Python实现翻译脚本

1.调用谷歌翻译

import re
import html
from urllib import parse
import requests

GOOGLE_TRANSLATE_URL = 'http://translate.google.cn/m?q=%s&tl=%s&sl=%s'

def translate(text, to_language="auto", text_language="auto"):

    text = parse.quote(text)
    url = GOOGLE_TRANSLATE_URL % (text,to_language,text_language)
    response = requests.get(url)
    data = response.text
    expr = r'(?s)class="(?:t0|result-container)">(.*?)<'
    result = re.findall(expr, data)
    if (len(result) == 0):
        return ""

    return html.unescape(result[0])

print(translate("你吃饭了么?", "en","zh-CN")) #汉语转英语
print(translate("你吃饭了么？", "ja","zh-CN")) #汉语转日语
print(translate("about your situation", "zh-CN","en")) #英语转汉语

2,爬虫类翻译 

import hmac
import base64
import time
import uuid
import requests


class TextTranslate:

    def __init__(self, locale="zh-CN", source="zh-CN", target="ko"):
        """
        初始化一个翻译对象
        :param locale: 所在地区
        :param source: 原文字类型 en 英文 ko 韩文 zh-CN 中文
        :param target: 要翻译成什么文字 en 英文 ko 韩文 zh-CN 中文
        """
        self.locale = locale
        self.source = source
        self.target = target
        self.url = "https://papago.naver.com/apis/n2mt/translate"
        self.key = "v1.6.4_4b23b99383"

    @property
    def __device_id(self):
        device_id = str(uuid.uuid4())
        return device_id

    @property
    def __timestamp(self):
        timestamp = str(int(time.time() * 1000))
        return timestamp

    def __has(self, device_id, timestamp):
        hmacs = device_id + "\n" + self.url.split("?")[0] + "\n" + timestamp
        hmac_obj = hmac.new(self.key.encode("utf8"))
        hmac_obj.update(hmacs.encode("utf8"))
        hmacb = hmac_obj.digest()
        md5b64 = base64.b64encode(hmacb).decode("utf8")
        return md5b64

    def __get_headers(self, timestamp, device_id):
        headers = {
            "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
            "timestamp": timestamp,
            "authorization": "PPG " + device_id + ":" + self.__has(device_id, timestamp),
        }

        return headers

    def __get_data(self, device_id, text):
        data = {
            "deviceId": device_id,
            "locale": self.locale,
            "dict": False,
            "dictDisplay": 30,
            "honorific": False,
            "instant": True,
            "paging": False,
            "source": self.source,
            "target": self.target,
            "text": text
        }

        return data

    def translate(self, text):
        device_id = self.__device_id
        timestamp = self.__timestamp
        headers = self.__get_headers(timestamp, device_id)
        data = self.__get_data(device_id, text)
        res = requests.post(url=self.url, headers=headers, data=data)
        return res.json()



if __name__ == '__main__':
    translate = TextTranslate(source="en", target="zh-CN")
    print(translate.translate("hello")["translatedText"])

 3.Python调用有道翻译的脚本

import urllib.request
import urllib.parse
import json
 
def get_data(words):
    data = {}
    data["type"] = "AUTO"
    data["i"] = words
    data["doctype"] = "json"
    data["xmlVersion"] = "1.8"
    data["keyfrom:fanyi"] = "web"
    data["ue"] = "UTF-8"
    data["action"] = "FY_BY_CLICKBUTTON"
    data["typoResult"] = "true"
    data = urllib.parse.urlencode(data).encode('utf-8')
    return data
 
def url_open(url, data):
    req = urllib.request.Request(url, data)
    req.add_header("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36")
    response = urllib.request.urlopen(req)
    html = response.read()
    html = html.decode("utf-8")
    return html
 
def get_json_data(html):
    result = json.loads(html)
    result = result['translateResult']
    result = result[0][0]['tgt']
    return result
 
def main():
    words = input("please input words: ")
    url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=dict.top"
 
    data = get_data(words)
    html = url_open(url, data)
    result = get_json_data(html)
    print("The result: %s" % result)
 
if __name__ == "__main__":
    while True:
        main()