public ExtractionResponse RunExtraction()
{
List <InputFileItem> inputItemCollection;
var fileReader = new InputFileReader(_csvDelimiter);
try
{
inputItemCollection = fileReader.GetInputItemCollection(Request.InputFilePath);
}
catch (Exception ex)
{
Response.GeneralException = ex.GetInnerMostException();
return(Response);
}
var successCnt = 0;
var markupAggregator = new MarkupAggregator(
HttpAgent, VerboseLogger, _hrefRegex, _invalidSiteLinkPatterns);
var emailExtractor = new EmailExtractor(_emailRegex);
var fileWriter = new OutputFileWriter(_csvDelimiter, Request.OutputDirectory);
foreach (var inputItem in inputItemCollection)
{
VerboseLogger.Log($"Extracting from {inputItem.SiteUrl} url...");
try
{
ProcessInputFileItem(inputItem, markupAggregator, emailExtractor, fileWriter);
VerboseLogger.Log($"Extraction completed for {inputItem.SiteUrl} url...");
successCnt++;
}
catch (Exception ex)
{
var eEx = new ExtractionException("", ex)
{
InputUrl = inputItem.SiteUrl
};
VerboseLogger.Log("Extraction failed. Moving to next url...");
Response.ExtractionExceptions = Response.ExtractionExceptions ?? new List <ExtractionException>();
Response.ExtractionExceptions.Add(eEx);
}
}
Response.SuccessfulExtractions = successCnt;
return(Response);
}
public ExtractionResponse RunExtraction()
{
List<InputFileItem> inputItemCollection;
var fileReader = new InputFileReader(_csvDelimiter);
try
{
inputItemCollection = fileReader.GetInputItemCollection(Request.InputFilePath);
}
catch (Exception ex)
{
Response.GeneralException = ex.GetInnerMostException();
return Response;
}
var successCnt = 0;
var markupAggregator = new MarkupAggregator(
HttpAgent, VerboseLogger, _hrefRegex, _invalidSiteLinkPatterns);
var emailExtractor = new EmailExtractor(_emailRegex);
var fileWriter = new OutputFileWriter(_csvDelimiter, Request.OutputDirectory);
foreach (var inputItem in inputItemCollection)
{
VerboseLogger.Log($"Extracting from {inputItem.SiteUrl} url...");
try
{
ProcessInputFileItem(inputItem, markupAggregator, emailExtractor, fileWriter);
VerboseLogger.Log($"Extraction completed for {inputItem.SiteUrl} url...");
successCnt++;
}
catch (Exception ex)
{
var eEx = new ExtractionException("", ex) { InputUrl = inputItem.SiteUrl };
VerboseLogger.Log("Extraction failed. Moving to next url...");
Response.ExtractionExceptions = Response.ExtractionExceptions ?? new List<ExtractionException>();
Response.ExtractionExceptions.Add(eEx);
}
}
Response.SuccessfulExtractions = successCnt;
return Response;
}
