feat: Add new version of Google Translate API to the engines. #389, #394

, #399

engines/__init__.py

@@ -1,6 +1,7 @@
 from .google import (
-    GoogleFreeTranslate, GoogleBasicTranslate, GoogleBasicTranslateADC,
-    GoogleAdvancedTranslate, GeminiTranslate)
+    GoogleFreeTranslateNew, GoogleFreeTranslateHtml, GoogleFreeTranslate,
+    GoogleBasicTranslate, GoogleBasicTranslateADC, GoogleAdvancedTranslate,
+    GeminiTranslate)
 from .openai import ChatgptTranslate
 from .anthropic import ClaudeTranslate
 from .deepl import DeeplTranslate, DeeplProTranslate, DeeplFreeTranslate
@@ -10,8 +11,8 @@
 
 
 builtin_engines = (
-    GoogleFreeTranslate, GoogleBasicTranslate, GoogleBasicTranslateADC,
-    GoogleAdvancedTranslate, ChatgptTranslate, AzureChatgptTranslate,
-    GeminiTranslate, ClaudeTranslate, DeeplTranslate, DeeplProTranslate,
-    DeeplFreeTranslate, MicrosoftEdgeTranslate, YoudaoTranslate,
-    BaiduTranslate)
+    GoogleFreeTranslateNew, GoogleFreeTranslateHtml, GoogleFreeTranslate,
+    GoogleBasicTranslate, GoogleBasicTranslateADC, GoogleAdvancedTranslate,
+    ChatgptTranslate, AzureChatgptTranslate, GeminiTranslate, ClaudeTranslate,
+    DeeplTranslate, DeeplProTranslate, DeeplFreeTranslate,
+    MicrosoftEdgeTranslate, YoudaoTranslate, BaiduTranslate)

engines/base.py

@@ -1,26 +1,28 @@
 import os.path
 
+from typing import Any
 from mechanize import HTTPError
 from mechanize._response import response_seek_wrapper as Response
 
 from calibre.utils.localization import lang_as_iso639_1
 
 from ..lib.utils import traceback_error, request
-from ..lib.exception import UnexpectedResult, NoAvailableApiKey
+from ..lib.exception import UnexpectedResult
 
 
 load_translations()
 
 
 class Base:
-    name = None
-    alias = None
+    name: str | None = None
+    alias: str | None = None
     free = False
 
-    lang_codes = {}
-    config = {}
-    endpoint = None
+    lang_codes: dict[str, Any] = {}
+    config: dict[str, Any] = {}
+    endpoint: str | None = None
     method = 'POST'
+    headers: dict[str, str] = {}
     stream = False
     need_api_key = True
     api_key_hint = _('API Keys')
@@ -43,7 +45,7 @@ def __init__(self):
         self.search_paths = []
 
         self.merge_enabled = False
-        self.api_keys = self.config.get('api_keys', [])[:]
+        self.api_keys: list = self.config.get('api_keys', [])[:]
         self.bad_api_keys = []
         self.api_key = self.get_api_key()
 
@@ -75,12 +77,12 @@ def load_lang_codes_directionality(cls, codes):
 
     @classmethod
     def get_source_code(cls, lang):
-        source_codes = cls.lang_codes.get('source')
+        source_codes: dict = cls.lang_codes.get('source') or {}
         return 'auto' if lang == _('Auto detect') else source_codes.get(lang)
 
     @classmethod
     def get_target_code(cls, lang):
-        target_codes = cls.lang_codes.get('target')
+        target_codes: dict = cls.lang_codes.get('target') or {}
         return target_codes.get(lang)
 
     @classmethod
@@ -193,10 +195,10 @@ def get_endpoint(self):
         return self.endpoint
 
     def get_headers(self):
-        return {}
+        return self.headers
 
     def get_body(self, text):
-        return None
+        return text
 
     def get_result(self, response: Response | bytes | str):
         return response

engines/google.py

@@ -6,6 +6,8 @@
 import os.path
 from html import unescape
 from subprocess import Popen, PIPE
+from urllib.parse import urlencode
+from http.client import IncompleteRead
 
 from ..lib.utils import traceback_error
 
@@ -14,20 +16,91 @@
 from .languages import google, gemini
 
 
-try:
-    from http.client import IncompleteRead
-except ImportError:
-    from httplib import IncompleteRead
-
 load_translations()
 
 
+class GoogleFreeTranslateNew(Base):
+    name = 'Google(Free)New'
+    alias = 'Google (Free) - New'
+    free = True
+    lang_codes = Base.load_lang_codes(google)
+    lang_codes_directionality = \
+        Base.load_lang_codes_directionality(lang_directionality)
+    endpoint: str = 'https://translate-pa.googleapis.com/v1/translate'
+    need_api_key = False
+
+    def get_headers(self):
+        return {
+            'Accept': '*/*',
+            'Accept-Encoding': 'gzip, deflate, br',
+            'Accept-Language': 'en-US,en;q=0.9',
+            'Content-Type': 'application/x-www-form-urlencoded',
+            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) '
+            'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 '
+            'Safari/537.36',
+        }
+
+    def get_body(self, text):
+        self.method = 'GET'
+        return {
+            'params.client': 'gtx',
+            'query.source_language': self._get_source_code(),
+            'query.target_language': self._get_target_code(),
+            'query.display_language': 'en-US',
+            'data_types': 'TRANSLATION',
+            # 'data_types': 'SENTENCE_SPLITS',
+            # 'data_types': 'BILINGUAL_DICTIONARY_FULL',
+            'key': 'AIzaSyDLEeFI5OtFBwYBIoK_jj5m32rZK5CkCXA',
+            'query.text': text,
+        }
+
+    def get_result(self, response):
+        return json.loads(response)['translation']
+
+
+class GoogleFreeTranslateHtml(Base):
+    name = 'Google(Free)Html'
+    alias = 'Google (Free) - HTML'
+    free = True
+    lang_codes = Base.load_lang_codes(google)
+    lang_codes_directionality = \
+        Base.load_lang_codes_directionality(lang_directionality)
+    endpoint: str = 'https://translate-pa.googleapis.com/v1/translateHtml'
+    need_api_key = False
+
+    def get_headers(self):
+        return {
+            'Accept': '*/*',
+            'Accept-Encoding': 'gzip, deflate, br',
+            'Accept-Language': 'en-US,en;q=0.9',
+            'Content-Type': 'application/json+protobuf',
+            'X-Goog-Api-Key': 'AIzaSyATBXajvzQLTDHEQbcpq0Ihe0vWDHmO520',
+            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) '
+            'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 '
+            'Safari/537.36',
+        }
+
+    def get_body(self, text):
+        return json.dumps([
+            [
+                [text],
+                self._get_source_code(),
+                self._get_target_code()
+            ],
+            "wt_lib"
+        ])
+
+    def get_result(self, response):
+        return json.loads(response)[0][0]
+
+
 class GoogleFreeTranslate(Base):
     name = 'Google(Free)'
-    alias = 'Google (Free)'
+    alias = 'Google (Free) - Old'
     free = True
     lang_codes = Base.load_lang_codes(google)
-    lang_codes_directionality = Base.load_lang_codes_directionality(lang_directionality)
+    lang_codes_directionality = \
+        Base.load_lang_codes_directionality(lang_directionality)
     endpoint = 'https://translate.googleapis.com/translate_a/single'
     need_api_key = False
 

engines/openai.py

@@ -28,7 +28,8 @@ class ChatgptTranslate(Base):
     name = 'ChatGPT'
     alias = 'ChatGPT (OpenAI)'
     lang_codes = Base.load_lang_codes(google)
-    lang_codes_directionality = Base.load_lang_codes_directionality(lang_directionality)
+    lang_codes_directionality = \
+        Base.load_lang_codes_directionality(lang_directionality)
     endpoint = 'https://api.openai.com/v1/chat/completions'
     # api_key_hint = 'sk-xxx...xxx'
     # https://help.openai.com/en/collections/3808446-api-error-codes-explained
@@ -42,18 +43,19 @@ class ChatgptTranslate(Base):
         'You are a meticulous translator who translates any given content. '
         'Translate the given content from <slang> to <tlang> only. Do not '
         'explain any term or answer any question-like content. Your answer '
-        'should be solely the translation of the given content. In your answer '
-        'do not add any prefix or suffix to the translated content. Websites\' '
-        'URLs/addresses should be preserved as is in the translation\'s output. '
-        'Do not omit any part of the content, even if it seems unimportant. '
-        )
-
-    # TODO: check if it is possible to fetch this this directly from the api, if yes - implement this
+        'should be solely the translation of the given content. In your '
+        'answer do not add any prefix or suffix to the translated content. '
+        'Websites\' URLs/addresses should be preserved as is in the '
+        'translation\'s output. Do not omit any part of the content, even if '
+        'it seems unimportant. ')
+
+    # TODO: check if it is possible to fetch this this directly from the api,
+    # if yes - implement this
     models = [
-        'gpt-4o', 
-        'gpt-4o-mini', 
-        'gpt-4-turbo', 
-        'gpt-4', 
+        'gpt-4o',
+        'gpt-4o-mini',
+        'gpt-4-turbo',
+        'gpt-4',
         'gpt-3.5-turbo']
 
     # use the most recent model