利用itext将html文件转化pdf文件

简单介绍一下：如何将html文件转化为pdf文件。

仅供自己学习。

常见的几个方法总结：

1：最简单的html用String方式表示的形式

package com.ctbri.test;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;

import com.itextpdf.html2pdf.HtmlConverter;

/**
 * Converts a simple Hello World HTML String to a PDF document.
 */
public class C01E01_HelloWorld {

	/** 
	 * The HTML-html原文件路径
	 * The target —— 结果的输出所在的文件夹
	 * DesT —— pdf输出的具体路径
	 */
	public static final String HTML = "
Test
Hello World
";
	public static final String TARGET = "target/results/ch01/";
	public static final String DEST = String.format("%stest-01.pdf", TARGET);
	
    public static void main(String[] args) throws IOException {
        File file = new File(TARGET);
        file.mkdirs();
        new C01E01_HelloWorld().createPdf(HTML, DEST);
        System.out.println("ok");
    }
    
    /**
     * Creates the PDF file.
     */
    public void createPdf(String html, String dest) throws IOException {
        HtmlConverter.convertToPdf(html, new FileOutputStream(dest));
    }
}

2、需要引入图片、css文件

对于这部分需要引入几个特定的属性：

1. BASEURI 用于表示装载有css、image、以及html等文件的文件夹
   
2. SRC    html文件所在的路径
   
3. TARGET PDF文件所在的父路径
   
4. DEST 生成的pdf文件的路径
   

比如：

public static final String BASEURI = "src/main/resources/html/";
public static final String SRC = String.format("%shello.html", BASEURI);
public static final String TARGET = "target/results/ch01/";
public static final String DEST = String.format("%stest-03.pdf", TARGET);

同时引入ConverterProperties 属性，用于添加Baseuri属性

package com.ctbri.test;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;

import com.itextpdf.html2pdf.ConverterProperties;
import com.itextpdf.html2pdf.HtmlConverter;

public class C01E02_HelloWorld {

	public static final String BASEURI = "src/main/resources/html/";
	public static final String HTML = "
Test
Hello World
";
	public static final String TARGET = "target/results/ch01/";
	public static final String DEST = String.format("%stest-02.pdf", TARGET);
	
    public static void main(String[] args) throws IOException {
        File file = new File(TARGET);
        file.mkdirs();
        new C01E02_HelloWorld().createPdf(BASEURI, HTML, DEST);
    }
    
    /**
     * Creates the PDF file.
     */
    public void createPdf(String baseUri, String html, String dest) throws IOException {
    	ConverterProperties properties = new ConverterProperties();
    	properties.setBaseUri(baseUri);
        HtmlConverter.convertToPdf(html, new FileOutputStream(dest), properties);
    }
}

3、html和pdf都用File对象表示

package com.ctbri.test;

import java.io.File;
import java.io.IOException;

import com.itextpdf.html2pdf.HtmlConverter;

/**
 * Converts a simple HTML file to PDF using File objects
 */
public class C01E03_HelloWorld {

	public static final String BASEURI = "src/main/resources/html/";
	public static final String SRC = String.format("%shello.html", BASEURI);
	public static final String TARGET = "target/results/ch01/";
	public static final String DEST = String.format("%stest-03.pdf", TARGET);
	
    public static void main(String[] args) throws IOException {
        File file = new File(TARGET);
        file.mkdirs();
        new C01E03_HelloWorld().createPdf(BASEURI, SRC, DEST);
    }

    /**
     * Creates the PDF file.
     * @param baseUri the base URI
     * @param src the path to the source HTML file
     * @param dest the path to the resulting PDF
     */
    public void createPdf(String baseUri, String src, String dest) throws IOException {
        HtmlConverter.convertToPdf(new File(src), new File(dest));
    }
}

4、html和pdf都用FileInputStream对象表示

package com.ctbri.test;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;

import com.itextpdf.html2pdf.ConverterProperties;
import com.itextpdf.html2pdf.HtmlConverter;

/**
 * Converts a simple HTML file to PDF using an InputStream and an OutputStream
 */
public class C01E04_HelloWorld {

	public static final String BASEURI = "src/main/resources/html/";
	public static final String SRC = String.format("%shello.html", BASEURI);
	public static final String TARGET = "target/results/ch01/";
	public static final String DEST = String.format("%stest-04.pdf", TARGET);
	
	/**
	 * The main method of this example.
	 */
    public static void main(String[] args) throws IOException {
        File file = new File(TARGET);
        file.mkdirs();
        new C01E04_HelloWorld().createPdf(BASEURI, SRC, DEST);
    }

    /**
     * Creates the PDF file.
     */
    public void createPdf(String baseUri, String src, String dest) throws IOException {
    	ConverterProperties properties = new ConverterProperties();
    	properties.setBaseUri(baseUri);
        HtmlConverter.convertToPdf(new FileInputStream(src), new FileOutputStream(dest), properties);
    }
}

5、html用FileInputStream、pdf用PDfWriter

利用pdfWriter代替outputStream ，前者可以更好的配合我们设置输出文件的属性。

package com.ctbri.test;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import com.itextpdf.html2pdf.ConverterProperties;
import com.itextpdf.html2pdf.HtmlConverter;
import com.itextpdf.kernel.pdf.PdfWriter;
import com.itextpdf.kernel.pdf.WriterProperties;

/**
 * Converts a simple HTML file to PDF using an InputStream and a PdfWriter
 */
public class C01E05_HelloWorld {

	public static final String BASEURI = "src/main/resources/html/";
	public static final String SRC = String.format("%shello.html", BASEURI);
	public static final String TARGET = "target/results/ch01/";
	public static final String DEST = String.format("%stest-05.pdf", TARGET);
	
    public static void main(String[] args) throws IOException {
        File file = new File(TARGET);
        file.mkdirs();
        new C01E05_HelloWorld().createPdf(BASEURI, SRC, DEST);
    }

    /**
     * Creates the PDF file. output using PdfWriter
     */
    public void createPdf(String baseUri, String src, String dest) throws IOException { 
    	ConverterProperties properties = new ConverterProperties();
    	properties.setBaseUri(baseUri);
    	PdfWriter writer = new PdfWriter(dest, new WriterProperties().setFullCompressionMode(true));
        HtmlConverter.convertToPdf(new FileInputStream(src), writer, properties);
    }
}

6、html用FileInputStream、pdf用PDfDocument

这一层和上一层不同之处在于，输出的时候用一层pdfDocument包裹在pdfWriter外面。

并且引入了pdf.setTagged() 方便我们加入侧边的语义结构。

package com.ctbri.test;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import com.itextpdf.html2pdf.ConverterProperties;
import com.itextpdf.html2pdf.HtmlConverter;
import com.itextpdf.kernel.pdf.PdfDocument;
import com.itextpdf.kernel.pdf.PdfWriter;

/**
 * Converts a simple HTML file to PDF using an InputStream and a PdfDocument
 */
public class C01E06_HelloWorld {

	public static final String BASEURI = "src/main/resources/html/";
	public static final String SRC = String.format("%shello.html", BASEURI);
	public static final String TARGET = "target/results/ch01/";
	public static final String DEST = String.format("%stest-06.pdf", TARGET);
	
    public static void main(String[] args) throws IOException {
        File file = new File(TARGET);
        file.mkdirs();
        new C01E06_HelloWorld().createPdf(BASEURI, SRC, DEST);
    }

    /**
     * Creates the PDF file.
     */
    public void createPdf(String baseUri, String src, String dest) throws IOException { 
    	ConverterProperties properties = new ConverterProperties();
    	properties.setBaseUri(baseUri);
    	PdfWriter writer = new PdfWriter(dest);
    	PdfDocument pdf = new PdfDocument(writer);
    	pdf.setTagged();		//用于增加目录
        HtmlConverter.convertToPdf(new FileInputStream(src), pdf, properties);
    }
}

总结：上面介绍了6中基础的将html转为pdf文件的方式，总体没有什么区别，都是对不同源文件或者输出文件处理的几种方式。

包括：File、OutputStream、pdfWriter、pdfDocument，基本上都能实现目地，只是对于不同的输出方式采用不同的方式。