Python中文转为拼音
# -*- coding: utf-8 -*-
import sys
def openTable():
f = open('gb-pinyin.table', 'r')
table = f.read()
f.close()
return table
def searchPinyin(num, table):
if(num>0 & num<160):
return chr(num)
v=table.split(';')
for i in xrange(len(v)-1,-1,-1):
s=v[i].split(',')
if int(s[1])<=num:
return s[0]
break
if __name__ == "__main__":
table = openTable()
if len(sys.argv) == 2:
chinese = sys.argv[1]
else:
sys.exit("Usage: python "+sys.argv[0]+" chinese")
i=0
str = ''
while(i<len(chinese)-1):
p = ord(chinese[i:i+1])
if(p>160):
i+=1
q = ord(chinese[i:i+1])
p = p*256+q-65536
i+=1
str = '%s%s' % (str, searchPinyin(p,table))
print str
新建gb-pinyin.table文件
a,-20319;ai,-20317;an,-20304;ang,-20295;ao,-20292;ba,-20283;bai,-20265;ban,-20257;bang,-20242;bao,-20230;bei,-20051;ben,-20036;beng,-20032;bi,-20026;bian,-20002;biao,-19990;bie,-19986;bin,-19982;bing,-19976;bo,-19805;bu,-19784;ca,-19775;cai,-19774;can,-19763;cang,-19756;cao,-19751;ce,-19746;ceng,-19741;cha,-19739;chai,-19728;chan,-19725;chang,-19715;chao,-19540;che,-19531;chen,-19525;cheng,-19515;chi,-19500;chong,-19484;chou,-19479;chu,-19467;chuai,-19289;chuan,-19288;chuang,-19281;chui,-19275;chun,-19270;chuo,-19263;ci,-19261;cong,-19249;cou,-19243;cu,-19242;cuan,-19238;cui,-19235;cun,-19227;cuo,-19224;da,-19218;dai,-19212;dan,-19038;dang,-19023;dao,-19018;de,-19006;deng,-19003;di,-18996;dian,-18977;diao,-18961;die,-18952;ding,-18783;diu,-18774;dong,-18773;dou,-18763;du,-18756;duan,-18741;dui,-18735;dun,-18731;duo,-18722;e,-18710;en,-18697;er,-18696;fa,-18526;fan,-18518;fang,-18501;fei,-18490;fen,-18478;feng,-18463;fo,-18448;fou,-18447;fu,-18446;ga,-18239;gai,-18237;gan,-18231;gang,-18220;gao,-18211;ge,-18201;gei,-18184;gen,-18183;geng,-18181;gong,-18012;gou,-17997;gu,-17988;gua,-17970;guai,-17964;guan,-17961;guang,-17950;gui,-17947;gun,-17931;guo,-17928;ha,-17922;hai,-17759;han,-17752;hang,-17733;hao,-17730;he,-17721;hei,-17703;hen,-17701;heng,-17697;hong,-17692;hou,-17683;hu,-17676;hua,-17496;huai,-17487;huan,-17482;huang,-17468;hui,-17454;hun,-17433;huo,-17427;ji,-17417;jia,-17202;jian,-17185;jiang,-16983;jiao,-16970;jie,-16942;jin,-16915;jing,-16733;jiong,-16708;jiu,-16706;ju,-16689;juan,-16664;jue,-16657;jun,-16647;ka,-16474;kai,-16470;kan,-16465;kang,-16459;kao,-16452;ke,-16448;ken,-16433;keng,-16429;kong,-16427;kou,-16423;ku,-16419;kua,-16412;kuai,-16407;kuan,-16403;kuang,-16401;kui,-16393;kun,-16220;kuo,-16216;la,-16212;lai,-16205;lan,-16202;lang,-16187;lao,-16180;le,-16171;lei,-16169;leng,-16158;li,-16155;lia,-15959;lian,-15958;liang,-15944;liao,-15933;lie,-15920;lin,-15915;ling,-15903;liu,-15889;long,-15878;lou,-15707;lu,-15701;lv,-15681;luan,-15667;lue,-15661;lun,-15659;luo,-15652;ma,-15640;mai,-15631;man,-15625;mang,-15454;mao,-15448;me,-15436;mei,-15435;men,-15419;meng,-15416;mi,-15408;mian,-15394;miao,-15385;mie,-15377;min,-15375;ming,-15369;miu,-15363;mo,-15362;mou,-15183;mu,-15180;na,-15165;nai,-15158;nan,-15153;nang,-15150;nao,-15149;ne,-15144;nei,-15143;nen,-15141;neng,-15140;ni,-15139;nian,-15128;niang,-15121;niao,-15119;nie,-15117;nin,-15110;ning,-15109;niu,-14941;nong,-14937;nu,-14933;nv,-14930;nuan,-14929;nue,-14928;nuo,-14926;o,-14922;ou,-14921;pa,-14914;pai,-14908;pan,-14902;pang,-14894;pao,-14889;pei,-14882;pen,-14873;peng,-14871;pi,-14857;pian,-14678;piao,-14674;pie,-14670;pin,-14668;ping,-14663;po,-14654;pu,-14645;qi,-14630;qia,-14594;qian,-14429;qiang,-14407;qiao,-14399;qie,-14384;qin,-14379;qing,-14368;qiong,-14355;qiu,-14353;qu,-14345;quan,-14170;que,-14159;qun,-14151;ran,-14149;rang,-14145;rao,-14140;re,-14137;ren,-14135;reng,-14125;ri,-14123;rong,-14122;rou,-14112;ru,-14109;ruan,-14099;rui,-14097;run,-14094;ruo,-14092;sa,-14090;sai,-14087;san,-14083;sang,-13917;sao,-13914;se,-13910;sen,-13907;seng,-13906;sha,-13905;shai,-13896;shan,-13894;shang,-13878;shao,-13870;she,-13859;shen,-13847;sheng,-13831;shi,-13658;shou,-13611;shu,-13601;shua,-13406;shuai,-13404;shuan,-13400;shuang,-13398;shui,-13395;shun,-13391;shuo,-13387;si,-13383;song,-13367;sou,-13359;su,-13356;suan,-13343;sui,-13340;sun,-13329;suo,-13326;ta,-13318;tai,-13147;tan,-13138;tang,-13120;tao,-13107;te,-13096;teng,-13095;ti,-13091;tian,-13076;tiao,-13068;tie,-13063;ting,-13060;tong,-12888;tou,-12875;tu,-12871;tuan,-12860;tui,-12858;tun,-12852;tuo,-12849;wa,-12838;wai,-12831;wan,-12829;wang,-12812;wei,-12802;wen,-12607;weng,-12597;wo,-12594;wu,-12585;xi,-12556;xia,-12359;xian,-12346;xiang,-12320;xiao,-12300;xie,-12120;xin,-12099;xing,-12089;xiong,-12074;xiu,-12067;xu,-12058;xuan,-12039;xue,-11867;xun,-11861;ya,-11847;yan,-11831;yang,-11798;yao,-11781;ye,-11604;yi,-11589;yin,-11536;ying,-11358;yo,-11340;yong,-11339;you,-11324;yu,-11303;yuan,-11097;yue,-11077;yun,-11067;za,-11055;zai,-11052;zan,-11045;zang,-11041;zao,-11038;ze,-11024;zei,-11020;zen,-11019;zeng,-11018;zha,-11014;zhai,-10838;zhan,-10832;zhang,-10815;zhao,-10800;zhe,-10790;zhen,-10780;zheng,-10764;zhi,-10587;zhong,-10544;zhou,-10533;zhu,-10519;zhua,-10331;zhuai,-10329;zhuan,-10328;zhuang,-10322;zhui,-10315;zhun,-10309;zhuo,-10307;zi,-10296;zong,-10281;zou,-10274;zu,-10270;zuan,-10262;zui,-10260;zun,-10256;zuo,-10254
Python中文转为拼音的更多相关文章
- Python中文转拼音代码(支持全拼和首字母缩写)
本文的代码,从https://github.com/cleverdeng/pinyin.py升级得来,针对原文的代码,做了以下升级: 1 2 3 4 1.可以传入参数firstcode:如果为 ...
- PHP 之中文转为拼音
/** * Created by PhpStorm. * User: Administrator * Date: 2019/1/2 0002 * Time: 下午 1:01 */ class PinY ...
- Python 汉字转拼音
本文参考: Python中文转拼音代码(支持全拼和首字母缩写) 中文中不可以有“()” # -*- coding: utf-8 -*- __version__ = '0.9' __all__ = [& ...
- python 将中文转拼音后填充到url做参数并写入excel
闲着没事写了个小工具,将中文转拼音后填充到url做参数并写如excel 一.先看下演示,是个什么东西 二.代码 代码用到一个中文转拼音的库,库是网上下的,稍微做了下修改,已经找不原来下载的地址了,然后 ...
- Python中文繁简体转换工具
Openccpy ___ _____ __ ___ ___ ___ _____ __ __ / __`\/\ '__`\ /'__`\/' _ `\ /'___\ /'___\/\ '__`\/\ \ ...
- java实现汉字转为拼音
java实现汉字转为拼音: 1.需要导入pinyin4j.jar package com.loo.pinyin; import net.sourceforge.pinyin4j.PinyinHelpe ...
- PHP中文转拼音扩展
Pinyin 基于 CC-CEDICT 词典的中文转拼音工具,更准确的支持多音字的汉字转拼音解决方案. 安装 使用 Composer 安装: $ composer require "over ...
- Mono 3.2 测试NPinyin 中文转换拼音代码
C#中文转换为拼音NPinyin代码 在Mono 3.2下运行正常,Spacebuilder 有使用到NPinyin组件,代码兼容性没有问题. using System; using System. ...
- 【原】python中文文本挖掘资料集合
这些网址是我在学习python中文文本挖掘时觉得比较好的网站,记录一下,后期也会不定期添加: 1.http://www.52nlp.cn/python-%E7%BD%91%E9%A1%B5%E7% ...
随机推荐
- laravel redis存数组并设置过期时间
$data = [ 'zoneList'=>$zoneList, 'eqList' => $eqList, 'mdateList' => $mdateList ]; Redis::s ...
- Flask之上下文管理机制
前引 在了解flask上下文管理机制之前,先来一波必知必会的知识点. 面向对象双下方法 首先,先来聊一聊面向对象中的一些特殊的双下划线方法,比如__call__.__getattr__系列.__get ...
- V8的垃圾回收和内存限制
V8的垃圾回收和内存限制 前言 在第三次浏览器大战中,来自Google的Chrome浏览器凭借优异的性能成为聚光灯下的焦点.而Chrome的成功离不开站在其背后的JavaScript引擎V8. 随着V ...
- iscsi-文件类型
iSCSI简介(Internet SCSI): iSCSI 小型计算机系统接口,IBM公司研发,用于在IP网络上运行SCSI协议:解决了 SCSI需要直连存储设备的局限性:可以不停机扩展存储容量,iS ...
- 安装mysql-proxy
1.下载安装包 wget https://cdn.mysql.com/archives/mysql-proxy/mysql-proxy-0.8.5-linux-glibc2.3-x86-64bit.t ...
- 安装aodh
在控制节点上执行 #!/bin/bash MYSQL_ROOT_PASSWD='m4r!adbOP' GNOCCHI_PASSWD='gnocchi1234!' CEILOMETER_PASSWD=' ...
- 《机器学习实战(基于scikit-learn和TensorFlow)》第七章内容学习心得
本章主要讲述了“集成学习”和“随机森林”两个方面. 重点关注:bagging/pasting.boosting.stacking三个方法. 首先,提出一个思想,如果想提升预测的准确率,一个很好的方法就 ...
- 使用vue-lbsmap快速开发地图应用/GPSBD
vue-lbsmap是一款基于vue的WebGIS地图插件,经过我们多年实际项目应用中积累的技术,打造的灵活.易用.数据驱动型插件,可以帮助您快速开展地图业务层的应用开发,完全免费 <!DOCT ...
- hanlp添加自定义字典的步骤介绍
本篇分享一个hanlp添加自定义字典的方法,供大家参考! 总共分为两步: 第一步:将自定义的字典放到custom目录下,然后删除CustomDicionary.txt.bin,因为分词的时候会读这 ...
- mybatis-plus配置多数据源invalid bound statement (not found)
mybatis-plus配置多数据源invalid bound statement (not found) 错误原因 引入mybatis-plus应该使用的依赖如下,而不是mybatis <de ...