生成PDF文档我们通常可以通过文档转换的形式来得到想要的PDF,但我们也可以通过最直接的方式来创建PDF文档,由此本篇文章将介绍C#如何来创建带图、文元素的PDF文档。同理,对于需要读取PDF文档的情况,我们也可以分情况来读取想要的文档元素(文本、图片)。在下面的示例中将做详细介绍。

示例要点梳理:

一、创建PDF文档(可支持中文)
1.写入文本(包括页边距、字体、字号等设置)
2.绘入图片
二、读取PDF文档
1.读取文本
1.1读取全部文本
1.2读取指定区域文本
2.读取图片
使用工具:Free Spire.PDF for .NET4.3 (最新免费版)
注:在编辑代码前引用Spire.PDF.dll,dll文件可在安装路径下的Bin文件夹中获取。

一、创建PDF文档

C#

using Spire.Pdf;
using Spire.Pdf.Graphics;
using System.Drawing;

namespace CreatePDF_PDF
{
    class Program
    {
        static void Main(string[] args)
        {
            //初始化一个PdfDocument类实例
            PdfDocument document = new PdfDocument();

            //声明 PdfUnitConvertor和PdfMargins类对象
            PdfUnitConvertor unitCvtr = new PdfUnitConvertor();
            PdfMargins margins = new PdfMargins();

            //设置页边距
            margins.Top = unitCvtr.ConvertUnits(2.54f, PdfGraphicsUnit.Centimeter, PdfGraphicsUnit.Point);
            margins.Bottom = margins.Top;
            margins.Left = unitCvtr.ConvertUnits(3.17f, PdfGraphicsUnit.Centimeter, PdfGraphicsUnit.Point);
            margins.Right = margins.Left;

            //新添加一个A4大小的页面
            PdfPageBase page = document.Pages.Add(PdfPageSize.A4, margins);

            //自定义PdfTrueTypeFont、PdfPen实例,设置字体类型、字号和字体颜色
            PdfTrueTypeFont font = new PdfTrueTypeFont(new Font("楷体", 11f),true);
            PdfPen pen = new PdfPen(Color.Black);

            //调用DrawString()方法在指定位置写入文本
            string text = ("《蝶恋花 送春》 \n 楼外垂杨千万缕,欲系青春,少住春还去。犹自风前飘柳絮,随春且看归何处?\n 绿满山川闻杜宇,便作无情,莫也愁人苦。把酒送春春不语,黄昏却下潇潇雨。");
            page.Canvas.DrawString(text, font, pen, 15, 13);

            //加载图片,并调用DrawImage()方法在指定位置绘入图片
            PdfImage image = PdfImage.FromFile("image1.jpg");
            float width = image.Width * 0.55f;
            float height = image.Height * 0.55f;
            float y = (page.Canvas.ClientSize.Width - width) / 3;
            page.Canvas.DrawImage(image, y, 60, width, height);

            //保存并打开文档
            document.SaveToFile("PDF创建.pdf");
            System.Diagnostics.Process.Start("PDF创建.pdf");
        }
    }
}

创建结果:
C# /VB.NET 创建、读取PDF文档

VB.NET

Imports Spire.Pdf
Imports Spire.Pdf.Graphics
Imports System.Drawing

Namespace CreatePDF_PDF

    Class Program

        Private Shared Sub Main(ByVal args As String())
            Dim document As PdfDocument = New PdfDocument()
            Dim unitCvtr As PdfUnitConvertor = New PdfUnitConvertor()
            Dim margins As PdfMargins = New PdfMargins()
            margins.Top = unitCvtr.ConvertUnits(2.54F, PdfGraphicsUnit.Centimeter, PdfGraphicsUnit.Point)
            margins.Bottom = margins.Top
            margins.Left = unitCvtr.ConvertUnits(3.17F, PdfGraphicsUnit.Centimeter, PdfGraphicsUnit.Point)
            margins.Right = margins.Left
            Dim page As PdfPageBase = document.Pages.Add(PdfPageSize.A4, margins)
            Dim font As PdfTrueTypeFont = New PdfTrueTypeFont(New Font("楷体", 11F), True)
            Dim pen As PdfPen = New PdfPen(Color.Black)
            Dim text As String =("《蝶恋花 送春》 " & vbLf & " 楼外垂杨千万缕,欲系青春,少住春还去。犹自风前飘柳絮,随春且看归何处?" & vbLf & " 绿满山川闻杜宇,便作无情,莫也愁人苦。把酒送春春不语,黄昏却下潇潇雨。")
            page.Canvas.DrawString(text, font, pen, 15, 13)
            Dim image As PdfImage = PdfImage.FromFile("image1.jpg")
            Dim width As Single = image.Width * 0.55F
            Dim height As Single = image.Height * 0.55F
            Dim y As Single =(page.Canvas.ClientSize.Width - width) / 3
            page.Canvas.DrawImage(image, y, 60, width, height)
            document.SaveToFile("PDF创建.pdf")
            System.Diagnostics.Process.Start("PDF创建.pdf")
        End Sub
    End Class
End Namespace

这里创建PDF文档,Spire.PDF支持直接生成PDF文档并同时实现添加文本、图片、图形、水印、表格、页眉页脚、页码等操作,这里示例代码以添加文本、图片为例,有需要可以参见以下博客:


using Spire.Pdf;
using System;
using System.IO;
using System.Text;
namespace ExtractText_PDF
{
    class Program
    {
        static void Main(string[] args)
        {
            //实例化PdfDocument类对象,并加载PDF文档
            PdfDocument doc = new PdfDocument();
            doc.LoadFromFile("sample.pdf");

            //实例化一个StringBuilder 对象
            StringBuilder content = new StringBuilder();

            //遍历文档所有PDF页面,提取文本
            foreach (PdfPageBase page in doc.Pages)
            {
                content.Append(page.ExtractText());
            }

            //将提取到的文本写为.txt格式并保存到本地路径
            String fileName = "获取文本.txt";
            File.WriteAllText(fileName, content.ToString());
            System.Diagnostics.Process.Start("获取文本.txt");
        }
    }
}

读取结果:
C# /VB.NET 创建、读取PDF文档

VB.NET

Imports Spire.Pdf
Imports System
Imports System.IO
Imports System.Text

Namespace ExtractText_PDF

    Class Program

        Private Shared Sub Main(ByVal args As String())
            Dim doc As PdfDocument = New PdfDocument()
            doc.LoadFromFile("sample.pdf")
            Dim content As StringBuilder = New StringBuilder()
            For Each page As PdfPageBase In doc.Pages
                content.Append(page.ExtractText())
            Next

            Dim fileName As String = "获取文本.txt"
            File.WriteAllText(fileName, content.ToString())
            System.Diagnostics.Process.Start("获取文本.txt")
        End Sub
    End Class
End Namespace

1.2 读取指定区域文本

C#

using Spire.Pdf;
using System.IO;
using System.Text;
using System.Drawing;

namespace ExtractText1_PDF
{
    class Program
    {
        static void Main(string[] args)
        {
            //创建PdfDocument类实例,并加载PDF文档
            PdfDocument pdf = new PdfDocument(); 
            pdf.LoadFromFile("sample.pdf");

            //获取PDF第一页  
            PdfPageBase page = pdf.Pages[0];

            //从第一页的指定矩形区域内提取文本  
            string text = page.ExtractText(new RectangleF(50, 50, 500, 170));

            //保存文本到.txt文件,并打开文档
            StringBuilder sb = new StringBuilder();
            sb.AppendLine(text);
            File.WriteAllText("Extract.txt", sb.ToString());
            System.Diagnostics.Process.Start("Extract.txt");
        }
    }
}

读取结果:
(此时读取的就只是指定区域内的文本)
C# /VB.NET 创建、读取PDF文档

VB.NET

Imports Spire.Pdf
Imports System.IO
Imports System.Text
Imports System.Drawing

Namespace ExtractText1_PDF

    Class Program

        Private Shared Sub Main(ByVal args As String())
            Dim pdf As PdfDocument = New PdfDocument()
            pdf.LoadFromFile("sample.pdf")
            Dim page As PdfPageBase = pdf.Pages(0)
            Dim text As String = page.ExtractText(New RectangleF(50, 50, 500, 170))
            Dim sb As StringBuilder = New StringBuilder()
            sb.AppendLine(text)
            File.WriteAllText("Extract.txt", sb.ToString())
            System.Diagnostics.Process.Start("Extract.txt")
        End Sub
    End Class
End Namespace

2. 读取PDF图片

C#

using Spire.Pdf;
using System.Collections.Generic;
using System.Drawing;

namespace ExtractImages_PDF
{
    class Program
    {
        static void Main(string[] args)
        {
            //创建一个PdfDocument类对象,加载PDF测试文档
            PdfDocument doc = new PdfDocument(); 
            doc.LoadFromFile("sample.pdf");

            //声明List类对象
            List<Image> ListImage = new List<Image>();

            //遍历PDF文档所有页面
            for (int i = 0; i < doc.Pages.Count; i++)
            {
                //获取文档所有页,并提取页面中的所有图片
                PdfPageBase page = doc.Pages[i];
                Image[] images = page.ExtractImages();
                if (images != null && images.Length > 0)
                {
                    ListImage.AddRange(images);
                }

            }
            //将获取到的图片保存到本地路径
            if (ListImage.Count > 0)
            {
                for (int i = 0; i < ListImage.Count; i++)
                {
                    Image image = ListImage[i];
                    image.Save("image" + (i + 1).ToString() + ".png", System.Drawing.Imaging.ImageFormat.Png);
                }
                //打开获取到的图片
                System.Diagnostics.Process.Start("image1.png");
            }

        }
    }
}

读取结果:
C# /VB.NET 创建、读取PDF文档

VB.NET

Imports Spire.Pdf
Imports System.Collections.Generic
Imports System.Drawing

Namespace ExtractImages_PDF

    Class Program

        Private Shared Sub Main(ByVal args As String())
            Dim doc As PdfDocument = New PdfDocument()
            doc.LoadFromFile("sample.pdf")
            Dim ListImage As List(Of Image) = New List(Of Image)()
            For i As Integer = 0 To doc.Pages.Count - 1
                Dim page As PdfPageBase = doc.Pages(i)
                Dim images As Image() = page.ExtractImages()
                If images IsNot Nothing AndAlso images.Length > 0 Then
                    ListImage.AddRange(images)
                End If
            Next

            If ListImage.Count > 0 Then
                For i As Integer = 0 To ListImage.Count - 1
                    Dim image As Image = ListImage(i)
                    image.Save("image" & (i + 1).ToString() & ".png", System.Drawing.Imaging.ImageFormat.Png)
                Next

                System.Diagnostics.Process.Start("image1.png")
            End If
        End Sub
    End Class
End Namespace