spatial-6.6.0-javadoc.jar; 赠送源代码:lucene-spatial-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-spatial-6.6.0.pom; 包含翻译后的API...
赠送jar包:lucene-misc-6.6.0.jar; 赠送原API文档:lucene-misc-6.6.0-javadoc.jar; 赠送源代码:lucene-misc-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-misc-6.6.0.pom; 包含翻译后的API文档:lucene...
赠送jar包:lucene-core-6.6.0.jar; 赠送原API文档:lucene-core-6.6.0-javadoc.jar; 赠送源代码:lucene-core-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-core-6.6.0.pom; 包含翻译后的API文档:lucene...
赠送jar包:lucene-backward-codecs-6.6.0.jar; 赠送原API文档:lucene-backward-codecs-6.6.0-javadoc.jar; 赠送源代码:lucene-backward-codecs-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-backward-...
赠送jar包:lucene-backward-codecs-6.6.0.jar; 赠送原API文档:lucene-backward-codecs-6.6.0-javadoc.jar; 赠送源代码:lucene-backward-codecs-6.6.0-sources.jar; 赠送Maven依赖信息文件:lucene-backward-...