我正在使用HttpWebRequest对象下载pdf文件,并使用所有“使用”块以及复制后的.Close方法将响应中的内容直接从响应流直接写入FileStream中。下一步,我需要使用一些第三方库(iText7)从该pdf文件中提取一些文本,但是它无法访问该文件。起初,我认为这是与iText7相关的问题,但后来我意识到似乎并非如此,因为我什至无法从文件资源管理器中删除文件,而我自己的应用程序出现“文件正在使用”错误。
这是示例代码:
HttpWebRequest webReq = (HttpWebRequest)HttpWebRequest.Create(url);
webReq.AllowAutoRedirect = true;
webReq.CookieContainer = Cookies;
webReq.UserAgent = UserAgent;
webReq.Referer = Referrer;
webReq.Method = WebRequestMethods.Http.Get;
using (HttpWebResponse response = (HttpWebResponse)webReq.GetResponse())
{
using (Stream httpResponseStream = response.GetResponseStream())
{
using (FileStream output = File.Create(file1))
{
httpResponseStream.CopyTo(output);
output.Close();
}
httpResponseStream.Close();
response.Close();
Cookies = webReq.CookieContainer;
}
}
GC.Collect();
ExtractPDFDoc(file1);//error throws in this function and the exception.message is "Cannot open document."
Console.WriteLine("now waiting to let you check the file is in use? try delete it manually...");
Console.ReadKey(); //added this line to ensure that file is actually in use. I can't even delete the file manually from windows file explorer at this time. But, interestingly, Acrobat Reader can OPEN the file when I double click, which makes me thing that Adobe and iText7 uses different methods to open the pdf file - but anyway - I can't help it tho.
您能帮忙这里有什么问题吗?
对于那些想要查看ExtractPDFDoc()方法的人:
public static object ExtractPDFDoc(string filename)
{
iText.Kernel.Pdf.PdfReader pdfReader = null;
iText.Kernel.Pdf.PdfDocument pdfDocument = null;
try
{
pdfReader = new iText.Kernel.Pdf.PdfReader(filename);
pdfDocument = new iText.Kernel.Pdf.PdfDocument(pdfReader);
}
catch (Exception ex)
{
pdfReader = null;
pdfDocument = null;
return new Exception(string.Format("ExtractPDFDoc() failed on file '{0}' with message '{1}'", filename, ex.Message));
//this is where I get the error, ex.Message is 'Cannot open document.'
//however, I can open it in Adobe Reader but I can't delete it before closing my app.
}
}
public static object ExtractPDFDoc(string filename)
{
iText.Kernel.Pdf.PdfReader pdfReader = null;
iText.Kernel.Pdf.PdfDocument pdfDocument = null;
try
{
pdfReader = new iText.Kernel.Pdf.PdfReader(filename);
pdfDocument = new iText.Kernel.Pdf.PdfDocument(pdfReader);
}
catch (Exception ex)
{
throw new Exception(string.Format("ExtractPDFDoc() failed on file '{0}' with message '{1}'", filename, ex.Message), ex);
}
finally
{
pdfReader?.Dispose();
pdfDocument?.Dispose();
}
}