任务2回答--廖旺

任务2

需求：实现静态html转PDF的功能模块

1. 支持多种纸张尺寸，例如：A3，A4，8K
   2. 纵向或横向排版
   3. 中文多字体支持

答案要求：

1. 排版相关参数的设定
2. html 转PDF第三方功能模块的选用
3. 或者有其它的解决方案

---

---

使用itextpdf+jsoup将html文件进行标准化处理后转pdf

排版相关参数设置如下：

 设置纸张大小和页边距

 

 设置字体为itext字体库中的宋体，大小为原size*10

代码如下：

package com.liaowang.topdf;

import com.itextpdf.text.*;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.text.pdf.PdfName;
import com.itextpdf.text.pdf.PdfWriter;
import com.itextpdf.text.pdf.codec.Base64;
import com.itextpdf.tool.xml.XMLWorker;
import com.itextpdf.tool.xml.XMLWorkerFontProvider;
import com.itextpdf.tool.xml.css.StyleAttrCSSResolver;
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.AbstractImageProvider;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;
import com.liaowang.topdf.com.liaowang.topdf.controller.api.PdfReportM1HeaderFooter;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Entities;
import org.jsoup.select.Elements;
import org.junit.jupiter.api.Test;
import org.springframework.boot.test.context.SpringBootTest;

import java.io.*;
@SpringBootTest
public class TopdfApplicationTests {

    @Test
    public void writeToPdf() throws Exception {
//        new Test().hellowPdf();
        //读取html文件
        String htmlStr = readHtmlFile();
        //将html文件转成PDF
        writeToOutputStreamAsPDF(htmlStr);
    }


//    ----------------------将html生成pdf---------------------------------
    /**
     * 创建PDF文件
     * @param htmlStr
     * @throws Exception
     */
    private static void writeToOutputStreamAsPDF(String htmlStr) throws Exception {
        String targetFile = "pdfDemo1.pdf";
        File targeFile = new File(targetFile);
        if(targeFile.exists()) {
            targeFile.delete();
        }

        //定义pdf文件尺寸，采用A4横切
        Document document = new Document(PageSize.A4,
                25, 25, 15, 40);// 左、右、上、下间距
        //定义输出路径
        PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream(targetFile));
        PdfReportM1HeaderFooter header = new PdfReportM1HeaderFooter("", 8, PageSize.A4);
        writer.setPageEvent(header);
        writer.addViewerPreference(PdfName.PRINTSCALING, PdfName.NONE);
        document.open();

        // CSS
        CSSResolver cssResolver = new StyleAttrCSSResolver();
        CssAppliers cssAppliers = new CssAppliersImpl(new XMLWorkerFontProvider(){

            @Override
            public Font getFont(String fontname, String encoding, boolean embedded, float size, int style, BaseColor color) {
                try {
                    //用于中文显示的Provider
                    BaseFont bfChinese = BaseFont.createFont(
                            "STSongStd-Light", "UniGB-UCS2-H", BaseFont.NOT_EMBEDDED);
                    return new Font(bfChinese, size*10, style);
                } catch (Exception e) {
                    return super.getFont(fontname, encoding, size, style);
                }
            }
        });

        //html
        HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
        htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
        htmlContext.setImageProvider(new AbstractImageProvider() {
            @Override
            public Image retrieve(String src) {
                //支持图片显示
                int pos = src.indexOf("base64,");
                try {
                    if (src.startsWith("data") && pos > 0) {
                        byte[] img = Base64.decode(src.substring(pos + 7));
                        return Image.getInstance(img);
                    } else if (src.startsWith("http")) {
                        return Image.getInstance(src);
                    }
                } catch (BadElementException ex) {
                    return null;
                } catch (IOException ex) {
                    return null;
                }
                return null;
            }

            @Override
            public String getImageRootPath() {
                return null;
            }
        });


        // Pipelines
        PdfWriterPipeline pdf = new PdfWriterPipeline(document, writer);
        HtmlPipeline html = new HtmlPipeline(htmlContext, pdf);
        CssResolverPipeline css = new CssResolverPipeline(cssResolver, html);

        // XML Worker
        XMLWorker worker = new XMLWorker(css, true);
        XMLParser p = new XMLParser(worker);
        p.parse(new ByteArrayInputStream(htmlStr.getBytes()));

        document.close();
    }

    /**
     * 读取 HTML 文件
     * @return
     */
    private static String readHtmlFile() {
        StringBuffer textHtml = new StringBuffer();
        try {
            File file = new File("D:\\maven-workspace\\gulimall\\topdf\\src\\main\\resources\\static\\demo.html");
            BufferedReader reader = new BufferedReader(new FileReader(file));
            String tempString = null;
            // 一次读入一行，直到读入null为文件结束
            while ((tempString = reader.readLine()) != null) {
                textHtml.append(tempString);
            }
            reader.close();
        } catch (IOException e) {
            System.out.println("e"+e.toString());
            return null;
        }
        String s = textHtml.toString();

        // 使用jsoup工具对html文件进行标准化处理
        org.jsoup.nodes.Document doc = Jsoup.parse(s);
        // 去除过大的宽度
        String style = doc.attr("style");
        if ((!style.isEmpty()) && style.contains("width")) {
            doc.attr("style", "");
        }
        Elements divs = doc.select("div");
        for (org.jsoup.nodes.Element div : divs) {
            String divStyle = div.attr("style");
            if ((!divStyle.isEmpty()) && divStyle.contains("width")) {
                div.attr("style", "");
            }
        }
        // jsoup生成闭合标签
        doc.outputSettings().syntax(org.jsoup.nodes.Document.OutputSettings.Syntax.xml);
        doc.outputSettings().escapeMode(Entities.EscapeMode.xhtml);
        return doc.html();

    }
}

package com.liaowang.topdf.com.liaowang.topdf.controller.api;


import java.io.IOException;

import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Element;
import com.itextpdf.text.Font;
import com.itextpdf.text.PageSize;
import com.itextpdf.text.Phrase;
import com.itextpdf.text.Rectangle;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.text.pdf.ColumnText;
import com.itextpdf.text.pdf.PdfContentByte;
import com.itextpdf.text.pdf.PdfPageEventHelper;
import com.itextpdf.text.pdf.PdfTemplate;
import com.itextpdf.text.pdf.PdfWriter;

/
public class PdfReportM1HeaderFooter extends PdfPageEventHelper {

    /**
     * 页眉
     */
    public String header = "";

    /**
     * 文档字体大小，页脚页眉最好和文本大小一致
     */
    public int presentFontSize = 12;

    /**
     * 文档页面大小，最好前面传入，否则默认为A4纸张
     */
    public Rectangle pageSize = PageSize.A4;

    // 模板
    public PdfTemplate total;

    // 基础字体对象
    public BaseFont bf = null;

    // 利用基础字体生成的字体对象，一般用于生成中文文字
    public Font fontDetail = null;

    /**
     *
     * Creates a new instance of PdfReportM1HeaderFooter 无参构造方法.
     *
     */
    public PdfReportM1HeaderFooter() {

    }

    /**
     *
     * Creates a new instance of PdfReportM1HeaderFooter 构造方法.
     *
     * @param yeMei
     *            页眉字符串
     * @param presentFontSize
     *            数据体字体大小
     * @param pageSize
     *            页面文档大小，A4，A5，A6横转翻转等Rectangle对象
     */
    public PdfReportM1HeaderFooter(String yeMei, int presentFontSize, Rectangle pageSize) {
        this.header = yeMei;
        this.presentFontSize = presentFontSize;
        this.pageSize = pageSize;
    }

    public void setHeader(String header) {
        this.header = header;
    }

    public void setPresentFontSize(int presentFontSize) {
        this.presentFontSize = presentFontSize;
    }

    /**
     *
     * TODO 文档打开时创建模板
     *
     * @see com.itextpdf.text.pdf.PdfPageEventHelper#onOpenDocument(com.itextpdf.text.pdf.PdfWriter, com.itextpdf.text.Document)
     */
    public void onOpenDocument(PdfWriter writer, Document document) {
        total = writer.getDirectContent().createTemplate(50, 50);// 共 页 的矩形的长宽高
    }

    /**
     *
     * TODO 关闭每页的时候，写入页眉，写入'第几页共'这几个字。
     *
     * @see com.itextpdf.text.pdf.PdfPageEventHelper#onEndPage(com.itextpdf.text.pdf.PdfWriter, com.itextpdf.text.Document)
     */
    public void onEndPage(PdfWriter writer, Document document) {

        try {
            if (bf == null) {
                bf = BaseFont.createFont("STSong-Light", "UniGB-UCS2-H", false);
            }
            if (fontDetail == null) {
                fontDetail = new Font(bf, presentFontSize, Font.NORMAL);// 数据体字体
            }
        } catch (DocumentException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }

        // 1.写入页眉
        ColumnText.showTextAligned(writer.getDirectContent(), Element.ALIGN_LEFT, new Phrase(header, fontDetail), document.left(), document.top() + 20, 0);

        // 2.写入前半部分的 第 X页/共
        int pageS = writer.getPageNumber();
        String foot1 = "第 " + pageS + " 页 /共";
        Phrase footer = new Phrase(foot1, fontDetail);

        // 3.计算前半部分的foot1的长度，后面好定位最后一部分的'Y页'这俩字的x轴坐标，字体长度也要计算进去 = len
        float len = bf.getWidthPoint(foot1, presentFontSize);

        // 4.拿到当前的PdfContentByte
        PdfContentByte cb = writer.getDirectContent();

        //自己增加的
        if(pageS==1){
            Phrase footerLeft = new Phrase("978-1-4799-0530-031.00 ©2013 IEEE", fontDetail);
            ColumnText.showTextAligned(cb, Element.ALIGN_LEFT, footerLeft, document.left(), document.bottom() - 20, 0);
        }

        // 5.写入页脚1，x轴就是(右margin+左margin + right() -left()- len)/2.0F 再给偏移20F适合人类视觉感受，否则肉眼看上去就太偏左了 ,y轴就是底边界-20,否则就贴边重叠到数据体里了就不是页脚了；注意Y轴是从下往上累加的，最上方的Top值是大于Bottom好几百开外的。
        ColumnText.showTextAligned(cb, Element.ALIGN_CENTER, footer, (document.rightMargin() + document.right() + document.leftMargin() - document.left() - len) / 2.0F + 20F, document.bottom() - 20, 0);

        // 6.写入页脚2的模板（就是页脚的Y页这俩字）添加到文档中，计算模板的和Y轴,X=(右边界-左边界 - 前半部分的len值)/2.0F + len ， y 轴和之前的保持一致，底边界-20
        cb.addTemplate(total, (document.rightMargin() + document.right() + document.leftMargin() - document.left()) / 2.0F + 20F, document.bottom() - 20); // 调节模版显示的位置

    }

    /**
     *
     * TODO 关闭文档时，替换模板，完成整个页眉页脚组件
     *
     * @see com.itextpdf.text.pdf.PdfPageEventHelper#onCloseDocument(com.itextpdf.text.pdf.PdfWriter, com.itextpdf.text.Document)
     */
    public void onCloseDocument(PdfWriter writer, Document document) {
        // 7.最后一步了，就是关闭文档的时候，将模板替换成实际的 Y 值,至此，page x of y 制作完毕，完美兼容各种文档size。
        total.beginText();
        total.setFontAndSize(bf, presentFontSize);// 生成的模版的字体、颜色
        String foot2 = " " + (writer.getPageNumber() - 1) + " 页";
        total.showText(foot2);// 模版显示的内容
        total.endText();
        total.closePath();
    }
}

 <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
        <!--        html转pdf-->
        <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>itextpdf</artifactId>
            <version>5.5.11</version>
        </dependency>
        <dependency>
            <groupId>com.itextpdf.tool</groupId>
            <artifactId>xmlworker</artifactId>
            <version>5.5.11</version>
        </dependency>
        <!-- 支持中文 -->
        <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>itext-asian</artifactId>
            <version>5.2.0</version>
        </dependency>
        <!-- 支持css样式渲染 -->
        <dependency>
            <groupId>org.xhtmlrenderer</groupId>
            <artifactId>flying-saucer-pdf-itext5</artifactId>
            <version>9.1.16</version>
        </dependency>
        <!-- 转换html为标准xhtml包 -->
        <dependency>
            <groupId>net.sf.jtidy</groupId>
            <artifactId>jtidy</artifactId>
            <version>r938</version>
        </dependency>
        
        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.15.3</version>
        </dependency>

    </dependencies>