《C# 爬虫破境之道》：第一境爬虫原理 — 第三节：WebResponse

第二节中，我们介绍了WebRequest，它可以帮助我们发送一个请求，不过正所谓“来而不往非礼也”，对方收到我们的请求，不给点回复，貌似不太合适（不过，还真有脸皮厚的：P）。

接下来，就重点研究一下，我们收到的回复，是个什么样的东东

[Code 1.3.1]

  1     //
  2     // Summary:
  3     //     Provides a response from a Uniform Resource Identifier (URI). This is an abstract
  4     //     class.
  5     public abstract class WebResponse : MarshalByRefObject, ISerializable, IDisposable
  6     {
  7         //
  8         // Summary:
  9         //     Initializes a new instance of the System.Net.WebResponse class.
 10         protected WebResponse();
 11         //
 12         // Summary:
 13         //     Initializes a new instance of the System.Net.WebResponse class from the specified
 14         //     instances of the System.Runtime.Serialization.SerializationInfo and System.Runtime.Serialization.StreamingContext
 15         //     classes.
 16         //
 17         // Parameters:
 18         //   serializationInfo:
 19         //     An instance of the System.Runtime.Serialization.SerializationInfo class that
 20         //     contains the information required to serialize the new System.Net.WebRequest
 21         //     instance.
 22         //
 23         //   streamingContext:
 24         //     An instance of the System.Runtime.Serialization.StreamingContext class that indicates
 25         //     the source of the serialized stream that is associated with the new System.Net.WebRequest
 26         //     instance.
 27         //
 28         // Exceptions:
 29         //   T:System.NotSupportedException:
 30         //     Any attempt is made to access the constructor, when the constructor is not overridden
 31         //     in a descendant class.
 32         protected WebResponse(SerializationInfo serializationInfo, StreamingContext streamingContext);
 33 
 34         //
 35         // Summary:
 36         //     Gets a System.Boolean value that indicates whether this response was obtained
 37         //     from the cache.
 38         //
 39         // Returns:
 40         //     true if the response was taken from the cache; otherwise, false.
 41         public virtual bool IsFromCache { get; }
 42         //
 43         // Summary:
 44         //     Gets a System.Boolean value that indicates whether mutual authentication occurred.
 45         //
 46         // Returns:
 47         //     true if both client and server were authenticated; otherwise, false.
 48         public virtual bool IsMutuallyAuthenticated { get; }
 49         //
 50         // Summary:
 51         //     When overridden in a descendant class, gets or sets the content length of data
 52         //     being received.
 53         //
 54         // Returns:
 55         //     The number of bytes returned from the Internet resource.
 56         //
 57         // Exceptions:
 58         //   T:System.NotSupportedException:
 59         //     Any attempt is made to get or set the property, when the property is not overridden
 60         //     in a descendant class.
 61         public virtual long ContentLength { get; set; }
 62         //
 63         // Summary:
 64         //     When overridden in a derived class, gets or sets the content type of the data
 65         //     being received.
 66         //
 67         // Returns:
 68         //     A string that contains the content type of the response.
 69         //
 70         // Exceptions:
 71         //   T:System.NotSupportedException:
 72         //     Any attempt is made to get or set the property, when the property is not overridden
 73         //     in a descendant class.
 74         public virtual string ContentType { get; set; }
 75         //
 76         // Summary:
 77         //     When overridden in a derived class, gets the URI of the Internet resource that
 78         //     actually responded to the request.
 79         //
 80         // Returns:
 81         //     An instance of the System.Uri class that contains the URI of the Internet resource
 82         //     that actually responded to the request.
 83         //
 84         // Exceptions:
 85         //   T:System.NotSupportedException:
 86         //     Any attempt is made to get or set the property, when the property is not overridden
 87         //     in a descendant class.
 88         public virtual Uri ResponseUri { get; }
 89         //
 90         // Summary:
 91         //     When overridden in a derived class, gets a collection of header name-value pairs
 92         //     associated with this request.
 93         //
 94         // Returns:
 95         //     An instance of the System.Net.WebHeaderCollection class that contains header
 96         //     values associated with this response.
 97         //
 98         // Exceptions:
 99         //   T:System.NotSupportedException:
100         //     Any attempt is made to get or set the property, when the property is not overridden
101         //     in a descendant class.
102         public virtual WebHeaderCollection Headers { get; }
103         //
104         // Summary:
105         //     Gets a value that indicates if headers are supported.
106         //
107         // Returns:
108         //     Returns System.Boolean. true if headers are supported; otherwise, false.
109         public virtual bool SupportsHeaders { get; }
110 
111         //
112         // Summary:
113         //     When overridden by a descendant class, closes the response stream.
114         //
115         // Exceptions:
116         //   T:System.NotSupportedException:
117         //     Any attempt is made to access the method, when the method is not overridden in
118         //     a descendant class.
119         public virtual void Close();
120         //
121         // Summary:
122         //     Releases the unmanaged resources used by the System.Net.WebResponse object.
123         public void Dispose();
124         //
125         // Summary:
126         //     When overridden in a descendant class, returns the data stream from the Internet
127         //     resource.
128         //
129         // Returns:
130         //     An instance of the System.IO.Stream class for reading data from the Internet
131         //     resource.
132         //
133         // Exceptions:
134         //   T:System.NotSupportedException:
135         //     Any attempt is made to access the method, when the method is not overridden in
136         //     a descendant class.
137         public virtual Stream GetResponseStream();
138         //
139         // Summary:
140         //     Releases the unmanaged resources used by the System.Net.WebResponse object, and
141         //     optionally disposes of the managed resources.
142         //
143         // Parameters:
144         //   disposing:
145         //     true to release both managed and unmanaged resources; false to releases only
146         //     unmanaged resources.
147         protected virtual void Dispose(bool disposing);
148         //
149         // Summary:
150         //     Populates a System.Runtime.Serialization.SerializationInfo with the data that
151         //     is needed to serialize the target object.
152         //
153         // Parameters:
154         //   serializationInfo:
155         //     The System.Runtime.Serialization.SerializationInfo to populate with data.
156         //
157         //   streamingContext:
158         //     A System.Runtime.Serialization.StreamingContext that specifies the destination
159         //     for this serialization.
160         protected virtual void GetObjectData(SerializationInfo serializationInfo, StreamingContext streamingContext);
161     }

System.Net.WebResponse 全貌

相比较WebRequest而言，WebResponse简单许多，这里就不再分解片断讲解了。有事儿说事儿，不要以貌取人：D

首先，与WebRequest的类似，它还是抽象类，两个构造函数的结构，一票子虚属性，大部分都是只读的，和一票子虚方法。

其次，与WebRequest不同，它继承了System.IDisposable接口，提醒我们啊，用完了，要释放啊~~~~~~

几个属性

[Code 1.3.2]

 1         /// <summary>
 2         /// 只读，指示这个回复是不是从缓存中获取的
 3         /// </summary>
 4         public virtual bool IsFromCache { get; }
 5         /// <summary>
 6         /// 只读，指示是否发生相互认证
 7         /// </summary>
 8         public virtual bool IsMutuallyAuthenticated { get; }
 9         /// <summary>
10         /// 指示收到的数据长度
11         /// </summary>
12         public virtual long ContentLength { get; set; }
13         /// <summary>
14         /// 指示收到的内容类型
15         /// </summary>
16         public virtual string ContentType { get; set; }
17         /// <summary>
18         /// 只读，指示收到的实际资源URI
19         /// </summary>
20         public virtual Uri ResponseUri { get; }
21         /// <summary>
22         /// 只读，Header集合，HTTP协议中的重点
23         /// </summary>
24         public virtual WebHeaderCollection Headers { get; }
25         /// <summary>
26         /// 只读，指示是否支持Header集合
27         /// </summary>
28         public virtual bool SupportsHeaders { get; }

System.Net.WebResponse 属性

重要的属性有Headers、ContentType、ContentLength。对于分析数据都是举足轻重的。

几个方法

[Code 1.3.3]

 1         /// <summary>
 2         /// 获得目标资源的数据流
 3         /// </summary>
 4         public virtual Stream GetResponseStream();
 5         /// <summary>
 6         /// 关闭Response流
 7         /// </summary>
 8         public virtual void Close();
 9         /// <summary>
10         /// 释放WebResponse对象
11         /// </summary>
12         public void Dispose();
13         /// <summary>
14         /// 释放WebResponse对象
15         /// </summary>
16         protected virtual void Dispose(bool disposing);
17         /// <summary>
18         /// 使用序列化目标对象所需的数据填充System.Runtime.Serialization.SerializationInfo
19         /// </summary>
20         protected virtual void GetObjectData(SerializationInfo serializationInfo, StreamingContext streamingContext);