internal string[] GetParagraphs()
{
List<string> paragraphs = new List<string>();
foreach (AsposePdf.Page page in _document.Pages)
{
var textVisitor = new AsposePdf.Text.TextAbsorber();
try
{
page.Accept(textVisitor);
}
catch (Exception e)
{
Logger.LogError(e);
}
if (String.IsNullOrEmpty(textVisitor.Text))
{
continue;
}
string[] lines = Regex.Split(textVisitor.Text, "\r\n"); // Todo: There should be a better way to get the text per paragraph!
paragraphs.AddRange(lines);
}
paragraphs.RemoveAll(String.IsNullOrEmpty);
return paragraphs.ToArray();
}
/// <summary>
/// 读取 pdf 文件中的文本
/// </summary>
/// <param name="filename"></param>
/// <returns></returns>
public static string GetTextFromPdf(string filename)
{
var textAbsorber = new Aspose.Pdf.Text.TextAbsorber();
var pdf = new Aspose.Pdf.Document(filename);
pdf.Pages.Accept(textAbsorber);
return(textAbsorber.Text);
}
public static string GetPdfContent(string filepath)
{
int numPDFMaxPage = Util.GetAppSetting("PDFMaxPage", PDFMaxPage.ToString()).ToInt();
Aspose.Pdf.Document doc = new Aspose.Pdf.Document(filepath);
Aspose.Pdf.Text.TextAbsorber txt = new Aspose.Pdf.Text.TextAbsorber();
StringBuilder sb = new StringBuilder();
for (int i = 1; i <= doc.Pages.Count; i++)
{
if (i > numPDFMaxPage)
{
break;
}
doc.Pages[i].Accept(txt);
sb.Append(txt.Text);
}
return(sb.ToString());
}
