This repository was archived by the owner on Sep 4, 2019. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 61
Expand file tree
/
Copy pathOtherHelper.cs
More file actions
303 lines (297 loc) · 10.4 KB
/
Copy pathOtherHelper.cs
File metadata and controls
303 lines (297 loc) · 10.4 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
using System;
using System.IO;
using System.Text;
namespace HttpCode.Core
{
/// <summary>
/// 正则表达式静态类
/// </summary>
public class RegexString
{
/// <summary>
/// 获取所有的A链接
/// </summary>
public static readonly string Alist = "<a[\\s\\S]+?href[=\"\']([\\s\\S]+?)[\"\'\\s+][\\s\\S]+?>([\\s\\S]+?)</a>";
/// <summary>
/// 获取所有的Img标签
/// </summary>
public static readonly string ImgList = "<img[\\s\\S]*?src=[\"\']([\\s\\S]*?)[\"\'][\\s\\S]*?>([\\s\\S]*?)>";
/// <summary>
/// 所有的Nscript
/// </summary>
public static readonly string Nscript = "<nscript[\\s\\S]*?>[\\s\\S]*?</nscript>";
/// <summary>
/// 所有的Style
/// </summary>
public static readonly string Style = "<style[\\s\\S]*?>[\\s\\S]*?</style>";
/// <summary>
/// 所有的Script
/// </summary>
public static readonly string Script = "<script[\\s\\S]*?>[\\s\\S]*?</script>";
/// <summary>
/// 所有的Html
/// </summary>
public static readonly string Html = "<[\\s\\S]*?>";
/// <summary>
/// 换行符号
/// </summary>
public static readonly string NewLine = Environment.NewLine;
/// <summary>
///获取网页编码
/// </summary>
public static readonly string Enconding = "<meta[^<]*charset=([^<]*)[\"']";
/// <summary>
/// 所有Html
/// </summary>
public static readonly string AllHtml = "([\\s\\S]*?)";
/// <summary>
/// title
/// </summary>
public static readonly string HtmlTitle = "<title>([\\s\\S]*?)</title>";
}
/// <summary>
/// 图片对象
/// </summary>
public class ImgItem
{
/// <summary>
/// 图片网址
/// </summary>
public string Src { get; set; }
/// <summary>
/// 图片标签Html
/// </summary>
public string Html { get; set; }
}
/// <summary>
/// A链接对象
/// </summary>
public class AItem
{
/// <summary>
/// 链接地址
/// </summary>
public string Href { get; set; }
/// <summary>
/// 链接文本
/// </summary>
public string Text { get; set; }
/// <summary>
/// 链接的图片
/// </summary>
public ImgItem Img { get; set; }
/// <summary>
/// 整个连接Html
/// </summary>
public string Html { get; set; }
/// <summary>
/// A链接的类型 文本/图像
/// </summary>
public AType Type { get; set; }
}
/// <summary>
/// A 标签类型
/// </summary>
public enum AType
{
/// <summary>
/// 文本链接(默认)
/// </summary>
Text,
/// <summary>
/// 图片链接
/// </summary>
Img
}
/// <summary>
/// 从流识别编码
/// </summary>
public class StreamEncoder
{
/// <summary>
/// 取得一个文本文件的编码方式。如果无法在文件头部找到有效的前导符，Encoding.Default将被返回。
/// </summary>
/// <param name="fileName">文件名。</param>
/// <returns></returns>
public static Encoding GetEncoding(string fileName)
{
return GetEncoding(fileName, Encoding.Default);
}
/// <summary>
/// 取得一个文本文件流的编码方式。
/// </summary>
/// <param name="stream">文本文件流。</param>
/// <returns></returns>
public static Encoding GetEncoding(FileStream stream)
{
return GetEncoding(stream, Encoding.Default);
}
/// <summary>
/// 取得一个文本文件的编码方式。
/// </summary>
/// <param name="fileName">文件名。</param>
/// <param name="defaultEncoding">默认编码方式。当该方法无法从文件的头部取得有效的前导符时，将返回该编码方式。</param>
/// <returns></returns>
public static Encoding GetEncoding(string fileName, Encoding defaultEncoding)
{
FileStream fs = new FileStream(fileName, FileMode.Open);
Encoding targetEncoding = GetEncoding(fs, defaultEncoding);
fs.Close();
return targetEncoding;
}
/// <summary>
/// 取得一个文本文件流的编码方式。
/// </summary>
/// <param name="stream">文本文件流。</param>
/// <param name="defaultEncoding">默认编码方式。当该方法无法从文件的头部取得有效的前导符时，将返回该编码方式。</param>
/// <returns></returns>
public static Encoding GetEncoding(FileStream stream, Encoding defaultEncoding)
{
Encoding targetEncoding = defaultEncoding;
if (stream != null && stream.Length >= 2)
{
//保存文件流的前4个字节
byte byte1 = 0;
byte byte2 = 0;
byte byte3 = 0;
byte byte4 = 0;
//保存当前Seek位置
long origPos = stream.Seek(0, SeekOrigin.Begin);
stream.Seek(0, SeekOrigin.Begin);
int nByte = stream.ReadByte();
byte1 = Convert.ToByte(nByte);
byte2 = Convert.ToByte(stream.ReadByte());
if (stream.Length >= 3)
{
byte3 = Convert.ToByte(stream.ReadByte());
}
if (stream.Length >= 4)
{
byte4 = Convert.ToByte(stream.ReadByte());
}
//根据文件流的前4个字节判断Encoding
//Unicode {0xFF, 0xFE};
//BE-Unicode {0xFE, 0xFF};
//UTF8 = {0xEF, 0xBB, 0xBF};
if (byte1 == 0xFE && byte2 == 0xFF)//UnicodeBe
{
targetEncoding = Encoding.BigEndianUnicode;
}
if (byte1 == 0xFF && byte2 == 0xFE && byte3 != 0xFF)//Unicode
{
targetEncoding = Encoding.Unicode;
}
if (byte1 == 0xEF && byte2 == 0xBB && byte3 == 0xBF)//UTF8
{
targetEncoding = Encoding.UTF8;
}
//恢复Seek位置
stream.Seek(origPos, SeekOrigin.Begin);
}
return targetEncoding;
}
/// <summary>
/// 从字节数组中返回字符编码
/// </summary>
/// <param name="sen">字节数组</param>
/// <returns>编码结果</returns>
public static System.Text.Encoding GetEncodingFromBytes(byte[] sen)
{
if (sen.Length == 0)
{
return null;
}
else
{
Stream stream = new MemoryStream(sen);
return GetEncoding(stream);
}
}
// 新增加一个方法，解决了不带BOM的 UTF8 编码问题
/// <summary>
/// 通过给定的文件流，判断文件的编码类型
/// </summary>
/// <param name="fs">文件流</param>
/// <returns>文件的编码类型</returns>
public static System.Text.Encoding GetEncoding(Stream fs)
{
byte[] Unicode = new byte[] { 0xFF, 0xFE, 0x41 };
byte[] UnicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };
byte[] UTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; //带BOM
Encoding reVal = Encoding.Default;
using (BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default))
{
byte[] ss = r.ReadBytes(4);
if (ss[0] == 0xFE && ss[1] == 0xFF && ss[2] == 0x00)
{
reVal = Encoding.BigEndianUnicode;
}
else if (ss[0] == 0xFF && ss[1] == 0xFE && ss[2] == 0x41)
{
reVal = Encoding.Unicode;
}
else
{
if (ss[0] == 0xEF && ss[1] == 0xBB && ss[2] == 0xBF)
{
reVal = Encoding.UTF8;
}
else
{
int i;
int.TryParse(fs.Length.ToString(), out i);
ss = r.ReadBytes(i);
if (IsUTF8Bytes(ss))
reVal = Encoding.UTF8;
}
}
r.Close();
return reVal;
}
}
/// <summary>
/// 判断是否是不带 BOM 的 UTF8 格式
/// </summary>
/// <param name="data"></param>
/// <returns></returns>
private static bool IsUTF8Bytes(byte[] data)
{
int charByteCounter = 1; //计算当前正分析的字符应还有的字节数
byte curByte; //当前分析的字节.
for (int i = 0; i < data.Length; i++)
{
curByte = data[i];
if (charByteCounter == 1)
{
if (curByte >= 0x80)
{
//判断当前
while (((curByte <<= 1) & 0x80) != 0)
{
charByteCounter++;
}
//标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X
if (charByteCounter == 1 || charByteCounter > 6)
{
return false;
}
}
}
else
{
//若是UTF-8 此时第一位必须为1
if ((curByte & 0xC0) != 0x80)
{
return false;
}
charByteCounter--;
}
}
if (charByteCounter > 1)
{
return false;
}
return true;
}
}
}