提供思路
读取源HTML文件
byte[] downloadBytes = SomeMethond(url);获取源文件
System.Web.HttpResponse response = System.Web.HttpContext.Current.Response;
response.Clear();
response.AddHeader("Content-Type", "binary/octet-stream");
response.AddHeader("Content-Disposition",
"attachment; filename=" + downloadName + "; size=" + downloadBytes.Length.ToString());
response.Flush();
response.BinaryWrite(downloadBytes);
response.Flush();
response.End();
读取源HTML文件
byte[] downloadBytes = SomeMethond(url);获取源文件
System.Web.HttpResponse response = System.Web.HttpContext.Current.Response;
response.Clear();
response.AddHeader("Content-Type", "binary/octet-stream");
response.AddHeader("Content-Disposition",
"attachment; filename=" + downloadName + "; size=" + downloadBytes.Length.ToString());
response.Flush();
response.BinaryWrite(downloadBytes);
response.Flush();
response.End();
using WebSupergoo.ABCpdf4.Objects;
using WebSupergoo.ABCpdf4.Atoms;
//这个是要生成pdf文档的源文件的地址
string strUrl = "http://localhost/PR/TempFiles/PrintDetail.aspx";
string strFolder = "D:\test_pdf\";
string strPageName = "test.pdf";
Doc doc = new Doc();
doc.Rect.Inset(72,144);
l_intTemp = doc.AddImageUrl(strUrl,true,0,true);
while (true)
{
doc.FrameRect();
if (doc.GetInfo(l_intTemp, "Truncated") != "1")
break;
doc.Page = doc.AddPage();
l_intTemp = doc.AddImageToChain(l_intTemp);
}
for (int i = 1; i <= doc.PageCount; i++)
{
doc.PageNumber = i;
doc.Flatten();
}
doc.Save(strFolder + strPageName);
doc.Clear();
itextsharp里不是有解析的东西么?
ITextSharp.Text.html.simpleparser;
这里面不是有HTMLWorker类么?
他里面有Parse解析功能吧?