时间:2020-08-09 python教程 查看: 1637
对于需要大量翻译的数据,人工翻译太慢,此时需要使用软件进行批量翻译。
1.使用360的翻译
def fanyi_word_cn(string):
url="https://fanyi.so.com/index/search"
#db_path = './db/tasks.db'
Form_Data= {}
#这里输入要翻译的英文
Form_Data['query']= string
Form_Data['eng']= '1'
#用urlencode把字典变成字符串,#服务器不接受字典,只接受字符串和二进制
data= parse.urlencode(Form_Data).encode('utf-8')
#改成服务器可识别的数据后,请求,获取回应数据
response= request.urlopen(url, data)
html= response.read().decode("utf-8")#解码方式
#java中的对象(集合)和数组(元素为集合),loads可转Python字典
result= json.loads(html)
#字典调取键名data下的键名fanyi,获取其值
translate_result= result["data"]["fanyi"]
#print(translate_result)
return translate_result
2.使用Google自带的API来翻译
注意,需要安装API模块即可。
pip install translator
#google api, per 1000 words everyday
def translate_cn_api(content):
translator= Translator(to_lang="zh")
translation = translator.translate(content)
return translation
3.使用Google翻译来做,是由于Google提供的API有字节限制,每天只能翻译1000字。
备注:环境准备
3.1 java环境
3.2 安装execjs模块
pip install PyExecJS
3.3 两个实现模块
HandleJs.py
#coding=utf-8
import execjs
class Py4Js():
def __init__(self):
self.ctx = execjs.compile("""
function TL(a) {
var k = "";
var b = 406644;
var b1 = 3293161072;
var jd = ".";
var $b = "+-a^+6";
var Zb = "+-3^+b+-f";
for (var e = [], f = 0, g = 0; g < a.length; g++) {
var m = a.charCodeAt(g);
128 > m ? e[f++] = m : (2048 > m ? e[f++] = m >> 6 | 192 : (55296 == (m & 64512) && g + 1 < a.length && 56320 == (a.charCodeAt(g + 1) & 64512) ? (m = 65536 + ((m & 1023) << 10) + (a.charCodeAt(++g) & 1023),
e[f++] = m >> 18 | 240,
e[f++] = m >> 12 & 63 | 128) : e[f++] = m >> 12 | 224,
e[f++] = m >> 6 & 63 | 128),
e[f++] = m & 63 | 128)
}
a = b;
for (f = 0; f < e.length; f++) a += e[f],
a = RL(a, $b);
a = RL(a, Zb);
a ^= b1 || 0;
0 > a && (a = (a & 2147483647) + 2147483648);
a %= 1E6;
return a.toString() + jd + (a ^ b)
};
function RL(a, b) {
var t = "a";
var Yb = "+";
for (var c = 0; c < b.length - 2; c += 3) {
var d = b.charAt(c + 2),
d = d >= t ? d.charCodeAt(0) - 87 : Number(d),
d = b.charAt(c + 1) == Yb ? a >>> d: a << d;
a = b.charAt(c) == Yb ? a + d & 4294967295 : a ^ d
}
return a
}
""")
def getTk(self,text):
return self.ctx.call("TL",text)
main.py
#coding=utf-8
#import urllib.request
import urllib2
from HandleJs import Py4Js
from translate import Translator
import requests
# Example: find_last('aaaa', 'a') returns 3
# Make sure your procedure has a return statement.
def find_last(string,str):
last_position=-1
while True:
position=string.find(str,last_position+1)
if position==-1:
return last_position
last_position=position
def open_url(url):
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
req = urllib2.Request(url = url,headers=headers)
response = urllib2.urlopen(req)
data = response.read().decode('utf-8')
return data
def translate_core(content,tk, language):
if len(content) > 4891:
print("too long byte >4891")
return
content = urllib2.quote(content)
if language == 'de':
url = "http://translate.google.cn/translate_a/single?client=t"+ "&sl=de&tl=zh-CN&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca"+"&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1"+"&srcrom=0&ssel=0&tsel=0&kc=2&tk=%s&q=%s"%(tk,content)
else:
url = "http://translate.google.cn/translate_a/single?client=t"+ "&sl=en&tl=zh-CN&hl=zh-CN&dt=at&dt=bd&dt=ex&dt=ld&dt=md&dt=qca"+"&dt=rw&dt=rm&dt=ss&dt=t&ie=UTF-8&oe=UTF-8&clearbtn=1&otf=1&pc=1"+"&srcrom=0&ssel=0&tsel=0&kc=2&tk=%s&q=%s"%(tk,content)
#result为json格式
result = open_url(url)
#print('results:' + result)
if len(content) < 10:
end = result.find("\",")
if end > 4:
return result[4:end]
else:
result_all = ''
if language == 'de':
result_all = result.split(',null,"de",null,null,')[0].replace('[[', '').replace(']]', ']')[1:]
else:
result_all = result.split(',null,"en",null,null,')[0].replace('[[', '').replace(']]', ']')[1:]
#print('result_all:' + result_all)
output_cn = ''
#解析中文字段并拼接
list = result_all.split('],[')
for i in range(len(list)-1):
end = list[i].find("\",")
tmp_buf = list[i][1:end]
output_cn = output_cn + tmp_buf
return output_cn
def translate_normal(content, language):
js = Py4Js()
tk = js.getTk(content)
#print('english:' + content)
cn_buf = translate_core(content,tk, language)
#print('Chinese:' + cn_buf)
return cn_buf
def translate_cn(content, language):
LEN_LIMIT = 4891
all_len = len(content)
print('en:' + content)
if all_len > LEN_LIMIT:
content_cn = ''
while True:
content_limit = content[0:LEN_LIMIT]
limit_end = find_last(content_limit, '.') + 1
#print('limit_end:' + str(limit_end))
if limit_end == 0:
limit_end = find_last(content_limit, ' ') + 1
if limit_end == 0:
limit_end = LEN_LIMIT
content_en = content[0:limit_end]
leave_len = all_len - limit_end
if content_en == '':
break;
#print('content_en:' + content_en)
content_cn = content_cn + translate_normal(content_en, language);
content = content[limit_end:]
return content_cn
else:
return translate_normal(content, language)
#google api, per 1000 words everyday
def translate_cn_api(content):
translator= Translator(to_lang="zh")
translation = translator.translate(content)
return translation
if __name__ == "__main__":
content = """Beautiful is better than ugly.
Explicit is better than implicit.
Simple is better than complex.
Complex is better than complicated.
Namespaces are one honking great idea -- let's do more of those!"""
#
content = """
IT-Grundschutz M5.131: Absicherung von IP-Protokollen unter Windows Server 2003."""
#content = 'High'
content = """Beautiful is better than ugly.
Explicit is better than implicit.
Simple is better than complex.
Complex is better than complicated.
Namespaces are one honking great idea -- let's do more of those!"""
language = 'en'
test = translate_cn(content.replace('\n', ''), language)
print('ok:' + test)
#content = 'Checks version'
此处实现了德语翻译成中文和英文翻译成中文。
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持python博客。