java 生成pdf

参考：https://www.showdoc.cc/243234797494858?page_id=1390154181784190

 

引入jar包

D:\Workspaces\MyEclipse 2017 CI\ZXJY\WebRoot\WEB-INF\lib\itext-asian-5.2.0.jar
D:\Workspaces\MyEclipse 2017 CI\ZXJY\WebRoot\WEB-INF\lib\itextpdf-5.5.1.jar

D:\Workspaces\MyEclipse 2017 CI\ZXJY\WebRoot\WEB-INF\lib\xmlworker-5.5.4.jar

java实现类

package com.pro.utils;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;

import javax.servlet.ServletOutputStream;
import javax.servlet.WriteListener;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
import javax.servlet.http.HttpServletResponseWrapper;

import org.jsoup.Jsoup;

import com.itextpdf.text.BaseColor;
import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Font;
import com.itextpdf.text.PageSize;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.tool.xml.Pipeline;
import com.itextpdf.tool.xml.XMLWorker;
import com.itextpdf.tool.xml.XMLWorkerFontProvider;
import com.itextpdf.tool.xml.XMLWorkerHelper;
import com.itextpdf.tool.xml.exceptions.CssResolverException;
import com.itextpdf.tool.xml.html.CssAppliers;
import com.itextpdf.tool.xml.html.CssAppliersImpl;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
import com.itextpdf.tool.xml.pipeline.css.CSSResolver;
import com.itextpdf.tool.xml.pipeline.css.CssResolverPipeline;
import com.itextpdf.tool.xml.pipeline.end.PdfWriterPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;

public class CreatePdfDocumentUtil {
	
	/**
     * 根据URL提前blog的基本信息，返回结果
     * @param URL 例：http://localhost:8080/scm/scm/po/gather/pdftest/pdftesthtml3.html(能直接返回某个html的URL,
     *            我开始传url时候被struts1拦截了，应为get不到session的登录人信息,所以得到的是登录页面的html)
     * @return
     * @throws Exception
     */
    public static  String[] extractHtmlInfo(String URL) throws Exception {
        /*这里为什么用数组，是因为返回的时候不仅可以返回选择的html，
        	还有从document提取其他的信息单独存在数组里返回，然后利用iText在pdf里面组装数据，可以在网上查*/
        String[] info = new String[1];
        // 直接把URL解析成document,然后调用document.html()解析为html
        org.jsoup.nodes.Document doc = Jsoup.connect(URL).get();
        // 此doc.select是用来选择完整的html中某一部分这里为第一个div的css为entry的部分,所以你的html上要有div的class为entry哦
        org.jsoup.nodes.Element entry = doc.select("div.entry").first();
        info[0] = entry.html();
        return info;
    }
 
    /**
     * 直接通过得到html来取得想要的部分html
     * @param html
     * @return
     * @throws Exception
     */
    public static  String[] extractHtmlInfo2(String html) throws Exception {
        String[] info = new String[1];
        // 把html转换为document
        org.jsoup.nodes.Document doc = Jsoup.parse(html);
        // 此doc.select是用来选择完整的html中某一部分这里为第一个div的css为entry的部分,所以你的html上要有div的class为entry哦
        org.jsoup.nodes.Element entry = doc.select("div.entry").first();
        info[0] = entry.html();
        return info;
    }
 
    /**
     * 把String 转为 InputStream
     * @param content
     * @return
     */
    public static InputStream parse2Stream(String content) {
        try {
            ByteArrayInputStream stream = new ByteArrayInputStream(
                    content.getBytes("UTF-8"));
            return stream;
        } catch (Exception e) {
 
            return null;
        }
    }
 
 
    /**
     * 直接把网页内容转为PDF文件
     *
     * @param
     * @throws Exception
     */
    public static void parseURL2PDFFile(String pdfFile, String html) {
        try {
            BaseFont bfCN = BaseFont.createFont("STSongStd-Light", "UniGB-UCS2-H",
                    false);
            // 中文字体定义
//            Font chFont = new Font(bfCN, 14, Font.NORMAL, BaseColor.BLUE);
//            Font secFont = new Font(bfCN, 12, Font.NORMAL, new BaseColor(0, 204,
//                    255));
//            Font textFont = new Font(bfCN, 12, Font.NORMAL, BaseColor.BLACK);
 
            Document document = new Document(PageSize.A4);
            // 设置pdf的背景图片
//            Image image = Image.getInstance("D:/移动背景图片.jpg");
//            image.setAlignment(image.UNDERLYING);
//            image.setAbsolutePosition(0,0);
//            image.scaleAbsolute(595,842);
 
            PdfWriter pdfwriter = PdfWriter.getInstance(document,
                    new FileOutputStream(pdfFile));
            pdfwriter.setViewerPreferences(PdfWriter.HideToolbar);
            document.open();
//            document.add(image);
            //得到解析的html
            String[] blogInfo = extractHtmlInfo2(html);
	        /*html文件转换为pdf文档
	        AsianFontProvider()函数是用来解决XMLWorkerHelper.getInstance().parseXHtml()转pdf中文不显示问题*/
            XMLWorkerHelper.getInstance().parseXHtml(pdfwriter, document,parse2Stream(blogInfo[0]),null, new AsianFontProvider());
 
            document.close();
        } catch (Exception e) {
            e.printStackTrace();
        } 
    }
    
    /**
     * 此forward方法执行完毕之后不会输出内容到浏览器，而是把输出到字节流，最后以字符串的形式返回
     * @param request
     * @param response
     * @param src
     * @return
     */
    public static String forward(HttpServletRequest request, HttpServletResponse response, String src) {
        try{

            /*  ↓↓↓↓↓重新构造response，修改response中的输出流对象，使其输出到字节数组↓↓↓↓↓  */
            final ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
            final ServletOutputStream servletOuputStream = new ServletOutputStream() {
                @Override
                public void write(int b) throws IOException {
                    byteArrayOutputStream.write(b);
                }
                @Override
                public boolean isReady() {
                    return false;
                }
                @Override
                public void setWriteListener(WriteListener writeListener) {
                }
            };

            final PrintWriter printWriter = new PrintWriter(new OutputStreamWriter(byteArrayOutputStream, "UTF-8"));

            response = new HttpServletResponseWrapper(response) {
                public ServletOutputStream getOutputStream() {
                    return servletOuputStream;
                }
                public PrintWriter getWriter() {
                    return printWriter;
                }
            };
             /*  ↑↑↑↑↑↑重新构造response，修改response中的输出流对象，使其输出到字节数组↑↑↑↑↑↑ */

            //执行forward操作
            request.getRequestDispatcher(src).forward(request,response);

            //把字节流中的内容太转为字符串
            return new String(byteArrayOutputStream.toByteArray(),"utf-8");
        }
        catch (Exception e){
            throw new RuntimeException(e);
        }
    }
    
    
    /**
     * 把html转换成pdf，以字节数组的形式返回pdf文件
     * @param html
     * @return pdf字节数组
     * @throws IOException
     * @throws DocumentException
     * @throws CssResolverException
     */
    public static byte[] html2pdf(String html) throws IOException, DocumentException,CssResolverException {
        Document document = new Document(PageSize.A4);
        ByteArrayOutputStream os = new ByteArrayOutputStream();
        PdfWriter writer = PdfWriter.getInstance(document,os);
        document.open();
        XMLWorkerFontProvider fontProvider = new XMLWorkerFontProvider(){
            @Override
            public Font getFont(String fontname, String encoding, float size, int style) {
                return super.getFont(fontname == null ? "宋体" : fontname, encoding, size, style);
            }
        };
        fontProvider.addFontSubstitute("lowagie", "garamond");
        fontProvider.setUseUnicode(true);
        //使用我们的字体提供器，并将其设置为unicode字体样式
        CssAppliers cssAppliers = new CssAppliersImpl(fontProvider);
        HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
        htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
        CSSResolver cssResolver = XMLWorkerHelper.getInstance().getDefaultCssResolver(true);
        Pipeline<?> pipeline = new CssResolverPipeline(cssResolver,new HtmlPipeline(htmlContext, new PdfWriterPipeline(document,writer)));
        XMLWorker worker = new XMLWorker(pipeline, true);
        XMLParser p = new XMLParser(worker);
        p.parse(new InputStreamReader(new ByteArrayInputStream(html.getBytes("gbk"))));
        document.close();
        return os.toByteArray();
    }

}

关于使用XMLWorkerHelper.getInstance().parseXHtml生成PDF时中文不显示或乱码问题

解决参考https://blog.csdn.net/gahd3000/article/details/77448877