Compact crawling (province, city (District Code \ zip code), county) data

The address information of the city needs to be used in recent projects, but few of the XML data downloaded from the Internet are the latest address information... the data is too old, leading to incomplete information in some regions. That's why I think the weather forecast official website has the latest and most comprehensive data. Paste the code, hoping to save some time for friends who are equally confused.

/*** @ Param var city name * @ returnstring array, 0 indicates zip code 1 indicates area code */@ suppresswarnings ("deprecation") Private string [] getzipcode (string var) {string [] code = new string [2]; string zipcode_s = "zip code:"; string zipcode_e = ""; string qhcode_s = "Area Code :"; string qhcode_e = "</TD>"; string encode = urlencoder. encode (VAR); try {URL url = new URL ("http://www.ip138.com/post/search.asp? Area = "+ encode +" & Action = area2zone "); bufferedreader BR = new bufferedreader (New inputstreamreader (URL. openstream (), "GBK"); For (string line; (line = BR. readline ())! = NULL;) {int zipnum = line. indexof (zipcode_s); If (zipnum> 1) {string STR = line. substring (zipnum + zipcode_s.length (); STR = Str. substring (0, str. indexof (zipcode_e); Code [0] = STR;} int qhnum = line. indexof (qhcode_s); If (qhnum> 1) {string STR = line. substring (qhnum + qhcode_s.length (); STR = Str. substring (0, str. indexof (qhcode_e); Code [1] = STR; break ;}} catch (exception e) {system. out. println (VAR + "\ T error" + E. tostring ();} return code;}/*** main program * @ throws exception */@ testpublic void main () throws exception {// 1: get all provinces treemap <string, string> provincesbuffer = getaddressinfo ("http://www.weather.com.cn//data/city3jdata/china.html"); element prcele = incluenthelper. createelement ("provinces"); // 2: Obtain the city element citysele = incluenthelper by province. createelement ("citys"); // 3: Obtain the district and county element distele = Documen Based on the province and city Thelper. createelement ("Districts"); int p = 1; int c = 1; int d = 1; for (Entry <string, string> PRC: provincesbuffer. entryset () {element province = incluenthelper. createelement ("Province"); province. addattribute ("ID", "" + (p )). addattribute ("provincename", PRC. getvalue ()). addtext (PRC. getvalue (); // get the zip code treemap <string, string> citybuffer = getaddressinfo ("http://www.weather.com.cn/data/city3jdata/provshi" + PRC. getkey () + ". html "); For (Entry <string, string> citys: citybuffer. entryset () {element city = incluenthelper. createelement ("city"); string [] zipcode = getzipcode (Citys. getvalue (); If (zipcode [0] = NULL | zipcode [1] = NULL) system. out. println ("missing" + Citys. getvalue () + "Zip or area code! "); City. addattribute ("ID", "" + C ). addattriys ("cityname", Citys. getvalue ()). addattribute ("PID", P + ""). addattribute ("zipcode", zipcode [0]). addattribute ("areacode", zipcode [1]). addtext (Citys. getvalue (); treemap <string, string> distsbuffer = getaddressinfo ("http://www.weather.com.cn/data/city3jdata/station/" + PRC. getkey () + "" + Citys. getkey () + ". html "); For (Entry <string, string> dists: distsbuffer. entryset () {String value = dists. getvalue (); If (value. equals (Citys. getvalue () continue; element district = incluenthelper. createelement ("District"); District. addattribute ("ID", "" + (d ++ )). addattribute ("districtname", dists. getvalue ()). addattribute ("CID", C + ""). addtext (dists. getvalue (); distele. add (district);} citysele. add (city); C ++;} prcele. add (province); P ++;} // 4: Save it to the local saveinf ("F: \ provinces. XML ", prcele); saveinf ("F: \ Citys. XML ", citysele); saveinf (" F: \ districts. XML ", distele);}/** save XML * @ Param savepath XML save path * @ Param varele root element */private void saveinf (string savepath, element varele) {document vardoc = incluenthelper. createdocument (); vardoc. add (varele); try {xmlwriter xmlwri = new xmlwriter (New fileoutputstream (new file (savepath), new outputformat ("\ t", true, "UTF-8 ")); xmlwri. write (vardoc); xmlwri. close ();} Catch (exception e) {system. out. println (savepath + "failed due to the following reasons"); throw new runtimeexception (e) ;}/ *** get information ** @ Param Address URL path * @ returnkey: information No. Value: Information name */private treemap <string, string> getaddressinfo (string address) {treemap <string, string> China = new treemap <string, string> (); bufferedreader BR = NULL; string buffer = NULL; try {URL url = new URL (Address); BR = new bufferedreader (New inputstrea Mreader (URL. openstream (), "UTF-8"); buffer = BR. readline ();} catch (exception e) {system. out. println ("error:" + E. getmessage ();} finally {If (BR! = NULL) Try {BR. close ();} catch (ioexception e) {e. printstacktrace () ;}} if (buffer = NULL) return China; buffer = buffer. replaceall ("\\{|\}| \" "," "); string [] splits = buffer. split (","); For (string SP: splits) {string [] split = sp. split (":"); If (split! = NULL & Split. length = 2) China. put (split [0], split [1]); elsesystem. out. println (Address);} buffer = NULL; return China ;}

Download XML data

Compact crawling (province, city (District Code \ zip code), county) data