Package org.apache.camel.dataformat.tagsoup

Examples of org.apache.camel.dataformat.tagsoup.TidyMarkupDataFormat

304
305
306
307
308
309
310
311
312
313
314
315
316
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(new BufferedInputStream(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
305
306
307
308
309
310
311
312
313
314
315
316
317
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(IOHelper.buffered(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
304
305
306
307
308
309
310
311
312
313
314
315
316
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(new BufferedInputStream(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
272
273
274
275
276
277
278
279
280
281
282
283
284
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            content = dataFormat.asStringTidyMarkup(new BufferedInputStream(url.openStream()));
        } catch (Throwable e) {
            if (errorOnDownloadFailure) {
                throw new MojoExecutionException("Download or validation of '" + page + "' failed: " + e);
            } else {
                getLog().error("Download or validation of '" + page + "' failed: " + e);
View Full Code Here
288
289
290
291
292
293
294
295
296
297
298
299
300
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(new BufferedInputStream(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
285
286
287
288
289
290
291
292
293
294
295
296
297
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(new BufferedInputStream(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
282
283
284
285
286
287
288
289
290
291
292
293
294
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            content = dataFormat.asStringTidyMarkup(new BufferedInputStream(url.openStream()));
        } catch (Throwable e) {
            if (errorOnDownloadFailure) {
                throw new MojoExecutionException("Download or validation of '" + page + "' failed: " + e);
            } else {
                getLog().error("Download or validation of '" + page + "' failed: " + e);
View Full Code Here
304
305
306
307
308
309
310
311
312
313
314
315
316
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(new BufferedInputStream(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
287
288
289
290
291
292
293
294
295
296
297
298
299
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(new BufferedInputStream(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
305
306
307
308
309
310
311
312
313
314
315
316
317
        getLog().info("Downloading: " + page);
        URL url = new URL(page);       
       
        try {
            TidyMarkupDataFormat dataFormat = new TidyMarkupDataFormat();
            dataFormat.setMethod("html");
            Node doc = dataFormat.asNodeTidyMarkup(IOHelper.buffered(url.openStream()));
            XPath xpath = XPathFactory.newInstance().newXPath();
            Node nd = (Node)xpath.evaluate("//div[@class='" + contentDivClass + "']", doc, XPathConstants.NODE);
            if (nd != null) {
                return  new XmlConverter().toString(nd, null);
            }
View Full Code Here
TOP

Related Classes of org.apache.camel.dataformat.tagsoup.TidyMarkupDataFormat

  • org.apache.camel.maven.HtmlToPdfMojo
  • org.ccil.cowan.tagsoup.HTMLSchema
  • org.ccil.cowan.tagsoup.Parser
  • org.ccil.cowan.tagsoup.XMLWriter
  • org.xml.sax.InputSource
  • org.xml.sax.XMLReader
  • javax.xml.transform.dom.DOMResult
  • javax.xml.transform.sax.SAXSource
  • javax.xml.transform.Transformer
  • java.io.StringWriter
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.