public void GetTextFromPdfUri() { var uri = new Uri("http://www.africau.edu/images/default/sample.pdf"); var parser = new UrlExtractor(uri); var content = parser.ExtractPlainText(); Assert.IsFalse(string.IsNullOrEmpty(content)); }
public void GetTextFromWordUri() { var uri = new Uri("http://iiswc.org/iiswc2012/sample.doc"); var parser = new UrlExtractor(uri); var content = parser.ExtractPlainText(); Assert.IsFalse(string.IsNullOrEmpty(content)); }
public void GetTextFromHtml() { var uri = new Uri("https://docs.microsoft.com/en-us/dotnet/api/system.net.webclient.downloadstring?view=net-5.0"); var parser = new UrlExtractor(uri); var content = parser.ExtractPlainText(); Assert.IsFalse(string.IsNullOrEmpty(content)); }