Java get page encoding

article from: http://babyjoycry.javaeye.com/blog/587527 here thanks to the original author ... \ (^o^)/~Recent research crawl Web content, found to get the encoding format of the page, Java does not have a ready-made method of implementation, although CSDN has a talent to write an article, accompanied by code, unfortunately, I did not find the relevant package, forced, had to do their own hands and clothing.

Import Java.io.BufferedReader; Import java.io.IOException; Import Java.io.InputStreamReader; Import java.net.HttpURLConnection; Import Java.net.URL; Import Java.util.Iterator; Import java.util.List; Import Java.util.Map; Import Java.util.Set; Import Cpdetector.io.CodepageDetectorProxy; Import Cpdetector.io.HTMLCodepageDetector; Import Cpdetector.io.JChardetFacade; public class Pageencodedetector {private static Codepagedetectorproxy detector = Codepagedetectorproxy. Getinstan   CE ();     static {Detector.add (new Htmlcodepagedetector (false));   Detector.add (Jchardetfacade.getinstance ());  }/** * Test case * @param args */public static void main (string[] args) {Pageencodedetector web     = new Pageencodedetector ();     try {System.out.println (Web.getcharset ("http://www.baidu.com/"));     } catch (IOException e) {//TODO auto-generated catch block E.printstacktrace (); }}/** * @param strurl * pageURL address, need to start with http://http://www.pujia.com * @return * @throws IOException */Public String Getcharset (strin     G strURL) throws IOException {//define URL object url url = new URL (strurl);     Gets the HTTP connection object HttpURLConnection URLConnection = (httpurlconnection) URL. OpenConnection ();     ;     Urlconnection.connect ();     Page encoding String strencoding = null; /** * First according to header information, determine the page encoding *//MAP is the header information (URL page header information) map<string, list<string>> Map = u     Rlconnection.getheaderfields ();     set<string> keys = Map.keyset ();     iterator<string> Iterator = Keys.iterator ();     Traversal, finding character encoding String key = null;     String tmp = NULL;       while (Iterator.hasnext ()) {key = Iterator.next ();       TMP = Map.get (key). ToString (). toLowerCase (); Get Content-type CharSet if (key! = null && key.equals ("Content-type")) {int m = tmp.indexof ("Char         Set= "); if (M! =-1) {strencoding = tMp.substring (M + 8). Replace ("]", "" ");         return strencoding; }}}/** * Get the page code by parsing meta *///Get Web page source code (English characters and numbers are not garbled, so you can get correct <meta/> area) StringBuffer     SB = new StringBuffer ();     String Line;       try {BufferedReader in = new BufferedReader (new InputStreamReader (URL. OpenStream ()));       while (line = In.readline ())! = null) {sb.append (line);     } in.close ();       } catch (Exception e) {//Report No errors that arise System.err.println (e);     System.err. println ("Usage:java HttpClient <URL> [<filename>]");     } String Htmlcode = Sb.tostring ();     Parse the HTML source, remove the <meta/> area, and remove the charset String strbegin = "<meta";     String strend = ">";     String strtmp;     int begin = Htmlcode.indexof (Strbegin);     int end =-1;     int inttmp;       while (Begin >-1) {end = Htmlcode.substring (BEGIN). IndexOf (Strend); if (Begin >-1&& End >-1) {strtmp = htmlcode.substring (begin, Begin + End). toLowerCase ();         Inttmp = Strtmp.indexof ("charset"); if (Inttmp >-1) {strencoding = strtmp.substring (inttmp + 7, end). replace ("=", ""). Replace ("/           "," "). Replace (" \ "", ""). Replace ("\", ""). Replace ("", "").         return strencoding;       }} Htmlcode = Htmlcode.substring (begin);     Begin = Htmlcode.indexof (Strbegin);     }/** * Parse bytes Get page encoding */strencoding = getfileencoding (URL);     Sets the default page character encoding if (strencoding = = null) {strencoding = "GBK";   } return strencoding; }/** * *<br> * Method Description: Through the Page Content Identification page encoding * *<br> * Input parameters: strURL Web links; Timeout Timeout setting * *<br> * return type: page encoding */public static String getfileencoding (url url) {java.ni     O.charset.charset charset = null;     try {charset = detector.detectcodepage (URL); } catch (Exception e) {System.out.println (E.getclass () + "parse" + "Encode failed");     } if (charset! = null) return Charset.name ();   return null;  } }

Need to download Cpdetector_1.0.5.jar and Chardet.jar

Java get page encoding