调用有道翻译接口进行翻译

  1 '''
  2 i: 你好
  3 from: AUTO
  4 to: AUTO
  5 smartresult: dict
  6 client: fanyideskweb
  7 salt: 16643765479061    //毫秒级别的时间戳后面加上个0-9之间的随机数,js代码：r + parseInt(10 * Math.random(), 10);这里的r表示时间戳字符串
  8 sign: 1d69ce8f7c6258243e573e31e29e0012    //签名，下面找到了
  9 lts: 1664376547906        //毫秒级别的时间戳
 10 bv: 42c8b36dd7d61c619e7b1dc11e44d870    //同设备相同，使用md5加密的（方法是：md5(User-Agent)==>md5（"5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.53"）
 11 doctype: json
 12 version: 2.1
 13 keyfrom: fanyi.web
 14 action: FY_BY_REALTlME
 15 
 16 /*
 17 解密出来了：sign的计算如下
 18 define("newweb/common/service", ["./utils", "./md5", "./jquery-1.7"], function(e, t) {
 19     var n = e("./jquery-1.7");
 20     e("./utils");
 21     e("./md5");
 22     var r = function(e) {
 23         var t = n.md5(navigator.appVersion)
 24           , r = "" + (new Date).getTime()
 25           , i = r + parseInt(10 * Math.random(), 10);
 26         return {
 27             ts: r,
 28             bv: t,
 29             salt: i,
 30             sign: n.md5("fanyideskweb" + e + i + "Ygy_4c=r#e#4EX^NUGUc5")    //在这里，e是要翻译的内容，i是毫秒级别的时间戳后面加上个0-9之间的随机数；后面这串字符串估计是服务器那边随机生成的，应该会变化。每次抓取的时候，可以查看下js代码
 31         }
 32     };
 33     
 34     总体来说，data数据由函数“generateSaltSign”计算出来
 35 */
 36 '''
 37 
 38 '''
 39 获取翻译结果
 40 The_translated_string：被翻译的字符串
 41 由于翻译是以行为单位，所以一行一个结果，函数将解析The_translated_string参数，并以字符串形式返回所有翻译结果
 42 '''
 43 def youdao_translate(The_translated_string:str):
 44     if(The_translated_string == ""):
 45         return {"":""}
 46     url = r'https://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'
 47 
 48     User_Agent = "5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36 Edg/106.0.1370.37"
 49     header = {
 50         "Accept": "application/json, text/javascript, */*; q=0.01",
 51         "Accept-Encoding": "gzip, deflate, br",
 52         "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
 53         "Connection": "keep-alive",
 54         #"Content-Length": "307",
 55         "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
 56         "Cookie":"[email protected]; OUTFOX_SEARCH_USER_ID_NCOO=775555146.507473; JSESSIONID=aaaQ2GYK5N-ozb24rKNcy; SESSION_FROM_COOKIE=unknown; DICT_UGC=be3af0da19b5c5e6aa4e17bd8d90b28a|; JSESSIONID=abcPzon0RcZqc7GltuAgy; ___rl__test__cookies=1665366515354",
 57         "Host": "fanyi.youdao.com",
 58         "Origin": "https://fanyi.youdao.com",
 59         "Referer": "https://fanyi.youdao.com/",
 60         "sec-ch-ua": """\"Google Chrome";v="105", "Not)A;Brand";v="8", "Chromium";v="105"\"""",
 61         "sec-ch-ua-mobile": "?0",
 62         "sec-ch-ua-platform": "Windows",
 63         "Sec-Fetch-Dest": "empty",
 64         "Sec-Fetch-Mode": "cors",
 65         "Sec-Fetch-Site": "same-origin",
 66         "User-Agent": User_Agent,
 67         "X-Requested-With": "XMLHttpRequest"
 68     }
 69 
 70     #The_translated_string=input("输入你要翻译的中文信息：\n")  # 被翻译的字符串
 71     timestamp = str(round(time.time()*1000))  # 毫秒级别的时间戳
 72     salt = timestamp + str(random.randint(0, 9))  # 毫秒级别的时间戳后面加上个0-9之间的随机数
 73     sign_str = "fanyideskweb" + The_translated_string + salt + "Ygy_4c=r#e#4EX^NUGUc5"  # 构造签名字符串
 74     # 签名，算法：sign: n.md5("fanyideskweb" + e + i + "Ygy_4c=r#e#4EX^NUGUc5")    //在这里，后面这串字符串估计是服务器那边随机生成的，应该会变化。每次抓取的时候，可以查看下js代码
 75     sign = hashlib.md5(str.encode(sign_str)).hexdigest()
 76     # 同设备相同，使用md5加密的（方法是：md5(User-Agent)==>md5（"5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.53"）
 77     bv = hashlib.md5(str.encode(User_Agent)).hexdigest()
 78     cookies = {
 79         "OUTFOX_SEARCH_USER_ID": "[email protected]",
 80         "OUTFOX_SEARCH_USER_ID_NCOO": "775555146.507473",
 81         "JSESSIONID": "aaaQ2GYK5N-ozb24rKNcy",
 82         "SESSION_FROM_COOKIE": "unknown",
 83         "DICT_UGC": "be3af0da19b5c5e6aa4e17bd8d90b28a|",
 84         "JSESSIONID": "abcPzon0RcZqc7GltuAgy",
 85         "___rl__test__cookies": "1665366515354"
 86     }
 87     data = {
 88         "i": The_translated_string,
 89         "from": "AUTO",
 90         "to": "AUTO",
 91         # 一般来说，是从中文翻译为英文
 92         # "from": "zh-CHS",
 93         # "to": "en",
 94         "smartresult": "dict",
 95         "client": "fanyideskweb",
 96         "salt": salt,
 97         "sign": sign,
 98         "lts": timestamp,
 99         "bv": bv,
100         "doctype": "json",
101         "version": "2.1",
102         "keyfrom": "fanyi.web",
103         "action": "FY_BY_CLICKBUTTION"
104     }
105     data = urlencode(data);
106     result = requests.post(url, data=data, cookies=cookies,headers=header)
107     json_result = json.loads(result.text);
108     #lines = The_translated_string.splitlines();     #按照行边界拆分
109     if(not json_result["errorCode"]):
110         ret_list="";
111         for i in json_result["translateResult"]:    #如果源字符串就是存在段落的，则这里就会根据其来分结果
112             for j in i:                             #翻译服务器认为该分段的，这里就会再次存在子项
113                 ret_list+=j['tgt']
114                 ret_list+="\n"
115             #ret_list[json_result["translateResult"][i][0]["src"]]=json_result["translateResult"][i][0]["tgt"]
116         return ret_list;
117     else:
118         return "errorCode = "+str(json_result["errorCode"]);