1、翻译模块、api使用分析
1、translate库：使用简单，但是有次数限制，翻译的准确性中等；
2、百度api（推荐使用）： 代码简单，有模块，但是需要注册，获取key值，翻译的准确性中下；
3、chrome翻译api：代码复杂，次数限制， 但是翻译的准确性较高；
4、有道翻译：代码复杂，次数限制，准确性中等；
2、使用方式：
- translate库：
from translate import Translator
#在任何两种语言之间，中文翻译成英文
translator=Translator(from_lang="chinese",to_lang="english")
translation = translator.translate("床前明月光，疑是地上霜;举头望明月,低头思故乡")
print(translation)
2、 百度api：
需要先去百度翻译进行注册，获取appid、secretkey值，记得填写可访问的服务器ip
# 百度通用翻译API,不包含词典、tts语音合成等资源，如有相关需求请联系translate_api@baidu.com
# coding=utf-8
import http.client
import hashlib
import urllib
import random
import json
def trans_lang(q):
trans_result = q
# 百度appid和密钥需要通过注册百度【翻译开放平台】账号后获得
appid = 'xxx' # 填写你的appid
secretKey = 'xxx' # 填写你的密钥
httpClient = None
myurl = '/api/trans/vip/translate' # 通用翻译API HTTP地址
fromLang = 'en' # 原文语种
toLang = 'zh' # 译文语种
salt = random.randint(32768, 65536)
# 手动录入翻译内容，q存放
sign = appid + q + str(salt) + secretKey
sign = hashlib.md5(sign.encode()).hexdigest()
myurl = myurl + '?appid=' + appid + '&q=' + urllib.parse.quote(q) + '&from=' + fromLang + \
'&to=' + toLang + '&salt=' + str(salt) + '&sign=' + sign
# 建立会话，返回结果
try:
httpClient = http.client.HTTPConnection('api.fanyi.baidu.com')
httpClient.request('GET', myurl)
# response是HTTPResponse对象
response = httpClient.getresponse()
result_all = response.read().decode("utf-8")
result = json.loads(result_all)
trans_result = result['trans_result'][0]['dst']
except Exception as e:
print(e)
finally:
if httpClient:
httpClient.close()
return trans_result
if __name__ == '__main__':
a = 'Customer Not Available & Mobile not reachable Customer Not Available & Mobile not reachable by SR: ANIL KUMAR (170435) (117510), MobileNo: 9996366909'
print(trans_lang(a))
3、chrome翻译api：
import requests
import re
import json
import time
class GoogleTranslator ():
_host = 'translate.google.cn'
_headers = {
'Host': _host,
'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Mobile Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
'Accept-Encoding': 'gzip, deflate, br',
'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
'Referer': 'https://' + _host,
'Connection': 'keep-alive',
'Cache-Control': 'max-age=0'
}
_language = {
'afrikaans': 'af',
'arabic': 'ar',
'belarusian': 'be',
'bulgarian': 'bg',
'catalan': 'ca',
'czech': 'cs',
'welsh': 'cy',
'danish': 'da',
'german': 'de',
'greek': 'el',
'english': 'en',
'esperanto': 'eo',
'spanish': 'es',
'estonian': 'et',
'persian': 'fa',
'finnish': 'fi',
'french': 'fr',
'irish': 'ga',
'galician': 'gl',
'hindi': 'hi',
'croatian': 'hr',
'hungarian': 'hu',
'indonesian': 'id',
'icelandic': 'is',
'italian': 'it',
'hebrew': 'iw',
'japanese': 'ja',
'korean': 'ko',
'latin': 'la',
'lithuanian': 'lt',
'latvian': 'lv',
'macedonian': 'mk',
'malay': 'ms',
'maltese': 'mt',
'dutch': 'nl',
'norwegian': 'no',
'polish': 'pl',
'portuguese': 'pt',
'romanian': 'ro',
'russian': 'ru',
'slovak': 'sk',
'slovenian': 'sl',
'albanian': 'sq',
'serbian': 'sr',
'swedish': 'sv',
'swahili': 'sw',
'thai': 'th',
'filipino': 'tl',
'turkish': 'tr',
'ukrainian': 'uk',
'vietnamese': 'vi',
'yiddish': 'yi',
'chinese_simplified': 'zh-CN',
'chinese_traditional': 'zh-TW',
'auto': 'auto'
}
_url = 'https://' + _host + '/translate_a/single'
_params = {
'client': 'webapp',
'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',
'otf': '1',
'ssel': '0',
'tsel': '0',
'kc': '1'
}
__cookies = None
__googleTokenKey = '376032.257956'
__googleTokenKeyUpdataTime = 600.0
__googleTokenKeyRetireTime = time.time() + 600.0
def __init__(self, src = 'en', dest = 'zh-CN', tkkUpdataTime = 600.0):
if src not in self._language and src not in self._language.values():
src = 'auto'
if dest not in self._language and dest not in self._language.values():
dest = 'auto'
self._params['sl'] = src
self._params['tl'] = dest
self.googleTokenKeyUpdataTime = tkkUpdataTime
self.__updateGoogleTokenKey()
def __updateGoogleTokenKey(self):
self.__googleTokenKey = self.__getGoogleTokenKey()
self.__googleTokenKeyRetireTime = time.time() + self.__googleTokenKeyUpdataTime
def __getGoogleTokenKey(self):
"""Get the Google TKK from https://translate.google.cn"""
# TKK example: '435075.3634891900'
result = ''
try:
res = requests.get('https://' + self._host, timeout = 3)
res.raise_for_status()
self.__cookies = res.cookies
result = re.search(r'tkk\:\'(\d+\.\d+)?\'', res.text).group(1)
except requests.exceptions.ReadTimeout as ex:
print('ERROR: ' + str(ex))
time.sleep(1)
return result
def __getGoogleToken(self, a, TKK):
"""Calculate Google tk from TKK """
# https://www.cnblogs.com/chicsky/p/7443830.html
# if text = 'Tablet Developer' and TKK = '435102.3120524463', then tk = '315066.159012'
def RL(a, b):
for d in range(0, len(b)-2, 3):
c = b[d + 2]
c = ord(c[0]) - 87 if 'a' <= c else int(c)
c = a >> c if '+' == b[d + 1] else a << c
a = a + c & 4294967295 if '+' == b[d] else a ^ c
return a
g = []
f = 0
while f < len(a):
c = ord(a[f])
if 128 > c:
g.append(c)
else:
if 2048 > c:
g.append((c >> 6) | 192)
else:
if (55296 == (c & 64512)) and (f + 1 < len(a)) and (56320 == (ord(a[f+1]) & 64512)):
f += 1
c = 65536 + ((c & 1023) << 10) + (ord(a[f]) & 1023)
g.append((c >> 18) | 240)
g.append((c >> 12) & 63 | 128)
else:
g.append((c >> 12) | 224)
g.append((c >> 6) & 63 | 128)
g.append((c & 63) | 128)
f += 1
e = TKK.split('.')
h = int(e[0]) or 0
t = h
for item in g:
t += item
t = RL(t, '+-a^+6')
t = RL(t, '+-3^+b+-f')
t ^= int(e[1]) or 0
if 0 > t:
t = (t & 2147483647) + 2147483648
result = t % 1000000
return str(result) + '.' + str(result ^ h)
def translate(self, text):
if time.time() > self.__googleTokenKeyRetireTime:
self.__updateGoogleTokenKey()
data = {'q': text}
self._params['tk'] = self.__getGoogleToken(text, self.__googleTokenKey)
result = ''
try:
res = requests.post(self._url,
headers = self._headers,
cookies = self.__cookies,
data = data,
params = self._params,
timeout = 6)
res.raise_for_status()
jsonText = res.text
if len(jsonText)>0:
jsonResult = json.loads(jsonText)
if len(jsonResult[0])>0:
for item in jsonResult[0]:
result += item[0]
return result
except Exception as ex:
print('ERROR: ' + str(ex))
return ''
import time
from GoogleTranslator import GoogleTranslator
def readFile(fileName):
with open(fileName, 'r') as f:
paragraph = ''
for line in f:
if line[0]!='\n':
paragraph += line.strip('\n')
else:
if len(paragraph)>0:
yield paragraph
paragraph = ''
if len(paragraph)>0:
yield paragraph
4、有道翻译api：
from urllib import request, parse
import json
from faker import Faker
class trans(object):
def __init__(self):
self.url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule'
def tran(self, text):
index = text.find("http")
text = text[:index]
text = text.replace('\n', '').replace('#', '').replace('RT ', '').replace(':', '')
ua = Faker().user_agent()
headers = {
'User-Agent': ua,
'Host': 'fanyi.youdao.com',
'Origin': 'http://fanyi.youdao.com',
'Referer': 'http://fanyi.youdao.com/',
}
# 表单数据
from_data = {
'i': text,
'from': 'UTO',
'to': 'UTO',
'smartresult': 'dict',
'client': 'fanyideskweb',
'doctype': 'json',
'version': '2.1',
'keyfrom': 'fanyi.web',
'action': 'FY_BY_REALTlME'
}
from_data = parse.urlencode(from_data).encode('utf-8')
req = request.Request(self.url, from_data, headers)
res = request.urlopen(req).read().decode("utf-8")
target = json.loads(res)
try:
result = target['translateResult'][0][0]['tgt']
except:
result = "Translate failed"
return result
if __name__ == '__main__':
Obj = trans()
for i in range(1000):
print(i)
text = "Egypt disinfecting streets in Cairo to combat the spread of Coronavirus.\n#COVID19Africa #CoronavirusPandemic\n https://t…"
res = Obj.tran(text)
print(res)
