简单的HTML提取程序,但是有时在抓取网站时(例如,下面所述的我知道的YES是假的)!该程序改为提取隐私政策;有没有办法解决?在其他程序上效果很好
string urlAddress = @"https://anyavien.com/how-to-use-rosemary-to-improve-memory-by 75/";
string BaseHTML = "";
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(urlAddress);
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
if (response.StatusCode == HttpStatusCode.OK)
{
Stream receiveStream = response.GetResponseStream();
StreamReader readStream = null;
if (response.CharacterSet == null)
{
readStream = new StreamReader(receiveStream);
Console.WriteLine("Error"); //make skip this link if error
}
else
{
readStream = new StreamReader(receiveStream, Encoding.GetEncoding(response.CharacterSet));
readStream.ToString();
//Console.WriteLine(readStream);
}
string ImpureChtml = readStream.ReadToEnd().ToString();
HtmlofEachC.Add(ImpureChtml);
// Console.WriteLine(ImpureChtml);
Console.WriteLine("----------Extracted HTML From Links----------------------- -");
Console.WriteLine("----------------------------------");
}