C#爬虫----Fiddler 插件开发 自动生成代码
标签：post ret url sub builder date tla nbsp 修改时间
哈喽^_^
一般我们在编写网页爬虫的时候经常会使用到Fiddler 这个工具来分析http包,而且通常并不是分析一个包就够了的,所以为了把更多的时间放在分析http包上,自动化生成封包代码就尤为重要了(其实之前已经有第三方的插件了,自己编写主要是为了适配自定义的http请求模块)!
首先注册拖拽事件 允许直接在Fiddler Session列表中拖入Session到插件界面
1 private void TrCode_Load(object sender, System.EventArgs e)
2 {
3 AllowDrop = true;
4 DragDrop += TrCode_DragDrop;
5 DragOver += TrCode_DragOver;
6 }
1 private void TrCode_DragOver(object sender, DragEventArgs e)
2 {
3 e.Effect = e.Data.GetDataPresent("Fiddler.Session[]") ? DragDropEffects.Copy : DragDropEffects.None;
4 }
5
6 private void TrCode_DragDrop(object sender, DragEventArgs e)
7 {
8 //获取拖入的Session数据 数据格式Fiddler.Session[]
9 var data = (Session[])e.Data.GetData("Fiddler.Session[]");
10 if (_sessions == data)
11 {
12 return;
13 }
14 _sessions = data;
15 if ((data == null)) return;
16 if (data.Length > 1)
17 {
18 AnalyticSession(data);
19 }
20 else
21 {
22 //多个也只获取第一个进行解析
23 AnalyticSession(data[0]);
24 }
25 }
获取到Session了 开始解析 并且生成代码 (生成的代码可以根据自己的情况去自定义 )
1 ///
2 /// 生成TrCode
3 ///
4 ///
5 ///
6 private void GenerateTrCode(Session session, bool addMethodName = false)
7 {
8
9 var stringBuilder = new StringBuilder(500);
10 string uri;
11 if (cbxGetPlaceholder.Checked && session.fullUrl.Split(‘?‘).Length > 1)
12 {
13 var str = session.fullUrl;
14 var getUrl = str.Split(‘?‘);
15 if (getUrl.Length == 2)
16 {
17 str = getUrl[1];
18 str = GetUrlParameters(str);
19 }
20 uri = getUrl[0] + "?" + str;
21 }
22 else
23 {
24 uri = session.fullUrl;
25 }
26 if (!addMethodName)
27 {
28 var strParameter = string.Empty;
29 var list = new List();
30 if (cbxPostPlaceholder.Checked)
31 {
32 list.AddRange(_listParameterInfo.Where(i => i.SubmitMethod == "Post"));
33 }
34 if (cbxGetPlaceholder.Checked)
35 {
36 list.AddRange(_listParameterInfo.Where(i => i.SubmitMethod == "Get"));
37 }
38 foreach (var parameter in list)
39 {
40 strParameter += $",string {parameter.ParameterName}";
41 }
42 if (!string.IsNullOrWhiteSpace(strParameter))
43 {
44 strParameter = strParameter.Remove(0, 1);
45 }
46 stringBuilder.AppendLine($@"
47 public void Submit({strParameter})
48 {{");
49 }
50 stringBuilder.AppendLine($"var submitType = new SubmitType();");
51 stringBuilder.AppendLine($"submitType.Url=\"{uri}\";");
52 if (session.RequestMethod == "POST")
53 {
54 if (session.RequestBody.Length > 0)
55 {
56 string submitString;
57 if (cbxPostPlaceholder.Checked)
58 {
59 var str = Uri.UnescapeDataString(Encoding.UTF8.GetString(session.RequestBody));
60 submitString = GetUrlParameters(str);
61 stringBuilder.AppendLine($"submitType.SubmitString = $\"{submitString}\";");
62 }
63 else
64 {
65 submitString = Uri.UnescapeDataString(Encoding.UTF8.GetString(session.RequestBody));
66 //字符 转义
67 submitString = submitString.Replace("{", "{{");
68 submitString = submitString.Replace("}", "}}");
69 submitString = submitString.Replace("\"", "\\\"");
70 stringBuilder.AppendLine($"submitType.SubmitString = \"{submitString}\";");
71 }
72 }
73 }
74 var nameValue = new NameValueCollection();
75 var addedContentType = false;
76 foreach (var headers in session.RequestHeaders)
77 {
78 switch (headers.Name)
79 {
80 case "Accept":
81 stringBuilder.AppendLine($"submitType.Accept = \"{headers.Value}\";");
82 break;
83 case "Accept-Encoding":
84 stringBuilder.AppendLine($"submitType.AcceptEncoding = \"{headers.Value}\";");
85 break;
86 case "Accept-Language":
87 stringBuilder.AppendLine($"submitType.AcceptLanguage = \"{headers.Value}\";");
88 break;
89 case "User-Agent":
90 stringBuilder.AppendLine($"submitType.UserAgent = \"{headers.Value}\";");
91 break;
92 case "Content-Type":
93 addedContentType = true;
94 stringBuilder.AppendLine($"submitType.ContentType = \"{headers.Value}\";");
95 break;
96 case "Referer":
97 stringBuilder.AppendLine($"submitType.Referer = \"{headers.Value}\";");
98 break;
99 case "Content-Length":
100 break;
101 case "Host":
102 break;
103 case "Connection":
104 break;
105 case "Cookie":
106 stringBuilder.AppendLine(checkBoxCookie.Checked
107 ? "submitType.Cookies = \"{cookies}\";"
108 : $"submitType.Cookies = \"{headers.Value}\";");
109 break;
110 case "Origin":
111 stringBuilder.AppendLine($"submitType.Origin = \"{headers.Value}\";");
112 break;
113 case "Cache-Control":
114 stringBuilder.AppendLine($"submitType.CacheControl = \"{headers.Value}\";");
115 break;
116 case "If-Modified-Since":
117 stringBuilder.AppendLine("//浏览器端缓存页面的最后修改时间,一般可以不使用,使用请使用上一个响应的结果");
118 stringBuilder.AppendLine("//submitType.IfModifiedSince = \"\";");
119 break;
120 default:
121 nameValue.Add(headers.Name, headers.Value);
122 break;
123 }
124 }
125 //如果不包含Content-Type 则给空
126 if (!addedContentType)
127 {
128 stringBuilder.AppendLine("submitType.ContentType = string.Empty;");
129 }
130 if (checkBoxProxy.Checked)
131 {
132
133 stringBuilder.AppendLine("submitType.AddProxyUri(runDataModel.ProxyUri);");
134 }
135 stringBuilder.AppendLine("submitType.UseCookieHelper = true;");
136 foreach (var key in nameValue.AllKeys)
137 {
138 stringBuilder.AppendLine($"submitType.RequestHeaders.Add(\"{key}\",\"{nameValue[key]}\");");
139 }
140
141 if (cbxImg.Checked)
142 {
143 var str = $@"
144 var image = {(session.RequestMethod == "POST" ? "Post" : "Get")}.Image(submitType);
145 var validateCode = new ValidateCode {{ Image = image,Cookies = submitType.ReturnCookies }};
146 return validateCode;
147 ";
148 stringBuilder.AppendLine(str);
149 }
150 else
151 {
152 stringBuilder.AppendLine(session.RequestMethod == "POST" ? "var html = Post.Html(submitType);" : "var html = Get.Html(submitType);");
153
154 }
155 if (!addMethodName)
156 {
157 stringBuilder.AppendLine(@"
158 }");
159 }
160 txtCode.Text = stringBuilder.ToString();
161 }
到这里就可以直接通过拖拽生成代码了
C#爬虫----Fiddler 插件开发 自动生成代码
标签：post ret url sub builder date tla nbsp 修改时间
原文地址：https://www.cnblogs.com/trevan/p/9494101.html
评论