嘿,亲!知识可是无价之宝呢,但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下,绝对物超所值哦!如有下载和支付问题,请联系我们QQ(微信同号):813200300
本次赞助数额为: 2 元微信扫码支付:2 元
请留下您的邮箱,我们将在2小时内将文件发到您的邮箱
此程序主要利用PDFBOX提取PDF中文字及图片。C#解析PDF相关资料太少了,研究了好多天,现在放上来,希望朋友们少走些弯路。适用于未加密的PDF。
以下是获取的文字截图:
using System;
using System.Collections.Generic;
using System.Text;
//
using org.pdfbox.pdmodel;
using org.pdfbox.util;
using org.pdfbox.cos;
using org.pdfbox.pdmodel.graphics.xobject;
using org.pdfbox.pdmodel.interactive.documentnavigation.outline;
namespace PDFParser
{
public class PDFParser
{
/// <summary>
/// 解析PDF,获取PDF文字
/// </summary>
/// <param name="file_path_name">PDF文件路径</param>
public static string GetText(string file_path_name)
{
PDDocument doc = PDDocument.load(file_path_name);
PDFTextStripper stripper = new PDFTextStripper();
return stripper.getText(doc);
}
/// <summary>
/// 解析PDF,获取PDF文字
/// </summary>
/// <param name="file_path_name">PDF文件路径</param>
/// <param name="startPage">起始页,从第1页开始</param>
/// <param name="endPageValue">结束页</param>
public static string GetText(string file_path_name,int startPageValue,int endPageValue)
{
PDDocument doc = PDDocument.load(file_path_name);
PDFTextStripper stripper = new PDFTextStripper();
// 设置是否排序
stripper.setSortByPosition(true);
stripper.setStartPage(startPageValue);
stripper.setEndPage(endPageValue);
return stripper.getText(doc);
}
/// <summary>
/// 解析PDF,当pdf是由图片构成时,导出每张图片
/// </summary>
/// <param name="file_path_name">PDF文件路径</param>
/// <param name="outFilePath">输出图片路径</param>
public static void GetImage(string file_path_name,string outFilePath)
{
// 内存中存储的PDF Document
PDDocument document = null;
try
{
// 装载文件
document = PDDocument.load(file_path_name);
PDDocumentCatalog cata = document.getDocumentCatalog();
//
COSDictionary cosDictionary = cata.getCOSDictionary();
// 得到所有页面的List
java.util.List pages = cata.getAllPages();
// 用来记录每个页面的图片名
int count = 1;
// 遍历每一页
for (int i = 0; i < pages.size(); i )
{
PDPage page = (PDPage)pages.get(i);
if (null != page)
{
// 得到每个页面资源
PDResources res = page.findResources();
// 获取页面图片信息
java.util.Map imgs = res.getImages();
if (null != imgs)
{
java.util.Set keySet = imgs.keySet();
java.util.Iterator it = keySet.iterator();
while (it.hasNext())
{
Object obj = it.next();
PDXObjectImage img = (PDXObjectImage)imgs.get(obj);
// 保存图片
img.write2file(outFilePath "page" (i 1) "_image" count);
count ;
}
}
}
}
}
catch (Exception e)
{
throw e;
}
finally
{
if (null != document)
document.close();
}
}
/// <summary>
/// 解析PDF,得到pdf的元数据
/// </summary>
/// <param name="file_path_name">PDF文件路径</param>
public static PDDocumentInformation GetMetadata(string file_path_name)
{
//导入pdf文档
PDDocument document = PDDocument.load(file_path_name);
PDDocumentInformation info = document.getDocumentInformation();
document.close();
return info;
}
/// <summary>
/// 解析PDF,得到一二级目录书签结构
/// </summary>
/// <param name="file_path_name">PDF文件路径</param>
private static void GetAllCata(string file_path_name)
{
// 内存中存储的PDF Document
PDDocument document = null;
try
{
document = PDDocument.load(file_path_name);
// 获得该pdf的目录对象
PDDocumentOutline root = document.getDocumentCatalog().getDocumentOutline();
if (root != null)
{
// 一级目录
PDOutlineItem item = root.getFirstChild();
while (item != null)
{
Console.WriteLine("Item:" item.getTitle());
// 二级目录
PDOutlineItem child = item.getFirstChild();
while (child != null)
{
Console.WriteLine(" Child:" child.getTitle());
// 下一个二级目录
child = child.getNextSibling();
}
// 下一个一级目录
item = item.getNextSibling();
}
}
}
catch (Exception e)
{
Console.WriteLine(e.ToString());
}
finally
{
if (null != document)
document.close();
}
}
/// <summary>
/// 解析PDF,得到pdf的元数据
/// </summary>
/// <param name="file_path_name">PDF文件路径</param>
private static PDDocumentInformation GetMetadata2(string file_path_name)
{
//导入pdf文档
PDDocument document = null;
PDDocumentInformation info = null;
try
{
document = PDDocument.load(file_path_name);
info = document.getDocumentInformation();
// 输出总页数
Console.WriteLine("总页数=" document.getNumberOfPages());
// 输出该文档标题
Console.WriteLine("文档标题Title=" info.getTitle());
// 输出该文档作者
Console.WriteLine("文档作者Author=" info.getAuthor());
// 输出该文档主题
Console.WriteLine("文档主题Subject=" info.getSubject());
// 输出该文档关键字
Console.WriteLine("文档关键字Keywords=" info.getKeywords());
// 输出该文档创建者
Console.WriteLine("文档创建者Creator=" info.getCreator());
// 输出该文档制作者
Console.WriteLine("文档制作者Producer=" info.getProducer());
// 输出该文档创建日期
Console.WriteLine("文档创建日期Creation Date=" info.getCreationDate());
// 输出该文档修改日期
Console.WriteLine("文档修改日期Modification Date=" info.getModificationDate());
// 输出该文档
Console.WriteLine("输出该文档Trapped=" info.getTrapped());
}
catch (Exception e)
{
Console.WriteLine(e.ToString());
}
finally
{
if (null != document)
document.close();
}
return info;
}
}
}