close
網友問了個問題，我天真的認為是UrlEncode()就可以解決，直到心冷大指點後，才知道事情不是我想的那麼簡單。經過測試後，不管用什麼方法都沒辦法正確的用WebClient去抓資料，google了老半天也找不到有用的資訊。結果無意中發現這篇，看來跟這個名為punycode的東西有關，有了關鍵字，呵~~人生就變彩色的了，一下子就找到有用的文章。
看起來是因為大多數的 DNS 伺服器僅支援 ASCII 字元，所以用中文字下去解析時就會發生錯誤，因此才出現punycode這個東西。以下是google到的解法
1: public partial class Form1 : Form {
2: public Form1() {
3: InitializeComponent();
4: }
5:
6: private void Form1_Load(object sender, EventArgs e) {
7: string strPunycode = "http://xn--" + Punycode.encode("正負2度c") + ".tw/";
8: WebClient client = new WebClient();
9: string html = client.DownloadString(strPunycode);
10: }
11: }
12:
13: class Punycode {
14: /* Punycode parameters */
15: static int TMIN = 1;
16: static int TMAX = 26;
17: static int BASE = 36;
18: static int INITIAL_N = 128;
19: static int INITIAL_BIAS = 72;
20: static int DAMP = 700;
21: static int SKEW = 38;
22: static char DELIMITER = '-';
23: /**
24: * Punycodes a unicode string.
25: *
26: * @param input Unicode string.
27: * @return Punycoded string.
28: */
29: public static String encode(String input) {
30: int n = INITIAL_N;
31: int delta = 0;
32: int bias = INITIAL_BIAS;
33: StringBuilder output = new StringBuilder();
34: // Copy all basic code points to the output
35: int b = 0;
36: for (int i = 0; i < input.Length; i++) {
37: char c = input[i];
38: if (isBasic(c)) {
39: output.Append(c);
40: b++;
41: }
42: }
43: // Append delimiter
44: if (b > 0) {
45: output.Append(DELIMITER);
46: }
47: int h = b;
48: while (h < input.Length) {
49: int m = int.MaxValue;
50: // Find the minimum code point >= n
51: for (int i = 0; i < input.Length; i++) {
52: int c = input[i];
53: if (c >= n && c < m) {
54: m = c;
55: }
56: }
57: if (m - n > (int.MaxValue - delta) / (h + 1)) {
58: throw new Exception("OVERFLOW");
59: }
60: delta = delta + (m - n) * (h + 1);
61: n = m;
62: for (int j = 0; j < input.Length; j++) {
63: int c = input[j];
64: if (c < n) {
65: delta++;
66: if (0 == delta) {
67: throw new Exception("OVERFLOW");
68: }
69: }
70: if (c == n) {
71: int q = delta;
72: for (int k = BASE; ; k += BASE) {
73: int t;
74: if (k <= bias) {
75: t = TMIN;
76: } else if (k >= bias + TMAX) {
77: t = TMAX;
78: } else {
79: t = k - bias;
80: }
81: if (q < t) {
82: break;
83: }
84: output.Append((char)digit2codepoint(t + (q - t) % (BASE - t)));
85: q = (q - t) / (BASE - t);
86: }
87: output.Append((char)digit2codepoint(q));
88: bias = adapt(delta, h + 1, h == b);
89: delta = 0;
90: h++;
91: }
92: }
93: delta++;
94: n++;
95: }
96: return output.ToString();
97: }
98: /**
99: * Decode a punycoded string.
100: *
101: * @param input Punycode string
102: * @return Unicode string.
103: */
104: public static String decode(String input) {
105: int n = INITIAL_N;
106: int i = 0;
107: int bias = INITIAL_BIAS;
108: StringBuilder output = new StringBuilder();
109: int d = input.LastIndexOf(DELIMITER);
110: if (d > 0) {
111: for (int j = 0; j < d; j++) {
112: char c = input[j];
113: if (!isBasic(c)) {
114: throw new Exception("BAD_INPUT");
115: }
116: output.Append(c);
117: }
118: d++;
119: } else {
120: d = 0;
121: }
122: while (d < input.Length) {
123: int oldi = i;
124: int w = 1;
125: for (int k = BASE; ; k += BASE) {
126: if (d == input.Length) {
127: throw new Exception("BAD_INPUT");
128: }
129: int c = input[d++];
130: int digit = codepoint2digit(c);
131: if (digit > (int.MaxValue - i) / w) {
132: throw new Exception("OVERFLOW");
133: }
134: i = i + digit * w;
135: int t;
136: if (k <= bias) {
137: t = TMIN;
138: } else if (k >= bias + TMAX) {
139: t = TMAX;
140: } else {
141: t = k - bias;
142: }
143: if (digit < t) {
144: break;
145: }
146: w = w * (BASE - t);
147: }
148: bias = adapt(i - oldi, output.Length + 1, oldi == 0);
149: if (i / (output.Length + 1) > int.MaxValue - n) {
150: throw new Exception("OVERFLOW");
151: }
152: n = n + i / (output.Length + 1);
153: i = i % (output.Length + 1);
154: output.Insert(i, (char)n);
155: i++;
156: }
157: return output.ToString();
158: }
159: public static int adapt(int delta, int numpoints, bool first) {
160: if (first) {
161: delta = delta / DAMP;
162: } else {
163: delta = delta / 2;
164: }
165: delta = delta + (delta / numpoints);
166: int k = 0;
167: while (delta > ((BASE - TMIN) * TMAX) / 2) {
168: delta = delta / (BASE - TMIN);
169: k = k + BASE;
170: }
171: return k + ((BASE - TMIN + 1) * delta) / (delta + SKEW);
172: }
173: public static bool isBasic(char c) {
174: return c < 0x80;
175: }
176: public static int digit2codepoint(int d) {
177: if (d < 26) {
178: // 0..25 : 'a'..'z'
179: return d + 'a';
180: } else if (d < 36) {
181: // 26..35 : '0'..'9';
182: return d - 26 + '0';
183: } else {
184: throw new Exception("BAD_INPUT");
185: }
186: }
187: public static int codepoint2digit(int c) {
188: if (c - '0' < 10) {
189: // '0'..'9' : 26..35
190: return c - '0' + 26;
191: } else if (c - 'a' < 26) {
192: // 'a'..'z' : 0..25
193: return c - 'a';
194: } else {
195: throw new Exception("BAD_INPUT");
196: }
197: }
198: }
．在C:\WINDOWS\Microsoft.NET\Framework\v2.0.50727\CONFIG\machine.config加入這一段
1: <section name="uri" type="System.Configuration.UriSection, System, Version=2.0.0.0, Culture=neutral, PublicKeyToken=b77a5c561934e089" />
．在app.config中加入
1: <configuration>
2: <uri>
3: <idn enabled="All" />
4: <iriParsing enabled="true" />
5: </uri>
6: </configuration>
然後程式碼完全不用動
1: public partial class Form1 : Form {
2: public Form1() {
3: InitializeComponent();
4: }
5:
6: private void Form1_Load(object sender, EventArgs e) {
7: string url = "http://正負2度c.tw/";
8: WebClient client = new WebClient();
9: string html = client.DownloadString(url);
10: }
11: }
以上就屬第二種最方便，也說明了.NET真的是好用到一個不行啊~~
全站熱搜
留言列表
