本文是基于pdf文档转png图片,然后进行图片拼接，拼接后的图片转为base64字符串，然后拼接html文档写入html文件实现pdf文档转html文档。
引入maven依赖
<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
<dependency>
<groupid>org.apache.pdfbox</groupid>
<artifactid>pdfbox</artifactid>
<version>2.0.12</version>
</dependency>
工具实现类
package com.frame.utils;
import org.apache.pdfbox.pdmodel.pddocument;
import org.apache.pdfbox.rendering.pdfrenderer;
import org.slf4j.logger;
import org.slf4j.loggerfactory;
import sun.misc.base64decoder;
import sun.misc.base64encoder;
import javax.imageio.imageio;
import java.awt.*;
import java.awt.image.bufferedimage;
import java.io.*;
/**
* pdf文档转html文档
* @author lxw
* @date 2020/6/17 16:45
*/
public class pdfconverthtmlutil {
/**
* 日志对象
*/
private static logger logger = loggerfactory.getlogger(pdfconverthtmlutil.class);
/**
* pdf文档流转png
* @param pdffileinputstream
* @return bufferedimage
*/
public static bufferedimage pdfstreamtopng(inputstream pdffileinputstream){
pddocument doc = null;
pdfrenderer renderer = null;
try {
doc = pddocument.load(pdffileinputstream);
renderer = new pdfrenderer(doc);
int pagecount = doc.getnumberofpages();
bufferedimage image = null;
for (int i = 0; i < pagecount; i++) {
if (image != null) {
image = combinebufferedimages(image, renderer.renderimagewithdpi(i, 144));
}
if (i == 0) {
image = renderer.renderimagewithdpi(i, 144); // windows native dpi
}
// bufferedimage srcimage = resize(image, 240, 240);//产生缩略图
}
return combinebufferedimages(image);
} catch (ioexception e) {
e.printstacktrace();
}finally {
try {
if(doc != null){doc.close();}
} catch (ioexception e) {
e.printstacktrace();
}
}
return null;
}
/**
*bufferedimage拼接处理，添加分割线
* @param images
* @return bufferedimage
*/
public static bufferedimage combinebufferedimages(bufferedimage... images) {
int height = 0;
int width = 0;
for (bufferedimage image : images) {
//height += math.max(height, image.getheight());
height += image.getheight();
width = image.getwidth();
}
bufferedimage combo = new bufferedimage(width, height, bufferedimage.type_int_argb);
graphics2d g2 = combo.creategraphics();
int x = 0;
int y = 0;
for (bufferedimage image : images) {
//int y = (height - image.getheight()) / 2;
g2.setstroke(new basicstroke(2.0f));// 线条粗细
g2.setcolor(new color(193, 193, 193));// 线条颜色
g2.drawline(x, y, width, y);// 线条起点及终点位置
g2.drawimage(image, x, y, null);
//x += image.getwidth();
y += image.getheight();
}
return combo;
}
/**
* 通过base64创建html文件并输出html文件
* @param base64
* @param htmlpath html保存路径
*/
public static void createhtmlbybase64(string base64,string htmlpath) {
stringbuilder stringhtml = new stringbuilder();
printstream printstream = null;
try {
// 打开文件
printstream = new printstream(new fileoutputstream(htmlpath));
} catch (filenotfoundexception e) {
e.printstacktrace();
}
// 输入html文件内容
stringhtml.append("<html><head>");
stringhtml.append("<meta http-equiv=\"content-type\" content=\"text/html; charset=utf-8\">");
stringhtml.append("<title></title>");
stringhtml.append("</head>");
stringhtml.append(
"<body style=\"\r\n" + " text-align: center;\r\n" + " background-color: #c1c1c1;\r\n" + "\">");
stringhtml.append("<img src=\"data:image/png;base64," + base64 + "\" />");
stringhtml.append("<a name=\"head\" style=\"position:absolute;top:0px;\"></a>");
//添加锚点用于返回首页
stringhtml.append("<a style=\"position:fixed;bottom:10px;right:10px\" href=\"#head\">回到首页</a>");
stringhtml.append("</body></html>");
try {
// 将html文件内容写入文件中
printstream.println(stringhtml.tostring());
} catch (exception e) {
e.printstacktrace();
}finally {
if(printstream != null){printstream.close();}
}
}
/**
* bufferedimage 转为 base64编码
* @param bufferedimage
* @return
*/
public static string bufferedimagetobase64(bufferedimage bufferedimage) {
bytearrayoutputstream bytearrayoutputstream = new bytearrayoutputstream();
string png_base64 = "";
try {
imageio.write(bufferedimage, "png", bytearrayoutputstream);// 写入流中
byte[] bytes = bytearrayoutputstream.tobytearray();// 转换成字节
base64encoder encoder = new base64encoder();
// 转换成base64串 删除 \r\n
png_base64 = encoder.encodebuffer(bytes).trim()
.replaceall("\n", "")
.replaceall("\r", "");
} catch (ioexception e) {
e.printstacktrace();
}
return png_base64;
}
}
测试demo
public static void main(string[] args) {
file file = new file("f:\1\\files\\mysql查询语句大全集锦(经典珍藏).pdf");
string htmlpath = "f:\1\\files\\mysql查询语句大全集锦(经典珍藏).html";
inputstream inputstream = null;
bufferedimage bufferedimage = null;
try {
inputstream = new fileinputstream(file);
bufferedimage = pdfstreamtopng(inputstream);
string base64_png = bufferedimagetobase64(bufferedimage);
createhtmlbybase64(base64_png,htmlpath);
} catch (filenotfoundexception e) {
e.printstacktrace();
}finally {
try {
if(inputstream != null){inputstream.close();}
} catch (ioexception e) {
e.printstacktrace();
}
}
}
最终结果 转换后文件
转换后的文件内容
文件预览效果
到此这篇关于java实现pdf转html文档的示例代码的文章就介绍到这了,更多相关java pdf转html 内容请搜索www.887551.com以前的文章或继续浏览下面的相关文章希望大家以后多多支持www.887551.com！
黄山市民网：https://www.huangshanshimin.com/
