private async Task <SolveCaptchaResult> SubmitCaptchaAnswerAsync(string captcha, string amzn, int tries, CancellationToken cancellationToken)
{
var query = HttpUtility.ParseQueryString(string.Empty);
query["amzn"] = amzn;
query["amzn-r"] = "%2F";
query["field-keywords"] = captcha;
using (var response = await _httpClient.GetAsync(ValidateCaptcha + "?" + query, cancellationToken))
{
var doc = await response.Content.ReadAsHtmlDocumentAsync();
// ensure not blocked
var title = new ExtractTitle().Execute(doc);
if (title != null && title.Contains("Robot Check"))
{
Log.Information("{Uri}: Solve Captcha Failed ({Tries} tries)", _uriForLogging, tries);
return(new SolveCaptchaResult
{
Success = false,
NextCaptchaPage = doc
});
}
Log.Information("{Uri}: Solve Captcha Success ({Tries} tries)", _uriForLogging, tries);
return(new SolveCaptchaResult
{
Success = true
});
}
}
private async Task <AmazonResponseResult> GetAsyncAsHtmlDoc(Uri uri, CancellationToken cancellationToken, bool setRedirectUri = false)
{
using (var response = await GetAsync(uri, cancellationToken))
{
if (response.StatusCode == HttpStatusCode.MovedPermanently || response.StatusCode == HttpStatusCode.Found)
{
var redirectedUri = response.Headers.Location;
return(await GetAsyncAsHtmlDoc(redirectedUri, cancellationToken, true));
}
if (response.StatusCode == HttpStatusCode.OK)
{
var result = new AmazonResponseResult
{
HtmlDocument = await response.Content.ReadAsHtmlDocumentAsync()
};
if (setRedirectUri)
{
result.RedirectUri = uri;
}
// ensure not blocked
var title = new ExtractTitle().Execute(result.HtmlDocument);
if (title != null && title.Contains("Robot Check"))
{
throw new EncounterCaptchaException("Amazon has blocked scraper.", uri, result.HtmlDocument);
}
return(result);
}
throw new NotSupportedException();
}
}
