itext 把html 生成 pdf html 生成 pdf

最新推荐文章于 2024-07-16 14:57:15 发布

置顶我已释然

最新推荐文章于 2024-07-16 14:57:15 发布

阅读量2.9k

点赞数

文章标签： html exception string border alignment encoding

本文链接：https://blog.csdn.net/zjshzxh/article/details/5749008

版权

本人在做把个人博客生成pdf电子书时，在网上找了很多itext的例子，发现很多是不支持html标记的。因此把个人的一点经验贡献出来。

1.把html页面转换成pdf（itext），页面符合w3c标准。

支持中文

所要包为core-renderer.jar,iText-2.0.8.jar

a.html的内容

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <title>My First Document</title> <mce:style type="text/css"></mce:style><style type="text/css" mce_bogus="1"> b { color: green; } body { font-family: SimSun; font-size:22px; } </style> </head> <body> <p> <b>fdasfdas！</b>FDASFDAS We've come for your Java. </p> </body> </html>

java内容如下

package com.test.mail; import java.io.File; import java.io.FileOutputStream; import org.w3c.dom.Document; import org.xhtmlrenderer.pdf.ITextFontResolver; import org.xhtmlrenderer.pdf.ITextRenderer; import com.lowagie.text.HeaderFooter; import com.lowagie.text.Phrase; import com.lowagie.text.Rectangle; import com.lowagie.text.pdf.BaseFont; public class ITextRendererTest { public static void main(String[] args) throws Exception { String inputFile = "WebRoot/1.html"; String url = new File(inputFile).toURI().toURL().toString(); String outputFile = "WebRoot/a.pdf"; FileOutputStream os = new FileOutputStream(outputFile); ITextRenderer renderer = new ITextRenderer(); renderer.setDocument(url); renderer.setDocumentFromString(""); // 解决中文支持问题 ITextFontResolver fontResolver = renderer.getFontResolver(); fontResolver.addFont("/home/core/simsun.ttf", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED); // fontResolver.addFont("WebRoot/simsun.ttc", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED); // 解决图片的相对路径问题 // renderer.getSharedContext().setBaseURL("file:/D:/z/temp/"); renderer.layout(); renderer.createPDF(os); os.close(); } }

2.把 html页面转换成pdf（itext），页面不符合w3c标准。

支持中文

所要包为core-renderer.jar,iText-2.0.8.jar，jtidy.jar

首先要把html页面转换成标准的w3c的html

java代码1，该方法为直接url连接的，如www.hao123.com

package com.test.pdf; import java.io.BufferedInputStream; import java.io.FileOutputStream; import java.io.IOException; import java.io.PrintWriter; import java.net.URL; import org.w3c.tidy.Tidy; public class TestHTML2XML { private String url; private String outFileName; private String errOutFileName; public TestHTML2XML(String url, String outFileName, String errOutFileName) { this.url = url; this.outFileName = outFileName; this.errOutFileName = errOutFileName; } public void convert() { URL u; BufferedInputStream in; FileOutputStream out; Tidy tidy = new Tidy(); tidy.setInputEncoding("utf-8"); tidy.setOutputEncoding("utf-8"); //Tell Tidy to convert HTML to XML tidy.setXmlOut(true); try { //Set file for error messages tidy.setErrout(new PrintWriter(new PrintWriter(errOutFileName), true)); u = new URL(url); //Create input and output streams in = new BufferedInputStream(u.openStream()); out = new FileOutputStream(outFileName); //Convert files tidy.parse(in, out); //Clean up in.close(); out.close(); } catch (IOException e) { System.out.println(this.toString() + e.toString()); } } public static void main(String[] args) { /* * Parameters are: * URL of HTML file * Filename of output file * Filename of error file */ TestHTML2XML t = new TestHTML2XML("http://hi.baidu.com/%D0%A1%B2%D6%B0%A2%CB%C4/blog/item/c3db65c88eb3581a7f3e6f30.html", "WebRoot/news.html", "erro.html"); t.convert(); } }

然后再用第一种方法。

java代码2。不标准的html直接在目录下面

package com.test.pdf; import java.io.BufferedInputStream; import java.io.File; import java.io.FileInputStream; import java.io.FileNotFoundException; import java.io.FileOutputStream; import java.io.InputStream; import java.io.OutputStream; import org.w3c.tidy.Tidy; public class Test { public static void main(String[] args) { Tidy tidy=new Tidy(); tidy.setXmlOut(true); tidy.setInputEncoding("utf-8"); tidy.setOutputEncoding("utf-8"); InputStream ss=null; try { ss = new FileInputStream("WebRoot/228581"); } catch (FileNotFoundException e) { } BufferedInputStream s=new BufferedInputStream(ss); OutputStream os=null; try { os=new FileOutputStream("WebRoot/3.html"); } catch (FileNotFoundException e) { } tidy.parse(ss, os); } }

然后做第一个方法

3.在java方法中声称html代码的字符串，然后转换成pdf。

支持中文

所要包为core-renderer.jar,iText-2.0.8.jar

package com.test.pdf; import java.io.ByteArrayInputStream; import java.io.DataInputStream; import java.io.DataOutputStream; import java.io.FileNotFoundException; import java.io.FileOutputStream; import java.io.InputStream; import java.io.OutputStream; import java.io.StringBufferInputStream; import javax.xml.parsers.DocumentBuilder; import javax.xml.parsers.DocumentBuilderFactory; import org.xhtmlrenderer.pdf.ITextFontResolver; import org.xhtmlrenderer.pdf.ITextRenderer; import com.lowagie.text.DocumentException; import com.lowagie.text.pdf.BaseFont; import com.lowagie.text.pdf.PdfWriter; public class Test1 { public static void main(String[] args) { StringBuffer buf = new StringBuffer(); buf.append("<?xml version='1.0' encoding='UTF-8'?>"); buf.append("<html xmlns=/"http://www.w3.org/1999/xhtml/">"); buf.append("<head><meta http-equiv=/"Content-Type/" content=/"text/html; charset=UTF-8/" /><mce:style type='text/css'></mce:style><style type='text/css' mce_bogus="1">"); buf.append("body {font-family: SimSun;font-size:22px;}"); buf.append("h3 { border: 1px solid #aaaaff; background: #ccccff; "); buf.append("padding: 1em; text-transform: capitalize; font-family: SimSun; font-weight: normal;}"); buf.append("p { margin: 1em 1em 4em 3em; } p:first-letter { color: red; font-size: 150%; }"); buf.append("h2 { background: #5555ff; color: white; border: 10px solid black; padding: 3em; font-size: 200%; }"); buf.append("</style></head>"); buf.append("<body>"); buf.append("<p>你好吗!</p>"); // for(int i=3; i>0; i--) { // buf.append("<h3>"+i+" bottles o发打算发打算发打算发打算发大f beer on the wall, " // + i + " bottles of beer!</h3>"); // buf.append("<p>Take one down and pass it around, " // + (i-1) + " bottles of beer on the wall</p>/n"); // } buf.append("<h2>No more bottles of beer on the wall, no more bottles of beer. "); buf.append("Go to the store and buy some more, 99 bottles of beer on the wall.</h2>"); buf.append("</body>"); buf.append("</html>"); DocumentBuilder builder; org.w3c.dom.Document doc=null; // InputStream is=new StringBufferInputStream(); ByteArrayInputStream bsin = new ByteArrayInputStream(buf.toString().getBytes()); DataInputStream dsin = new DataInputStream(bsin); try { builder = DocumentBuilderFactory.newInstance().newDocumentBuilder(); doc = builder.parse(dsin); } catch (Exception e1) { } ITextRenderer renderer = new ITextRenderer(); // renderer.setDocument(doc,null); renderer.setDocumentFromString(buf.toString()); ITextFontResolver fontResolver = renderer.getFontResolver(); try { fontResolver.addFont("/home/core/simsun.ttf", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED); } catch (Exception e1) { e1.printStackTrace(); } String outputFile = "WebRoot/bottles1.pdf"; OutputStream os=null; try { os = new FileOutputStream(outputFile); } catch (FileNotFoundException e) { e.printStackTrace(); } renderer.layout(); try { renderer.createPDF(os); PdfWriter pd= renderer.getWriter(); pd.newPage(); os.close(); } catch (Exception e) { e.printStackTrace(); } } }

4.itext把html生成pdf，然后转换成pdf。

读去一次后要关闭documeng对象

package com.test.pdf; import java.io.ByteArrayInputStream; import java.io.DataInputStream; import java.io.FileOutputStream; import com.lowagie.text.Document; import com.lowagie.text.DocumentException; import com.lowagie.text.Element; import com.lowagie.text.HeaderFooter; import com.lowagie.text.Paragraph; import com.lowagie.text.Phrase; import com.lowagie.text.Rectangle; import com.lowagie.text.html.HtmlParser; import com.lowagie.text.html.HtmlWriter; import com.lowagie.text.html.simpleparser.HTMLWorker; import com.lowagie.text.pdf.PdfWriter; public class Test2 { public static void main(String[] args) throws Exception, DocumentException { StringBuffer buf = new StringBuffer(); buf.append("<?xml version='1.0' encoding='UTF-8'?>"); buf.append("<html xmlns=/"http://www.w3.org/1999/xhtml/">"); buf.append("<head><meta http-equiv=/"Content-Type/" content=/"text/html; charset=UTF-8/" /><mce:style type='text/css'></mce:style><style type='text/css' mce_bogus="1">"); buf.append("body {font-family: SimSun;font-size:22px;}"); buf.append("h3 { border: 1px solid #aaaaff; background: #ccccff; "); buf.append("padding: 1em; text-transform: capitalize; font-family: SimSun; font-weight: normal;}"); buf.append("p { margin: 1em 1em 4em 3em; } p:first-letter { color: red; font-size: 150%; }"); buf.append("h2 { background: #5555ff; color: white; border: 10px solid black; padding: 3em; font-size: 200%; }"); buf.append("</style></head>"); buf.append("<body>"); buf.append("<p>xxx</p>"); buf.append("<h2>No more bottles of beer on the wall, no more bottles of beer. "); buf.append("Go to the store and buy some more, 99 bottles of beer on the wall.</h2>"); buf.append("</body>"); buf.append("</html>"); ByteArrayInputStream bsin = new ByteArrayInputStream(buf.toString().getBytes()); DataInputStream dsin = new DataInputStream(bsin); Document document = new Document(); PdfWriter.getInstance(document, new FileOutputStream("WebRoot/Helloworld.pdf")); document.open(); /** * 页眉 */ HeaderFooter footer = new HeaderFooter(new Phrase("This is page: "), true); footer.setAlignment(HeaderFooter.ALIGN_CENTER); document.setFooter(footer); HeaderFooter header =new HeaderFooter(new Paragraph("我是标题"),false); document.setHeader(header); Paragraph d=new Paragraph(); // document.add(new Phrase(str)); Paragraph dd=new Paragraph("ddddddddd"); document.add(dd); dd.add("xxxxd"); document.add(dd); document.newPage(); // com.lowagie.text.html.HtmlParser p=new HtmlParser(); p.go(document, "WebRoot/a.html"); // d1.parse(document, dsin); document.close(); } }

4.itext 把html生成pdf(可以无限次添加html而不会关闭document)，然后转换成pdf（很牛）。

所要包为iText-2.0.8.ja

首先要新建个HtmlP类继成HtmlParser 复写一下方法

public void go(DocListener document, String file) { try { SAXmyHtmlHandler d =new SAXmyHtmlHandler(document); d.setControlOpenClose(false); parser.parse(file,d ); } catch(SAXException se) { throw new ExceptionConverter(se); } catch(IOException ioe) { throw new ExceptionConverter(ioe); } }

然后就可以转换了

package com.test.pdf; import java.io.ByteArrayInputStream; import java.io.DataInputStream; import java.io.FileOutputStream; import com.lowagie.text.Document; import com.lowagie.text.DocumentException; import com.lowagie.text.Element; import com.lowagie.text.HeaderFooter; import com.lowagie.text.Paragraph; import com.lowagie.text.Phrase; import com.lowagie.text.Rectangle; import com.lowagie.text.html.HtmlParser; import com.lowagie.text.html.HtmlWriter; import com.lowagie.text.html.simpleparser.HTMLWorker; import com.lowagie.text.pdf.PdfWriter; public class Test2 { public static void main(String[] args) throws Exception, DocumentException { StringBuffer buf = new StringBuffer(); buf.append("<?xml version='1.0' encoding='UTF-8'?>"); buf.append("<html xmlns=/"http://www.w3.org/1999/xhtml/">"); buf.append("<head><meta http-equiv=/"Content-Type/" content=/"text/html; charset=UTF-8/" /><mce:style type='text/css'></mce:style><style type='text/css' mce_bogus="1">"); buf.append("body {font-family: SimSun;font-size:22px;}"); buf.append("h3 { border: 1px solid #aaaaff; background: #ccccff; "); buf.append("padding: 1em; text-transform: capitalize; font-family: SimSun; font-weight: normal;}"); buf.append("p { margin: 1em 1em 4em 3em; } p:first-letter { color: red; font-size: 150%; }"); buf.append("h2 { background: #5555ff; color: white; border: 10px solid black; padding: 3em; font-size: 200%; }"); buf.append("</style></head>"); buf.append("<body>"); buf.append("<p>xxx</p>"); buf.append("<h2>No more bottles of beer on the wall, no more bottles of beer. "); buf.append("Go to the store and buy some more, 99 bottles of beer on the wall.</h2>"); buf.append("</body>"); buf.append("</html>"); ByteArrayInputStream bsin = new ByteArrayInputStream(buf.toString().getBytes()); DataInputStream dsin = new DataInputStream(bsin); Document document = new Document(); PdfWriter.getInstance(document, new FileOutputStream("WebRoot/Helloworld.pdf")); document.open(); /** * 页眉 */ HeaderFooter footer = new HeaderFooter(new Phrase("This is page: "), true); footer.setAlignment(HeaderFooter.ALIGN_CENTER); document.setFooter(footer); HeaderFooter header =new HeaderFooter(new Paragraph("我是标题"),false); document.setHeader(header); Paragraph d=new Paragraph(); // document.add(new Phrase(str)); Paragraph dd=new Paragraph("ddddddddd"); document.add(dd); dd.add("xxxxd"); document.add(dd); document.newPage(); // com.lowagie.text.html.HtmlParser d1=new HtmlParser(); HtmlP p=new HtmlP(); System.out.println(document); p.go(document, "WebRoot/a.html"); p.go(document, "WebRoot/a.html"); // d1.parse(document, dsin); document.newPage(); document.add(dd); // d1.go(document, "WebRoot/a.html"); document.close(); } }

该方法不支持外部css样式，只支持标签中的css

5.itext 生成目录。

package com.test.pdf; import java.awt.Color; import java.io.FileOutputStream; import com.lowagie.text.Chapter; import com.lowagie.text.Chunk; import com.lowagie.text.Document; import com.lowagie.text.Element; import com.lowagie.text.Font; import com.lowagie.text.FontFactory; import com.lowagie.text.PageSize; import com.lowagie.text.Paragraph; import com.lowagie.text.Section; import com.lowagie.text.pdf.PdfWriter; /** * Creates a document with outlines (bookmarks) using the Chapter and Section object. * * @author blowagie */ public class ChapterSection { /** * Creates a document with outlines. * * @param args * no arguments needed */ public static void main(String[] args) { System.out.println("Chapters and Sections"); // step 1: creation of a document-object Document document = new Document(PageSize.A4, 50, 50, 50, 50); try { // step 2: we create a writer that listens to the document PdfWriter writer=PdfWriter.getInstance(document, new FileOutputStream("WebRoot/ChapterSection.pdf")); // step 3: we open the document writer.setViewerPreferences(PdfWriter.PageModeUseOutlines); document.open(); // step 4: we add content to the document // we define some fonts Font chapterFont = FontFactory.getFont(FontFactory.HELVETICA, 24, Font.NORMAL, new Color(255, 0, 0)); Font sectionFont = FontFactory.getFont(FontFactory.HELVETICA, 20, Font.NORMAL, new Color(0, 0, 255)); Font subsectionFont = FontFactory.getFont(FontFactory.HELVETICA, 18, Font.BOLD, new Color(0, 64, 64)); // we create some paragraphs Paragraph blahblah = new Paragraph("blah blah blah blah blah blah blaah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah"); Paragraph blahblahblah = new Paragraph("blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blaah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah blah"); // this loop will create 7 chapters for (int i = 1; i < 8; i++) { Paragraph cTitle = new Paragraph("This is chapter " + i, chapterFont); Chapter chapter = new Chapter(cTitle, i); // in chapter 4 we change the alignment to ALIGN_JUSTIFIED if (i == 4) { blahblahblah.setAlignment(Element.ALIGN_JUSTIFIED); blahblah.setAlignment(Element.ALIGN_JUSTIFIED); chapter.add(blahblah); } // in chapter 5, the alignment is changed again if (i == 5) { blahblahblah.setAlignment(Element.ALIGN_CENTER); blahblah.setAlignment(Element.ALIGN_RIGHT); chapter.add(blahblah); } // the alignment is changed to ALIGN_JUSTIFIED again if (i == 6) { blahblahblah.setAlignment(Element.ALIGN_JUSTIFIED); blahblah.setAlignment(Element.ALIGN_JUSTIFIED); } // in every chapter 3 sections will be added for (int j = 1; j < 4; j++) { Paragraph sTitle = new Paragraph("This is section " + j + " in chapter " + i, sectionFont); Section section = chapter.addSection(sTitle, 1); // for chapters > 2, the outine isn't open by default if (i > 2) section.setBookmarkOpen(false); // in all chapters except the 1st one, some extra text is added to section 3 if (j == 3 && i > 1) { section.setIndentationLeft(72); section.add(blahblah); section.add(new Paragraph("test")); } // in every section 3 subsections are added for (int k = 1; k < 4; k++) { Paragraph subTitle = new Paragraph("This is subsection " + k + " of section " + j, subsectionFont); Section subsection = section.addSection(subTitle, 3); // in the first subsection of section 3, extra text is added if (k == 1 && j == 3) { subsection.add(blahblahblah); } subsection.add(blahblah); } // in the section section of every chapter > 2 extra text is added if (j == 2 && i > 2) { section.add(blahblahblah); } // a new page is added after the second section in Chapter 1 if (j == 2 && i == 1) { section.add(Chunk.NEXTPAGE); } } document.add(chapter); } } catch(Exception de) { de.printStackTrace(); } // step 5: we close the document document.close(); } }

没有时间，暂时先写这么多，解急用！