/// <summary>
/// 从pdf中导出图片
/// </summary>
/// <param name="pdfFilePath"></param>
/// <param name="outDir"></param>
public static void DealPdf(string pdfFilePath, string outDir)
{
//加载PDF文档
PdfDocument doc = new PdfDocument();
doc.LoadFromFile(pdfFilePath);
FileInfo file = new FileInfo(pdfFilePath);
if (!file.Exists)
{
Console.WriteLine($"pdf文件不存在");
}
string path = Path.Combine(outDir, file.Name.Replace(".pdf", ""));
if (!Directory.Exists(path))
{
Directory.CreateDirectory(path);
}
for (int i = 0; i < doc.Pages.Count; i++)
{
Console.WriteLine($"处理第{i+1}页面图片");
// 实例化一个Spire.Pdf.PdfPageBase对象
PdfPageBase page = doc.Pages[i];
var texts = page.FindAllText().Finds.Where(a =>
(a.Size.Height >= 9 && a.Size.Height <= 10))
.OrderBy(a => a.Bounds, new PointComparer()).ToList();
if (!texts.Any())
{
texts = page.FindAllText().Finds.Where(a =>
(a.Size.Height >= 6 && a.Size.Height <= 7))
.OrderBy(a => a.Bounds, new PointComparer()).ToList();
}
var images = page.ImagesInfo.Where(a => a.Bounds.Size.Width < 300)
.OrderBy(a => a.Bounds, new PointComparer()).ToList();
for (int j = 0; j < texts.Count; j++)
{
try
{
images[j].Image.Save(Path.Combine(path, $"{i + 1}_{j + 1}_{texts[j].MatchText ?? texts[j].SearchText}.jpg"));
}
catch (Exception e)
{
}
}
//// 获取所有pages里面的图片
//Image[] images = page.ExtractImages();
//if (images != null && images.Length > 0)
//{
// listImages.AddRange(images);
//}
}
}