java获取页面编码

 

http://babyjoycry.javaeye.com/blog/587527

 

1. import info.monitorenter.cpdetector.io.CodepageDetectorProxy; 2. import info.monitorenter.cpdetector.io.HTMLCodepageDetector; 3. import info.monitorenter.cpdetector.io.JChardetFacade; 4. 5. import java.io.BufferedReader; 6. import java.io.IOException; 7. import java.io.InputStreamReader; 8. import java.net.HttpURLConnection; 9. import java.net.URL; 10. import java.util.Iterator; 11. import java.util.List; 12. import java.util.Map; 13. import java.util.Set; 14. 15. public class WebEncoding { 16. private static CodepageDetectorProxy detector = CodepageDetectorProxy 17. .getInstance(); 18. static { 19. 20. detector.add(new HTMLCodepageDetector(false)); 21. 22. detector.add(JChardetFacade.getInstance()); 23. 24. } 25. /** 测试用例 26. * @param args 27. */ 28. public static void main(String[] args) { 29. WebEncoding web=new WebEncoding(); 30. try { 31. System.out.println(web.getCharset("http://www.pujia.com/")); 32. } catch (IOException e) { 33. // TODO Auto-generated catch block 34. e.printStackTrace(); 35. } 36. } 37. /** 38. * @param strurl 39. * 页面url地址,需要以 http://开始，例：http: //www.pujia.com 40. * @return 41. * @throws IOException 42. */ 43. public String getCharset(String strurl) throws IOException { 44. // 定义URL对象 45. URL url = new URL(strurl); 46. // 获取http连接对象 47. HttpURLConnection urlConnection = (HttpURLConnection) url 48. .openConnection(); 49. ; 50. urlConnection.connect(); 51. // 网页编码 52. String strencoding = null; 53. 54. /** 55. * 首先根据header信息，判断页面编码 56. */ 57. // map存放的是header信息(url页面的头信息) 58. Map<String, List<String>> map = urlConnection.getHeaderFields(); 59. Set<String> keys = map.keySet(); 60. Iterator<String> iterator = keys.iterator(); 61. 62. // 遍历,查找字符编码 63. String key = null; 64. String tmp = null; 65. while (iterator.hasNext()) { 66. key = iterator.next(); 67. tmp = map.get(key).toString().toLowerCase(); 68. // 获取content-type charset 69. if (key != null && key.equals("Content-Type")) { 70. int m = tmp.indexOf("charset="); 71. if (m != -1) { 72. strencoding = tmp.substring(m + 8).replace("]", ""); 73. return strencoding; 74. } 75. } 76. } 77. 78. /** 79. * 通过解析meta得到网页编码 80. */ 81. // 获取网页源码(英文字符和数字不会乱码，所以可以得到正确<meta/>区域) 82. StringBuffer sb = new StringBuffer(); 83. String line; 84. try { 85. BufferedReader in = new BufferedReader(new InputStreamReader(url 86. .openStream())); 87. while ((line = in.readLine()) != null) { 88. sb.append(line); 89. } 90. in.close(); 91. } catch (Exception e) { // Report any errors that arise 92. System.err.println(e); 93. System.err 94. .println("Usage: java HttpClient <URL> [<filename>]"); 95. } 96. String htmlcode = sb.toString(); 97. // 解析html源码，取出<meta />区域，并取出charset 98. String strbegin = "<meta"; 99. String strend = ">"; 100. String strtmp; 101. int begin = htmlcode.indexOf(strbegin); 102. int end = -1; 103. int inttmp; 104. while (begin > -1) { 105. end = htmlcode.substring(begin).indexOf(strend); 106. if (begin > -1 && end > -1) { 107. strtmp = htmlcode.substring(begin, begin + end).toLowerCase(); 108. inttmp = strtmp.indexOf("charset"); 109. if (inttmp > -1) { 110. strencoding = strtmp.substring(inttmp + 7, end).replace( 111. "=", "").replace("/", "").replace("/"", "") 112. .replace("/'", "").replace(" ", ""); 113. return strencoding; 114. } 115. } 116. htmlcode = htmlcode.substring(begin); 117. begin = htmlcode.indexOf(strbegin); 118. } 119. 120. /** 121. * 分析字节得到网页编码 122. */ 123. strencoding = getFileEncoding(url); 124. 125. // 设置默认网页字符编码 126. if (strencoding == null) { 127. strencoding = "GBK"; 128. } 129. 130. return strencoding; 131. } 132. 133. /** 134. * 135. *<br> 136. * 方法说明：通过网页内容识别网页编码 137. * 138. *<br> 139. * 输入参数：strUrl 网页链接; timeout 超时设置 140. * 141. *<br> 142. * 返回类型：网页编码 143. */ 144. public static String getFileEncoding(URL url) { 145. 146. java.nio.charset.Charset charset = null; 147. try { 148. 149. charset = detector.detectCodepage(url); 150. 151. } catch (Exception e) { 152. 153. System.out.println(e.getClass() + "分析" + "编码失败"); 154. 155. } 156. 157. if (charset != null) 158. 159. return charset.name(); 160. 161. return null; 162. 163. } 164. }