这是一个包装好的下载类，它支持gzip并检查编码标头和meta标签，以便对其正确解码。
实例化该类，然后调用
GetPage()。
public class HttpDownloader{ private readonly string _referer; private readonly string _userAgent; public Encoding Encoding { get; set; } public WebHeaderCollection Headers { get; set; } public Uri Url { get; set; } public HttpDownloader(string url, string referer, string userAgent) { Encoding = Encoding.GetEncoding("ISO-8859-1"); Url = new Uri(url); // verify the uri _userAgent = userAgent; _referer = referer; } public string GetPage() { HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url); if (!string.IsNullOrEmpty(_referer)) request.Referer = _referer; if (!string.IsNullOrEmpty(_userAgent)) request.UserAgent = _userAgent; request.Headers.Add(HttpRequestHeader.AcceptEncoding, "gzip,deflate"); using (HttpWebResponse response = (HttpWebResponse)request.GetResponse()) { Headers = response.Headers; Url = response.ResponseUri; return ProcessContent(response); } } private string ProcessContent(HttpWebResponse response) { SetEncodingFromHeader(response); Stream s = response.GetResponseStream(); if (response.ContentEncoding.ToLower().Contains("gzip")) s = new GZipStream(s, CompressionMode.Decompress); else if (response.ContentEncoding.ToLower().Contains("deflate")) s = new DeflateStream(s, CompressionMode.Decompress); MemoryStream memStream = new MemoryStream(); int bytesRead; byte[] buffer = new byte[0x1000]; for (bytesRead = s.Read(buffer, 0, buffer.Length); bytesRead > 0; bytesRead = s.Read(buffer, 0, buffer.Length)) { memStream.Write(buffer, 0, bytesRead); } s.Close(); string html; memStream.Position = 0; using (StreamReader r = new StreamReader(memStream, Encoding)) { html = r.ReadToEnd().Trim(); html = CheckmetaCharSetAndReEnpre(memStream, html); } return html; } private void SetEncodingFromHeader(HttpWebResponse response) { string charset = null; if (string.IsNullOrEmpty(response.CharacterSet)) { Match m = Regex.Match(response.ContentType, @";s*charsets*=s*(?<charset>.*)", RegexOptions.IgnoreCase); if (m.Success) { charset = m.Groups["charset"].Value.Trim(new[] { ''', '"' }); } } else { charset = response.CharacterSet; } if (!string.IsNullOrEmpty(charset)) { try { Encoding = Encoding.GetEncoding(charset); } catch (ArgumentException) { } } } private string CheckmetaCharSetAndReEnpre(Stream memStream, string html) { Match m = new Regex(@"<metas+.*?charsets*=s*""?(?<charset>[A-Za-z0-9_-]+)""?", RegexOptions.Singleline | RegexOptions.IgnoreCase).Match(html); if (m.Success) { string charset = m.Groups["charset"].Value.ToLower() ?? "iso-8859-1"; if ((charset == "unipre") || (charset == "utf-16")) { charset = "utf-8"; } try { Encoding metaEncoding = Encoding.GetEncoding(charset); if (Encoding != metaEncoding) { memStream.Position = 0L; StreamReader repreReader = new StreamReader(memStream, metaEncoding); html = repreReader.ReadToEnd().Trim(); repreReader.Close(); } } catch (ArgumentException) { } } return html; }}
