private async Task <UrlResultModel> ParseUrlAsync(Uri url)
{
var resultModel = new UrlResultModel()
{
Url = url.ToString()
};
using (WebClient c = new WebClient())
{
try
{
string body = await c.DownloadStringTaskAsync(url);
if (!string.IsNullOrEmpty(body))
{
resultModel.AnchorCount = AnchorRegEx.Matches(body).Count;
}
}
catch (ArgumentException e)
{
resultModel.Error = e.Message;
}
catch (WebException e)
{
resultModel.Error = e.Message;
}
}
return(resultModel);
}
public static void SelectSearchEngine()
{
UrlResultModel urlObject = new UrlResultModel();
Console.Write("Search:");
urlObject.content = Console.ReadLine();
urlObject.engineUrl = "https://www.google.com.br/search?q=";
ConnectEngine(urlObject);
}
public UrlResultModel Upload(HttpPostedFileBase file, string watermark)
{
UrlResultModel result = new UrlResultModel();
result.HasError = false;
string path = AppDomain.CurrentDomain.BaseDirectory + "uploads\\";
var sourcePath = Path.Combine(path, file.FileName);
file.SaveAs(sourcePath);
try
{
Guid id = Guid.NewGuid();
var filename = System.IO.Path.GetFileNameWithoutExtension(sourcePath);
var extension = System.IO.Path.GetExtension(sourcePath);
string tempPath = path + "_" + Guid.NewGuid() + ".pdf";
string targetPath = path + $"{id}_{filename}.pdf";
if (new List <string>()
{
".ppt", ".pptx"
}.Contains(extension.Trim().ToLower()))
{
AsposeTransPdf.AsposePPTToPDF(sourcePath, tempPath);
}
if (new List <string>()
{
".doc", ".docx"
}.Contains(extension.Trim().ToLower()))
{
AsposeTransPdf.AsposeWordToPDF(sourcePath, tempPath);
}
if (new List <string>()
{
".xls", ".xlsx"
}.Contains(extension.Trim().ToLower()))
{
AsposeTransPdf.AsposeExcelToPDF(sourcePath, tempPath);
}
//WordToPDF(tempPath, targetPath);
ITextSharpUtils.setWatermark(tempPath, targetPath, String.IsNullOrWhiteSpace(watermark) ? "金 风 科 技" : watermark);
System.IO.File.Delete(tempPath);
result.Url = $"uploads\\{id}_{filename}.pdf";
}
catch (Exception e)
{
result.HasError = true;
result.ErrorMessage = e.Message;
}
finally
{
System.IO.File.Delete(sourcePath);
}
return(result);
}
public static void ConnectEngine(UrlResultModel url)
{
HtmlWeb web = new HtmlWeb();
HtmlDocument document = web.Load(url.engineUrl + url.content);
document.Save(Environment.GetFolderPath(Environment.SpecialFolder.Desktop) + @"\ScraperTexto.txt");
HtmlDocument documentParse = new HtmlDocument();
documentParse.Load(Environment.GetFolderPath(Environment.SpecialFolder.Desktop) + @"\ScraperTexto.txt");
HtmlNode[] nodes = documentParse.DocumentNode.SelectNodes("//a").ToArray();
foreach (HtmlNode obj in nodes)
{
obj.InnerHtml = Regex.Replace(obj.InnerHtml, @"<[^>]*>", String.Empty);
Console.WriteLine(obj.InnerHtml + " ");
}
Console.Read();
}
