java htmlparser 使用教程_htmlparser使用指南

最新推荐文章于 2021-03-06 03:18:49 发布

原创最新推荐文章于 2021-03-06 03:18:49 发布 · 307 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#java htmlparser 使用教程

本文主要介绍Java中HtmlParser的使用，包含采用Visitor和Filter方式访问HTML的代码示例，如设置URL、编码，使用NodeVisitor、NodeFilter等进行节点访问和提取。还提及相关项目，如nekohtml可将HTML转为标准XML文档，不过文档较少。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1.*采用Visitor方式访问Html2.3.try{4. Parser parser=newParser();5. parser.setURL(”http://www.google.com”);6. parser.setEncoding(parser.getEncoding());7. NodeVisitor visitor=newNodeVisitor() {8.publicvoidvisitTag(Tag tag) {9. logger.fatal(”testVisitorAll() Tag name is :”10.+tag.getTagName()+” \n Class is :”11.+tag.getClass());12. }13.14. };15.16. parser.visitAllNodesWith(visitor);17. }catch(ParserException e) {18. e.printStackTrace();19. }20.21.*采用Filter方式访问html22.23.try{24.25. NodeFilter filter=newNodeClassFilter(LinkTag.class);26. Parser parser=newParser();27. parser.setURL(”http://www.google.com”);28. parser.setEncoding(parser.getEncoding());29. NodeList list=parser.extractAllNodesThatMatch(filter);30.for(inti=0; i

149.*/150.publicvoidtestImageVisitor() {151.try{152. ImageTag imgLink;153. ObjectFindingVisitor visitor=newObjectFindingVisitor(154. ImageTag.class);155. Parser parser=newParser();156. parser.setURL(”http://www.google.com”);157. parser.setEncoding(parser.getEncoding());158. parser.visitAllNodesWith(visitor);159. Node[] nodes=visitor.getTags();160.for(inti=0; i

176.*/177.publicvoidtestNodeFilter() {178.try{179. NodeFilter filter=newTagNameFilter(”IMG”);180. Parser parser=newParser();181. parser.setURL(”http://www.google.com”);182. parser.setEncoding(parser.getEncoding());183. NodeList list=parser.extractAllNodesThatMatch(filter);184.for(inti=0; i

194.*/195.publicvoidtestLinkTag() {196.try{197.198. NodeFilter filter=newNodeClassFilter(LinkTag.class);199. Parser parser=newParser();200. parser.setURL(”http://www.google.com”);201. parser.setEncoding(parser.getEncoding());202. NodeList list=parser.extractAllNodesThatMatch(filter);203.for(inti=0; i用法

214.*/215.publicvoidtestLinkCSS() {216.try{217.218. Parser parser=newParser();219. parser220. .setInputHTML(”

Link Test”221.+“”222.+“”223.+“”+“”);224. parser.setEncoding(parser.getEncoding());225. NodeList nodeList=null;226.227.for(NodeIterator e=parser.elements(); e.hasMoreNodes();) {228. Node node=e.nextNode();229. logger230. .fatal(”testLinkCSS()”+node.getText()231.+node.getClass());232.233. }234. }catch(Exception e) {235. e.printStackTrace();236. }237. }238./*239. * 测试OrFilter的用法

240.*/241.publicvoidtestOrFilter() {242. NodeFilter inputFilter=newNodeClassFilter(InputTag.class);243. NodeFilter selectFilter=newNodeClassFilter(SelectTag.class);244. Parser myParser;245. NodeList nodeList=null;246.247.try{248. Parser parser=newParser();249. parser250. .setInputHTML(”

OrFilter Test”251.+“”252.+“”253.+“”254.+“”255.+“”256.+“”257.+“12”258.+“ yeeach.com”259.+“”);260.261. parser.setEncoding(parser.getEncoding());262. OrFilter lastFilter=newOrFilter();263. lastFilter.setPredicates(newNodeFilter[] { selectFilter,264. inputFilter });265. nodeList=parser.parse(lastFilter);266.for(inti=0; i<=nodeList.size(); i++) {267.if(nodeList.elementAt(i)instanceofInputTag) {268. InputTag tag=(InputTag) nodeList.elementAt(i);269. logger.fatal(”OrFilter tag name is :”+tag.getTagName()270.+” ,tag value is:”+tag.getAttribute(”value”));271. }272.if(nodeList.elementAt(i)instanceofSelectTag) {273. SelectTag tag=(SelectTag) nodeList.elementAt(i);274. NodeList list=tag.getChildren();275.276.for(intj=0; j的解析

292.*/293.publicvoidtestTable() {294. Parser myParser;295. NodeList nodeList=null;296. myParser=Parser.createParser(”

”+“

1-11	1-12	1-13
1-21	1-22	1-23
1-31	1-32	1-33

”300.+“

2-11	2-12	2-13
2-21	2-22	2-23
2-31	2-32	2-33

”304.+“”, “GBK”);305. NodeFilter tableFilter=newNodeClassFilter(TableTag.class);306. OrFilter lastFilter=newOrFilter();307. lastFilter.setPredicates(newNodeFilter[] { tableFilter });308.try{309. nodeList=myParser.parse(lastFilter);310.for(inti=0; i<=nodeList.size(); i++) {311.if(nodeList.elementAt(i)instanceofTableTag) {312. TableTag tag=(TableTag) nodeList.elementAt(i);313. TableRow[] rows=tag.getRows();314.315.for(intj=0; j”+td[k].toPlainTextString());320. }321.322. }323.324. }325. }326.327. }catch(ParserException e) {328. e.printStackTrace();329. }330. }331./*332. * 测试NodeVisitor的用法，遍历所有节点

333.*/334.publicvoidtestVisitorAll() {335.try{336. Parser parser=newParser();337. parser.setURL(”http://www.google.com”);338. parser.setEncoding(parser.getEncoding());339. NodeVisitor visitor=newNodeVisitor() {340.publicvoidvisitTag(Tag tag) {341. logger.fatal(”testVisitorAll() Tag name is :”342.+tag.getTagName()+” \n Class is :”343.+tag.getClass());344. }345.346. };347.348. parser.visitAllNodesWith(visitor);349. }catch(ParserException e) {350. e.printStackTrace();351. }352. }353./*354. * 测试对指定Tag的NodeVisitor的用法

355.*/356.publicvoidtestTagVisitor() {357.try{358.359. Parser parser=newParser(360. “

dddd”361.+“”362.+“”363.+“”+“”364.+“ yeeach.com”365.+“”);366. NodeVisitor visitor=newNodeVisitor() {367.publicvoidvisitTag(Tag tag) {368.if(taginstanceofHeadTag) {369. logger.fatal(”visitTag() HeadTag : Tag name is :”370.+tag.getTagName()+” \n Class is :”371.+tag.getClass()+“\n Text is :”372.+tag.getText());373. }elseif(taginstanceofTitleTag) {374. logger.fatal(”visitTag() TitleTag : Tag name is :”375.+tag.getTagName()+” \n Class is :”376.+tag.getClass()+“\n Text is :”377.+tag.getText());378.379.380. }elseif(taginstanceofLinkTag) {381. logger.fatal(”visitTag() LinkTag : Tag name is :”382.+tag.getTagName()+” \n Class is :”383.+tag.getClass()+“\n Text is :”384.+tag.getText()+” \n getAttribute is :”385.+tag.getAttribute(”href”));386. }else{387. logger.fatal(”visitTag() : Tag name is :”388.+tag.getTagName()+” \n Class is :”389.+tag.getClass()+“\n Text is :”390.+tag.getText());391. }392.393. }394.395. };396.397. parser.visitAllNodesWith(visitor);398. }catch(Exception e) {399. e.printStackTrace();400. }401. }402./*403. * 测试HtmlPage的用法

404.*/405.publicvoidtestHtmlPage() {406. String inputHTML=“”+“

”407.+“Welcome to the HTMLParser website”408.+“”+“”+“Welcome to HTMLParser”409.+“

1-11	1-12	1-13
1-21	1-22	1-23
1-31	1-32	1-33

”413.+“

2-11	2-12	2-13
2-21	2-22	2-23
2-31	2-32	2-33

”417.+“”+“”;418. Parser parser=newParser();419.try{420. parser.setInputHTML(inputHTML);421. parser.setEncoding(parser.getURL());422. HtmlPage page=newHtmlPage(parser);423. parser.visitAllNodesWith(page);424. logger.fatal(”testHtmlPage-title is :”+page.getTitle());425. NodeList list=page.getBody();426.427.for(NodeIterator iterator=list.elements(); iterator428. .hasMoreNodes();) {429. Node node=iterator.nextNode();430. logger.fatal(”testHtmlPage-node is :”+node.toHtml());431. }432.433. }catch(ParserException e) {434.//TODO Auto-generated catch block435. e.printStackTrace();436. }437. }438./*439. * 测试LinkBean的用法

440.*/441.publicvoidtestLinkBean() {442. Parser parser=newParser();443.444. LinkBean linkBean=newLinkBean();445. linkBean.setURL(”http://www.google.com”);446. URL[] urls=linkBean.getLinks();447.448.for(inti=0; i

5、相关的项目

nekohtml

：评价比htmlparser好，把html正规化标准的xml文档，用xerces处理，但文档较少。

其他一些html parser可以参考相关的汇总文章：

6、参考文档

crawler,爬虫,htmlparser,nekohtml,scrape,scraping,spider