写一个aps.net 的模拟蜘蛛程序,简单流程搞定了,最关键的 网页编码判断上,
utf -8gb2312bgk。用这种方案,不行
static string GetHtml(string url, Encoding encoding)
{
byte[] buf = new WebClient().DownloadData(url);
if (encoding != null) return encoding.GetString(buf);
string html = Encoding.UTF8.GetString(buf);
encoding = GetEncoding(html);
if (encoding == null || encoding == Encoding.UTF8) return html;
return encoding.GetString(buf);
}
只能区分 utf8 与 非utf8 被否定,而且 encoding 不支持中文的gbk 怎么办?
utf -8gb2312bgk。用这种方案,不行
static string GetHtml(string url, Encoding encoding)
{
byte[] buf = new WebClient().DownloadData(url);
if (encoding != null) return encoding.GetString(buf);
string html = Encoding.UTF8.GetString(buf);
encoding = GetEncoding(html);
if (encoding == null || encoding == Encoding.UTF8) return html;
return encoding.GetString(buf);
}
只能区分 utf8 与 非utf8 被否定,而且 encoding 不支持中文的gbk 怎么办?
encoding.default
{
HttpWebRequest request = null;
HttpWebResponse response = null;
StreamReader reader = null;
try
{
request = (HttpWebRequest)WebRequest.Create(url);
request.Timeout = 20000;
request.AllowAutoRedirect = false; response = (HttpWebResponse)request.GetResponse();
if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
{
if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
else
reader = new StreamReader(response.GetResponseStream(), Encoding.ASCII); string html = reader.ReadToEnd(); Regex reg_charset = new Regex(@"charset\b\s*=\s*(?<charset>[^""]*)");
if (reg_charset.IsMatch(html))
{
return reg_charset.Match(html).Groups["charset"].Value;
}
else if (response.CharacterSet != string.Empty)
{
return response.CharacterSet;
}
else
return Encoding.Default.BodyName;
}
}
catch
{
}
finally
{ if (response != null)
{
response.Close();
response = null;
}
if (reader != null)
reader.Close(); if (request != null)
request = null; } return Encoding.Default.BodyName;
}