Python返回漢字的漢語拼音(原創)

最近做程序用到漢字轉漢語拼音的問題，首先想到Google一下，但是拿來看了一下源碼，不是甚清楚。

後來想到自己Delphi有一個獲得拼音的代碼。於是找了出來。研究了一下代碼如下：

 

 

function get_hz_pywb(hzstr: string; pytype: integer): string; var I: Integer; allstr: string; hh: THandle; pp: pointer; ss: TStringList; function retturn_wbpy(tempstr: string; tqtype: integer): string; var outstr, str: string; i: integer; begin //################### 漢字查詢電位 i := 0; while i <= ss.Count - 1 do begin str := ss.Strings[i]; if (tempstr = trim(str[1] + str[2])) or (tempstr = trim(str[3] + str[4])) then begin str := ss.Strings[i]; Break; end; i := i + 1; end; //################### outstr := ''; //提取編碼 if tqtype = 1 then begin for i := pos('①', str) + 2 to pos('②', str) - 1 do if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i]; end; if tqtype = 2 then begin for i := pos('②', str) + 2 to pos('③', str) - 1 do if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i]; end; if tqtype = 3 then begin for i := pos('③', str) + 2 to pos('④', str) - 1 do if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i]; end; if tqtype = 4 then begin for i := pos('④', str) + 2 to length(str) do if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i]; end; Result := trim(outstr); end; begin //加載資源文件,將內容賦值給 s ss := TStringList.Create; hh := FindResource(hInstance, 'mywb', 'TXT'); hh := LoadResource(hInstance, hh); pp := LockResource(hh); ss.Text := pchar(pp); UnLockResource(hh); FreeResource(hh); allstr := ''; i := 0; while i <= length(hzstr) do //提取漢字字符 begin if (Ord(hzstr[I]) > 127) then begin if allstr = '' then allstr := retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype) else allstr := allstr + retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype); i := i + 2; end else begin if allstr = '' then allstr := hzstr[I] else allstr := allstr + hzstr[I]; i := i + 1; end; end; ss.Free; Result := trim(allstr); en

這是 http://download.csdn.net/source/1050411資源地址。

我把他改成Python代碼供大家研究。。。。

 

 

# -*-coding:utf-8-*- # 返回漢字的拼音 def Return_pinyin(word): global reslist for line in reslist: if (word==line[0]+line[1]) or (word==line[2]+line[3]): str = line break # 取①和②之間的內容 s = str.find(u'①')+4 e = str.find(u'②')+3 return str[s:e] def GetPy(word): #首先裝載資源文件 i=0 allstr = '' while i<len(word): if ord(word[i])>127: if allstr: allstr += Return_pinyin(word[i]+word[i+1]) else: allstr = Return_pinyin(word[i]+word[i+1]) i +=2 else: if allstr: allstr += word[i] else: allstr = word[i] i +=1 return allstr if __name__=='__main__': f = open('wbtext1.txt','r') reslist = f.readlines() f.close() word = raw_input(u'請輸入漢字: ') print GetPy(word).lower()

 

如果大家有什麼問題歡迎討論。。。。。。