Python调用有道翻译接口

a121bc

两个接口都发了，网上流传的translate和translate_o的都可以调用，对ip有次数限制，多次会被封，建议使用ip连接池
第一个调用translate接口，使用了ip连接池proxy_pool-master（github上有），需要Linux装SSDB，速度好慢；当然也可以不用，去掉proxies参数即可，只不过会出现验证码，但是速度极佳。
第二个调用translate_o接口，两个接口似乎是独立的，验证码不相关。
业务代码主要是读取文件夹下的所有txt文件根据正则翻译指定内容，再输出到另一个文件夹下（只是为了汉化游戏而已，学Java的第一次写python，写的不好，请大家多多指点），
大部分代码都是网上整理的，salt部分根据网站js进行了更新，应该最近还可用。

[Python] 纯文本查看 复制代码

?

001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123

# -*- coding: UTF-8 -*-import hashlib import random import requests import time import re import os   ################################## def get_proxy():     return requests.get("http://127.0.0.1:5010/get/").json()   def delete_proxy(proxy):     requests.get("http://127.0.0.1:5010/delete/?proxy={}".format(proxy))   # your spider code   def getHtml(s, url, headers, data):     # ....     while True:         retry_count = 2         proxy = get_proxy().get("proxy")         while retry_count > 0:             try:                 # resp = s.post(self.url, headers=self.headers, data=data)                 html = s.post(url, headers=headers,data=data , proxies={"http": "http://{}".format(proxy)}, timeout=1)                 # 使用代{过}{滤}理访问                 return html.json()             except Exception:                                   retry_count -= 1                 print('代{过}{滤}理不通, 剩余机会:'+ str(retry_count))         # 出错5次, 删除代{过}{滤}理池中代{过}{滤}理         delete_proxy(proxy)         print('删除代{过}{滤}理'+proxy)     return None   ##################################   s = requests.Session() m = hashlib.md5() class Dict:     def __init__(self):         self.headers = {             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36',             'Referer': 'http://fanyi.youdao.com/',             'contentType': 'application/x-www-form-urlencoded; charset=UTF-8',             'Cookie': 'OUTFOX_SEARCH_USER_ID=-352392290@116.136.20.84; P_INFO=a121bc; OUTFOX_SEARCH_USER_ID_NCOO=710017829.1902944; JSESSIONID=aaaDa3sqezCDY-snjj91w; SESSION_FROM_COOKIE=unknown; ___rl__test__cookies='+str(int(time.time() * 1000))         }         self.url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&sessionFrom='         self.base_config()       def base_config(self):         """         设置基本的参数，cookie         """         s.get('http://fanyi.youdao.com/')       def translate(self,e):         # i = "With what? I'll be out with my Mom at an expo for the next few days, but..."         i = e         self.headers['Content-Length']=str(233+len(e))         ts = str(int(time.time() * 1000))         salf = ts + str(random.randint(0, 9))         n = 'fanyideskweb' + i + salf + "n%A-rKaT5fb[Gy?;N5@Tj"         m.update(n.encode('utf-8'))         sign = m.hexdigest()         data = {             'i': i,             'from': 'AUTO',             'to': 'AUTO',             'smartresult': 'dict',             'client': 'fanyideskweb',             'salt': salf,             'sign': sign,             'ts': ts,             'bv': '53539dde41bde18f4a71bb075fcf2e66',             'doctype': 'json',             'version': "2.1",             'keyfrom': "fanyi.web",             'action': "FY_BY_REALTlME"         }           ##########################################                   # resp = s.post(self.url, headers=self.headers, data=data)         # rt = resp.json()         rt = getHtml(s, self.url, self.headers, data)           ####################                   arr = []         for c in rt['translateResult'][0]:             arr.append(c['tgt'])         return ''.join(arr)   # dic = Dict() # resp = dic.translate('hello girl') # print(resp)     # 遍历文件夹 def copy(file, file2):     for root, dirs, files in os.walk(file):         # 遍历文件         for f in files:             # time.sleep(random.random())             print(f)             file_path = os.path.join(root, f)             fi = open(file_path,'r',encoding='utf-8')             fi2 =  open(os.path.join(file2, f),'w',encoding='utf-8')             while True:                 line = fi.readline()                 if line.startswith("C_"):                     dic = Dict()                     line = re.sub(r'([\w\s]+)\|([^|]+)([.\s]+)',lambda m: m.group(1)+'|'+dic.translate(m.group(2))+m.group(3),line)                     print('翻译成功：'+ line)                 fi2.write(line)                 if not line:                     fi.close()                     fi2.close()                     break   copy("C:\\Users\\Administrator\\Desktop\\python-test\\dialogues","C:\\Users\\Administrator\\Desktop\\python-test\\def")

第二个

[Python] 纯文本查看 复制代码

?

01 02 03 04 05 06 07 08 09 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83

import json import random import time import hashlib import requests import re import os from urllib import parse from urllib import request     def trans(content):     # 等待用户输入需要翻译的单词     i = content     # 有道翻译的url链接     url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'     # 构造有道的加密参数     client = "fanyideskweb"     ts = int(time.time() * 1000)     salt = str(ts + random.randint(1, 10))     flowerStr = "n%A-rKaT5fb[Gy?;N5@Tj"     sign = hashlib.md5((client + i + salt + flowerStr).encode('utf-8')).hexdigest()     bv = '53539dde41bde18f4a71bb075fcf2e66'     # 创建Form_Data字典，存储请求体     Form_Data = {}     # 需要翻译的文字     Form_Data['i'] = i     # 下面这些都先按照我们之前抓包获取到的数据     Form_Data['from'] = 'AUTO'     Form_Data['to'] = 'AUTO'     Form_Data['smartresult'] = 'dict'     Form_Data['client'] = client     Form_Data['salt'] = salt     Form_Data['sign'] = sign     Form_Data['ts'] = ts     Form_Data['bv'] = bv     Form_Data['doctype'] = 'json'     Form_Data['version'] = '2.1'     Form_Data['keyfrom'] = 'fanyi.web'     Form_Data['action'] = 'FY_BY_REALTIME'     Form_Data['typoResult'] = 'false'     # 对数据进行字节流编码处理     data = parse.urlencode(Form_Data).encode('utf-8')     # 创建Request对象     req = request.Request(url=url, data=data, method='POST')     # 写入header信息     req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36')     req.add_header('cookie', 'OUTFOX_SEARCH_USER_ID=-352392290@116.136.20.84')     req.add_header('Referer', 'http://fanyi.youdao.com/')     # 传入创建好的Request对象     response = request.urlopen(req, timeout=5)     # 读取信息并进行字节流解码     html = response.read().decode('utf-8')     print(html)     # 把返回来的json字符串解析成字典     translate_results = json.loads(html)     # 打印翻译结果     translate_result = translate_results["translateResult"][0][0]['tgt']     print("翻译的结果是：%s" % translate_result)     return translate_result   trans('Hey, Mrs. Juliana! Yeah, like a baby. What are you up to?')   def copy(file, file2):     for root, dirs, files in os.walk(file):         # 遍历文件         for f in files:             time.sleep(random.random())             file_path = os.path.join(root, f)             fi = open(file_path,'r',encoding='utf-8')             fi2 =  open(os.path.join(file2, f),'w',encoding='utf-8')             while True:                 line = fi.readline()                 if line.startswith("C_"):                     line = re.sub(r'([\w\s]+)\|([^|]+)([.\s]+)',lambda m: m.group(1)+'|'+trans(m.group(2))+m.group(3),line)                 fi2.write(line)                 if not line:                     fi.close()                     fi2.close()                     print(f)                     break   # copy("C:\\Users\\Administrator\\Desktop\\python-test\\dialogues","C:\\Users\\Administrator\\Desktop\\python-test\\def")

goldli

支持了。

HuanInJa

https://github.com/crud-boy/py-reptile-collection/tree/master/%E8%B0%B7%E6%AD%8C%E7%BF%BB%E8%AF%91

这里有个谷歌翻译，无ip次数限制，就是限制文字个数5000

a121bc

HuanInJa 发表于 2019-10-2 20:13
https://github.com/crud-boy/py-reptile-collection/tree/master/%E8%B0%B7%E6%AD%8C%E7%BF%BB%E8%AF%91
...

这个很棒，但是和有道一样，翻译的都不太好，有百度的吗，大神？

mikeee

a121bc 发表于 2019-10-3 09:29
这个很棒，但是和有道一样，翻译的都不太好，有百度的吗，大神？

百度、搜狗、谷歌、有道、qq、小牛任君选择 https://github.com/ffreemt

cj13888

学习借鉴一下，谢谢分享