[转][htmlparser]htmlparser应用例子（全）

2012-12-28

[转][htmlparser]htmlparser使用例子（全）from :?http://gcgmh.iteye.com/blog/474093??import?java.net.UR

[转][htmlparser]htmlparser使用例子（全）

from :?http://gcgmh.iteye.com/blog/474093

import?java.net.URL;??
??
import?junit.framework.TestCase;??
??
import?org.apache.log4j.Logger;??
import?org.htmlparser.Node;??
import?org.htmlparser.NodeFilter;??
import?org.htmlparser.Parser;??
import?org.htmlparser.Tag;??
import?org.htmlparser.beans.LinkBean;??
import?org.htmlparser.filters.NodeClassFilter;??
import?org.htmlparser.filters.OrFilter;??
import?org.htmlparser.filters.TagNameFilter;??
import?org.htmlparser.tags.HeadTag;??
import?org.htmlparser.tags.ImageTag;??
import?org.htmlparser.tags.InputTag;??
import?org.htmlparser.tags.LinkTag;??
import?org.htmlparser.tags.OptionTag;??
import?org.htmlparser.tags.SelectTag;??
import?org.htmlparser.tags.TableColumn;??
import?org.htmlparser.tags.TableRow;??
import?org.htmlparser.tags.TableTag;??
import?org.htmlparser.tags.TitleTag;??
import?org.htmlparser.util.NodeIterator;??
import?org.htmlparser.util.NodeList;??
import?org.htmlparser.util.ParserException;??
import?org.htmlparser.visitors.HtmlPage;??
import?org.htmlparser.visitors.NodeVisitor;??
import?org.htmlparser.visitors.ObjectFindingVisitor;??
??
public?class?T?extends?TestCase?{??
??
??private?static?final?Logger?logger?=?Logger.getLogger(T.class);??
??
??public?T(String?name)?{??
????super(name);??
??}??
??
??/*?
???*?测试ObjectFindVisitor的用法?
???*/??
??public?void?testImageVisitor()?{??
????try?{??
??????ImageTag?imgLink;??
??????ObjectFindingVisitor?visitor?=?new?ObjectFindingVisitor(ImageTag.class);??
??????Parser?parser?=?new?Parser();??
??????parser.setURL("http://www.google.com");??
??????parser.setEncoding(parser.getEncoding());??
??????parser.visitAllNodesWith(visitor);??
??????Node[]?nodes?=?visitor.getTags();??
??????for?(int?i?=?0;?i?<?nodes.length;?i++)?{??
????????imgLink?=?(ImageTag)?nodes[i];??
????????logger.fatal("testImageVisitor()?ImageURL?=?"?+?imgLink.getImageURL());??
????????logger.fatal("testImageVisitor()?ImageLocation?=?"?+?imgLink.extractImageLocn());??
????????logger.fatal("testImageVisitor()?SRC?=?"?+?imgLink.getAttribute("SRC"));??
??????}??
????}?catch?(Exception?e)?{??
??????e.printStackTrace();??
????}??
??}??
??
??/*?
???*?测试TagNameFilter用法?
???*/??
??public?void?testNodeFilter()?{??
????try?{??
??????NodeFilter?filter?=?new?TagNameFilter("IMG");??
??????Parser?parser?=?new?Parser();??
??????parser.setURL("http://www.google.com");??
??????parser.setEncoding(parser.getEncoding());??
??????NodeList?list?=?parser.extractAllNodesThatMatch(filter);??
??????for?(int?i?=?0;?i?<?list.size();?i++)?{??
????????logger.fatal("testNodeFilter()?"?+?list.elementAt(i).toHtml());??
??????}??
????}?catch?(Exception?e)?{??
??????e.printStackTrace();??
????}??
??
??}??
??
??/*?
???*?测试NodeClassFilter用法?
???*/??
??public?void?testLinkTag()?{??
????try?{??
??
??????NodeFilter?filter?=?new?NodeClassFilter(LinkTag.class);??
??????Parser?parser?=?new?Parser();??
??????parser.setURL("http://www.google.com");??
??????parser.setEncoding(parser.getEncoding());??
??????NodeList?list?=?parser.extractAllNodesThatMatch(filter);??
??????for?(int?i?=?0;?i?<?list.size();?i++)?{??
????????LinkTag?node?=?(LinkTag)?list.elementAt(i);??
????????logger.fatal("testLinkTag()?Link?is?:"?+?node.extractLink());??
??????}??
????}?catch?(Exception?e)?{??
??????e.printStackTrace();??
????}??
??
??}??
??
??/*?
???*?测试<link?href="?text=’text/css’?rel=’stylesheet’?/>用法?
???*/??
??public?void?testLinkCSS()?{??
????try?{??
??
??????Parser?parser?=?new?Parser();??
??????parser.setInputHTML("<head><title>Link?Test</title>"??
??????????+?"<link?href=’/test01/css.css'?text='text/css'?rel='stylesheet'?/>"??
??????????+?"<link?href='/test02/css.css'?text='text/css'?rel='stylesheet'?/>"?+?"</head>"??
??????????+?"<body>");??
??????parser.setEncoding(parser.getEncoding());??
??
??????for?(NodeIterator?e?=?parser.elements();?e.hasMoreNodes();)?{??
????????Node?node?=?e.nextNode();??
????????logger.fatal("testLinkCSS()"?+?node.getText()?+?node.getClass());??
??
??????}??
????}?catch?(Exception?e)?{??
??????e.printStackTrace();??
????}??
??}??
??
??/*?
???*?测试OrFilter的用法?
???*/??
??public?void?testOrFilter()?{??
????NodeFilter?inputFilter?=?new?NodeClassFilter(InputTag.class);??
????NodeFilter?selectFilter?=?new?NodeClassFilter(SelectTag.class);??
??
????NodeList?nodeList?=?null;??
??
????try?{??
??????Parser?parser?=?new?Parser();??
??????parser??
??????????.setInputHTML("<head><title>OrFilter?Test</title>"??
??????????????+?"<link?href='/test01/css.css'?text='text/css'?rel='stylesheet'?/>"??
??????????????+?"<link?href='/test02/css.css'?text='text/css'?rel='stylesheet'?/>"??
font-size: 1em; margin-top: 0px; margin-righ 1 楼满月无双 2011-08-10 testLinkCSS()方法怎么取出 <link href属性的值呢？？ 2 楼 zxhDaniel 2011-08-13 满月无双写道testLinkCSS()方法怎么取出 <link href属性的值呢？？
你可以拿到那个link这个节点的对象Node，然后再用getAttribute()这种类似的方法取出来

热点排行

CSS

[转][htmlparser]htmlparser应用例子（全）