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
- Linux系统调优相关工具
一.系统调优概述 系统的运行状况: CPU -> MEM -> DISK*-> NETWORK -> 应用程序调优 分析是否有瓶颈(依据当前应用需求) 调优(把错误的调正确) ...
- MongoDB 实体映射
@Id主键,不可重复,自带索引,可以在定义的列名上标注,需要自己生成并维护不重复的约束.如果自己不设置@Id主键,mongo会自动生成一个唯一主键,并且插入时效率远高于自己设置主键.在实际业务中不建议 ...
- 用python实现简单EXCEL数据统计的实例
用python实现简单EXCEL数据统计的实例 下面小编就为大家带来一篇用python实现简单EXCEL数据统计的实例.小编觉得挺不错的,现在就分享给大家,也给大家做个参考.一起跟随小编过来看看吧 任 ...
- LeetCode.1217-交换芯片(Play with Chips)
这是小川的第次更新,第篇原创 看题和准备 今天介绍的是LeetCode算法题中Easy级别的第270题(顺位题号是1217).There are some chips, and the i-th ch ...
- LeetCode.1200-最小绝对值差(Minimum Absolute Difference)
这是小川的第次更新,第篇原创 看题和准备 今天介绍的是LeetCode算法题中Easy级别的第268题(顺位题号是1200).给定一个由不同的整数组成的数组arr,找到所有对元素,其中任意两个元素的绝 ...
- Linux服务知识点总结
一.firewalld防火墙 1.firewalld简述 firewalld:防火墙,其实就是一个隔离工具:工作于主机或者网络的边缘.对于进出本主机或者网络的报文根据事先定义好的网络规则做匹配检测,对 ...
- BiLSTM-CRF模型理解
适用任务 中文分词.词性标注.命名实体识别是自然语言理解中,基础性的工作,同时也是非常重要的工作. 在很多NLP的项目中,工作开始之前都要经过这三者中的一到多项工作的处理. 在深度学习中,有一种模型可 ...
- C语言Ⅰ博客作业10
这个作业属于那个课程 C语言程序设计II 这个作业要求在哪里 https://edu.cnblogs.com/campus/zswxy/CST2019-3/homework/10097 我在这个课程的 ...
- C# PC版微信消息监听自动回复
最近有个微商客户需要搞个 个人微信监听群消息关键字并实现自动回复功能, 因为他有很多群 很多买家咨询的话 一个个回复太麻烦, 客户要求 比如群里有人发 关键字 产品1 则自动回复产品1的相关描述 ...
- Kafka主题体系架构-复制、故障转移和并行处理
本文讨论了Kafka主题的体系架构,讨论了如何将分区用于故障转移和并行处理. Kafka主题,日志和分区 Kafka将主题存储在日志中.主题日志分为多个分区.Kafka将日志的分区分布在多个服务器或磁 ...