html 转换成pdf

最新推荐文章于 2023-07-12 09:36:11 发布

iteye_20151

最新推荐文章于 2023-07-12 09:36:11 发布

阅读量382

点赞数

分类专栏： java笔记文章标签： htmltopdf

本文链接：https://blog.csdn.net/iteye_20151/article/details/82564574

版权

java笔记专栏收录该内容

26 篇文章 0 订阅

订阅专栏

[size=medium][b][color=blue]解决需求：[/color][/b][/size]

[b]1.字符串html代码转换成pdf文件[/b]
[b]2.根据FreeMarker模板动态生成静态html文件[/b]
[b]3.把静态html文件装换成pdf文件
4.解决html编写不够严谨规范的问题，自动转换为符合规范的格式
5.支持中文及换行
6.pdf文件打水印 - （html文件设置背景图片即可）
7.使用用户根据自己的需求改写jar包中的代码添加页眉页脚，及当前第几页[/b]

[b][color=red][size=medium]注意：[/size][/color][/b]

[b]使用jar包的版本，特定的jar包是经过改写而实现支持中文及换行问题，附件中给出的就是一组特定版本的jar包，能够解决以上需求[/b]

[color=blue]还是有点毛病：[/color]
加粗不管用，css样式和B标签都不管用这。。

[color=blue]
参考了很多网上的文章：[/color]
[url]http://swordshadow.iteye.com/blog/1983935#comments[/url]等等。。。

[color=blue]先来个效果图：[/color]
[img]http://dl.iteye.com/upload/picture/pic/132197/00de7503-80c3-30b6-8ffc-c2809a634b74.jpg[/img]

[b][color=red]1.得到html的文本内容[/color][/b]


import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
/**
 * <ul>
 * <li>功能描述: 工具类 得到html内容</li>
 * </ul>
 * @author gjw
 */
public class GetHtmlContent{
    /**
     * <ul>
     * <li>功能描述: 得到html内容</li>
     * </ul>
     * @param ******
     * @param ******
     * @return ******
     * @author gjw
     */
    public static String getHtmlContent(String tender_id,String invest_id)
    {
        try
        {
            String path = "./upload/44/445/"+tender_id+"/"+invest_id;
            File f = new File(path+"/ceshi.html");
            if (f.exists())
            {
                FileInputStream ism = new FileInputStream(f);
                InputStreamReader isr = new InputStreamReader(ism,"utf-8");
                BufferedReader bs = new BufferedReader(isr);
                String info;
                info = bs.readLine();
                String content = "";
                while(info!=null){
                    content+=info;
                    info =   bs.readLine();
                }
                return content;
            }
            return null;
        } catch (IOException e)
        {
            e.printStackTrace();
            return null;
        }
    }
}

[b][color=red]2.String类型的html转换成pdf[/color][/b]


import java.io.ByteArrayOutputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.SQLException;

import javax.xml.parsers.ParserConfigurationException;

import org.htmlcleaner.CleanerProperties;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.PrettyXmlSerializer;
import org.htmlcleaner.TagNode;
import org.xhtmlrenderer.pdf.ITextFontResolver;
import org.xhtmlrenderer.pdf.ITextRenderer;
import org.xml.sax.SAXException;

import LuceneDAO.BaseDAO;

import com.lowagie.text.DocumentException;
import com.lowagie.text.pdf.BaseFont;


public class PdfRenderer {
 public static void main(String[] args) throws IOException, DocumentException, ParserConfigurationException, SAXException {

     // Create a buffer to hold the cleaned up HTML 将不严格的html编写方式转为严谨的html编码方式
     ByteArrayOutputStream out = new ByteArrayOutputStream();

     // Clean up the HTML to be well formed
     HtmlCleaner cleaner = new HtmlCleaner();
     CleanerProperties props = cleaner.getProperties();

     TagNode node = cleaner.clean(getcontext());
     // Instead of writing to System.out we now write to the ByteArray buffer
     new PrettyXmlSerializer(props).writeXmlToStream(node, out);

     // Create the PDF
     ITextRenderer renderer = new ITextRenderer();
     renderer.setDocumentFromString(new String(out.toByteArray()));
     //BaseFont fontResolver = renderer.getFontResolver();
     ITextFontResolver fontResolver = renderer.getFontResolver(); 
     //解决中文不显示问题
     fontResolver.addFont("C:/Windows/Fonts/arialuni.ttf", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);  
     //设置资源路径 如图片样式文件
     //renderer.getSharedContext().setBaseURL("C:\\htmltopdf\\");
     renderer.layout();
     OutputStream outputStream = new FileOutputStream(".\\towork\\HTMLasPDF.pdf");
     renderer.createPDF(outputStream);

     // Finishing up
     renderer.finishPDF();
     out.flush();
     out.close();
 }
 public static String getcontext()
 {
      Connection con = null;
      PreparedStatement ps = null;
      ResultSet rs = null;
      String sql = "select * from post where fileid = 1";
      BaseDAO baseDao = null;
      try{
          baseDao = new BaseDAO();
          con = baseDao.getConnection();
          ps = con.prepareStatement(sql);
          rs = ps.executeQuery();
          while(rs.next()){
              return rs.getString("fdesc").toString();
          }
      }catch(Exception e){
          e.printStackTrace();
      }finally{
          try
         {
             ps.close();
         } catch (SQLException e)
         {
             e.printStackTrace();
         }
          try
         {
             rs.close();
         } catch (SQLException e)
         {
             e.printStackTrace();
         }
          try
         {
             con.close();
         } catch (SQLException e)
         {
             e.printStackTrace();
         }
      }
      return"";
 }
}

连接数据库类文件


import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.SQLException;

public class BaseDAO {
	// 必须参数
	public static final String DRIVER = "com.mysql.jdbc.Driver"; // 驱动名称
	public static final String URL = "jdbc:mysql://localhost:3306/lucene"; // 数据库地址
	public static final String DBNAME = "root"; // 用户名
	public static final String PASSWORD = "tiger"; // 密码

	/**
	 * 获取数据库连接
	 * 
	 * @return con
	 * @throws ClassNotFoundException
	 * @throws SQLException
	 */
	public Connection getConnection() throws ClassNotFoundException,
			SQLException {
		Class.forName(DRIVER);
		Connection con = DriverManager.getConnection(URL, DBNAME, PASSWORD);
		return con;
	}

}

[b][color=red]3.html静态文件生成pdf[/color][/b]


import java.io.ByteArrayOutputStream;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;

import javax.xml.parsers.ParserConfigurationException;

import org.htmlcleaner.CleanerProperties;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.PrettyXmlSerializer;
import org.htmlcleaner.TagNode;
import org.xhtmlrenderer.pdf.ITextFontResolver;
import org.xhtmlrenderer.pdf.ITextRenderer;
import org.xml.sax.SAXException;

import com.lowagie.text.DocumentException;
import com.lowagie.text.pdf.BaseFont;


public class PdfRenderer {
 public static void main(String[] args) throws IOException, DocumentException, ParserConfigurationException, SAXException {

     // Create a buffer to hold the cleaned up HTML将不严格的html编写方式转为严谨的html编码方式
     ByteArrayOutputStream out = new ByteArrayOutputStream();

     // Clean up the HTML to be well formed
     HtmlCleaner cleaner = new HtmlCleaner();
     CleanerProperties props = cleaner.getProperties();
     InputStream inputStream = new FileInputStream(".\\towork\\user.html");

     TagNode node = cleaner.clean(inputStream, "utf-8");
     // Instead of writing to System.out we now write to the ByteArray buffer
     new PrettyXmlSerializer(props).writeXmlToStream(node, out);

     // Create the PDF
     ITextRenderer renderer = new ITextRenderer();
     renderer.setDocumentFromString(new String(out.toByteArray()));

     ITextFontResolver fontResolver = renderer.getFontResolver(); 
     fontResolver.addFont("C:/Windows/Fonts/arialuni.ttf", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);  

     renderer.layout();
     OutputStream outputStream = new FileOutputStream(".\\towork\\HTMLasPDF.pdf");
     renderer.createPDF(outputStream);

     // Finishing up
     renderer.finishPDF();
     out.flush();
     out.close();
 }
}

[b][color=red]4.利用freemark生成静态的html文件[/color][/b]


//工具类
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.Map;

import freemarker.template.Configuration;
import freemarker.template.DefaultObjectWrapper;
import freemarker.template.Template;
import freemarker.template.TemplateException;
/**
 * 生成 静态html文件的方法
 * */
public class FreeMarkerUtil{
//templatePath模板文件存放路径
//templateName 模板文件名称
//filename 生成的文件名称
public static void analysisTemplate(String templatePath,String templateName,String fileName,Map<?,?>root){
try {
   Configuration config=new Configuration();
  //设置要解析的模板所在的目录，并加载模板文件
  config.setDirectoryForTemplateLoading(new File(templatePath));
   //设置包装器，并将对象包装为数据模型
   config.setObjectWrapper(new DefaultObjectWrapper());

   //获取模板,并设置编码方式，这个编码必须要与页面中的编码格式一致
   //否则会出现乱码
   Template template=config.getTemplate(templateName,"UTF-8");
   //合并数据模型与模板
   FileOutputStream fos = new FileOutputStream(fileName);
   Writer out = new OutputStreamWriter(fos,"UTF-8");
      template.process(root, out);
      out.flush();
      out.close();
  } catch (IOException e) {
   e.printStackTrace();
  }catch (TemplateException e) {
   e.printStackTrace();
  }
 }
}


//测试类
import java.util.HashMap;
import java.util.Map;

import com.seening.utils.SWResultList;
import com.sinocec.model.xrwd.SWAreaFactory;
/**
 * 测试ftl生成html文件
 * */
public class ClientTest{
    public static void main(String[] args){
        User user=new User();
        user.setUserName("李四");
        user.setUserPassword("123");

        Map<String,Object> root=new HashMap<String, Object>();
        root.put("user", user);;
        String templatesPath="./WEB-INF/templet";
        String templateFile="templet.ftl";
        String htmlFile="./upload/templet/commontemplet.html";
        FreeMarkerUtil.analysisTemplate(templatesPath,templateFile,htmlFile,root);
    }
}

core-renderer3.jar
htmlcleaner.jar
iText-2.0.8.jar
iTextAsian.jar
jtidy-r8-21122004.jar
mysql-connector-java-5.1.6-bin.jar

下面有测试项目
http://www.micmiu.com/opensource/expdoc/itext-xml-worker-cn/