程序師世界是廣大編程愛好者互助、分享、學習的平台,程序師世界有你更精彩!
首頁
編程語言
C語言|JAVA編程
Python編程
網頁編程
ASP編程|PHP編程
JSP編程
數據庫知識
MYSQL數據庫|SqlServer數據庫
Oracle數據庫|DB2數據庫
 程式師世界 >> 編程語言 >> .NET網頁編程 >> C# >> C#入門知識 >> C#若何解析http報文

C#若何解析http報文

編輯:C#入門知識

C#若何解析http報文。本站提示廣大學習愛好者:(C#若何解析http報文)文章只能為提供參考,不一定能成為您想要的結果。以下是C#若何解析http報文正文


上面經由過程一段內容有文字解釋有代碼剖析,並附有展現圖供年夜家進修。

要解析HTTP報文,須要完成以下操作:

讀取HTTP報頭供給的各類屬性
剖析屬性值,從中獲得內容編碼和字符集編碼
將報頭數據和內容停止分別
斷定內容能否文本照樣二進制,假如是二進制的則不停止處置
假如內容是文本,按報頭中供給的內容編碼和字符集編碼停止解緊縮息爭碼
今朝沒有找到.Net框架內置的解析辦法,實際上HttpClient等類在外部應當曾經完成懂得析,但不知為什麼沒有地下這些處置辦法。(亦或是我沒找到)

那末只能本身來解析這些數據了。

我們先來看看這個經由gzip緊縮的文本內容的HTTP報文:

這裡供給一個老外寫的粗陋的解析類(曾經過修正,原代碼中存在一些嚴重BUG):

public enum HTTPHeaderField
{
 Accept = 0,
 Accept_Charset = 1,
 Accept_Encoding = 2,
 Accept_Language = 3,
 Accept_Ranges = 4,
 Authorization = 5,
 Cache_Control = 6,
 Connection = 7,
 Cookie = 8,
 Content_Length = 9,
 Content_Type = 10,
 Date = 11,
 Expect = 12,
 From = 13,
 Host = 14,
 If_Match = 15,
 If_Modified_Since = 16,
 If_None_Match = 17,
 If_Range = 18,
 If_Unmodified_Since = 19,
 Max_Forwards = 20,
 Pragma = 21,
 Proxy_Authorization = 22,
 Range = 23,
 Referer = 24,
 TE = 25,
 Upgrade = 26,
 User_Agent = 27,
 Via = 28,
 Warn = 29,
 Age = 30,
 Allow = 31,
 Content_Encoding = 32,
 Content_Language = 33,
 Content_Location = 34,
 Content_Disposition = 35,
 Content_MD5 = 36,
 Content_Range = 37,
 ETag = 38,
 Expires = 39,
 Last_Modified = 40,
 Location = 41,
 Proxy_Authenticate = 42,
 Refresh = 43,
 Retry_After = 44,
 Server = 45,
 Set_Cookie = 46,
 Trailer = 47,
 Transfer_Encoding = 48,
 Vary = 49,
 Warning = 50,
 WWW_Authenticate = 51
};
class HTTPHeader
{
 #region PROPERTIES
 private string[] m_StrHTTPField = new string[52];
 private byte[] m_byteData = new byte[4096];
 public string[] HTTPField
 {
  get { return m_StrHTTPField; }
  set { m_StrHTTPField = value; }
 }
 public byte[] Data
 {
  get { return m_byteData; }
  set { m_byteData = value; }
 }
 #endregion
 // convertion
 System.Text.ASCIIEncoding encoding = new System.Text.ASCIIEncoding();
 #region CONSTRUCTEUR
 /// <summary>
 /// Constructeur par défaut - non utilisé
 /// </summary>
 private HTTPHeader()
 { }
 public HTTPHeader(byte[] ByteHTTPRequest)
 {
  string HTTPRequest = encoding.GetString(ByteHTTPRequest);
  try
  {
   int IndexHeaderEnd;
   string Header;
   // Si la taille de requête est supérieur ou égale à 1460, alors toutes la chaine est l'entête http
   if (HTTPRequest.Length <= 1460)
    Header = HTTPRequest;
   else
   {
    IndexHeaderEnd = HTTPRequest.IndexOf("\r\n\r\n");
    Header = HTTPRequest.Substring(0, IndexHeaderEnd);
    Data = ByteHTTPRequest.Skip(IndexHeaderEnd + 4).ToArray();
   }
   HTTPHeaderParse(Header);
  }
  catch (Exception)
  { }
 }
 #endregion
 #region METHODES
 private void HTTPHeaderParse(string Header)
 {
  #region HTTP HEADER REQUEST & RESPONSE
  HTTPHeaderField HHField;
  string HTTPfield, buffer;
  int Index;
  foreach (int IndexHTTPfield in Enum.GetValues(typeof(HTTPHeaderField)))
  {
   HHField = (HTTPHeaderField)IndexHTTPfield;
   HTTPfield = "\n" + HHField.ToString().WordStr('_', '-') + ": "; //Ajout de \n devant pour éviter les doublons entre cookie et set_cookie
   // Si le champ n'est pas présent dans la requête, on passe au champ suivant
   Index = Header.IndexOf(HTTPfield);
   if (Index == -1)
    continue;
   buffer = Header.Substring(Index + HTTPfield.Length);
   Index = buffer.IndexOf("\r\n");
   if (Index == -1)
    m_StrHTTPField[IndexHTTPfield] = buffer.Trim();
   else
    m_StrHTTPField[IndexHTTPfield] = buffer.Substring(0, Index).Trim();
   //Console.WriteLine("Index = " + IndexHTTPfield + " | champ = " + HTTPfield.Substring(1) + " " + m_StrHTTPField[IndexHTTPfield]);
  }
  // Affichage de tout les champs
  /*for (int j = 0; j < m_StrHTTPField.Length; j++)
  {
   HHField = (HTTPHeaderField)j;
   Console.WriteLine("m_StrHTTPField[" + j + "]; " + HHField + " = " + m_StrHTTPField[j]);
  }
  */
  #endregion
 }
 #endregion
}

編寫以下代碼以完成解析文件:

class Program
{
 static void Main(string[] args)
 {
  SRART: Console.WriteLine("輸出待解析的HTTP報文數據文件完全途徑:");
  var filename = Console.ReadLine();
  try
  {
   FileStream fs = new FileStream(filename, FileMode.Open);
   BinaryReader br = new BinaryReader(fs);
   var data = br.ReadBytes((int)fs.Length);
   var header = new HTTPHeader(data);
   var x = 0;
   foreach (var f in header.HTTPField)
   {
    if (!String.IsNullOrEmpty(f))
    {
     Console.WriteLine($"[{x:00}] - {(HTTPHeaderField) x} : {f}");
    }
    x++;
   }
   Console.WriteLine($"總數據尺寸{fs.Length}字節,現實數據尺寸{header.Data.Length}字節");
   Console.WriteLine(Encoding.UTF8.GetString(header.Data));
   Console.WriteLine();
   br.Close();
   fs.Close();  
  }
  catch (Exception e)
  {
   Console.WriteLine(e);
  }
  goto SRART;
 }
}

這裡還未完成gzip解緊縮和字符解碼,直接用UTF8解碼輸入的。(須要時再寫吧,都是膂力活兒~)

後果圖展現:

上面的圖是沒有經由gzip緊縮過的數據。

以上就是用C#若何解析http報文的全體內容,哪位年夜俠還有好的辦法迎接提出名貴看法,愛好年夜家愛好以上內容所述。

  1. 上一頁:
  2. 下一頁:
Copyright © 程式師世界 All Rights Reserved