Google Translation - Add User-Agent Fix #289

deep_translator/__init__.py

@@ -7,14 +7,14 @@
 from deep_translator.deepl import DeeplTranslator
 from deep_translator.detection import batch_detection, single_detection
 from deep_translator.google import GoogleTranslator
+from deep_translator.googleweb import GoogleTranslatorWeb
 from deep_translator.libre import LibreTranslator
 from deep_translator.linguee import LingueeTranslator
 from deep_translator.microsoft import MicrosoftTranslator
 from deep_translator.mymemory import MyMemoryTranslator
 from deep_translator.papago import PapagoTranslator
 from deep_translator.pons import PonsTranslator
 from deep_translator.qcri import QcriTranslator
-from deep_translator.tencent import TencentTranslator
 from deep_translator.yandex import YandexTranslator
 
 __author__ = """Nidhal Baccouri"""
@@ -23,6 +23,7 @@
 
 __all__ = [
     "GoogleTranslator",
+    "GoogleTranslatorWeb",
     "PonsTranslator",
     "LingueeTranslator",
     "MyMemoryTranslator",
@@ -33,7 +34,6 @@
     "LibreTranslator",
     "PapagoTranslator",
     "ChatGptTranslator",
-    "TencentTranslator",
     "BaiduTranslator",
     "single_detection",
     "batch_detection",

deep_translator/google.py

@@ -36,6 +36,7 @@ def __init__(
         @param target: target language to translate to
         """
         self.proxies = proxies
+        self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"}
         super().__init__(
             base_url=BASE_URLS.get("GOOGLE_TRANSLATE"),
             source=source,
@@ -65,7 +66,7 @@ def translate(self, text: str, **kwargs) -> str:
                 self._url_params[self.payload_key] = text
 
             response = requests.get(
-                self._base_url, params=self._url_params, proxies=self.proxies
+                self._base_url, params=self._url_params, proxies=self.proxies, headers=self.headers
             )
             if response.status_code == 429:
                 raise TooManyRequests()

deep_translator/googleweb.py

@@ -0,0 +1,70 @@
+# Requirement: pip3 install setuptools selenium undetected-chromedriver
+# xpz3
+
+import undetected_chromedriver as uc
+import urllib.parse
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from time import sleep
+
+class GoogleTranslatorWeb:
+    """
+    Google Translate scraper using headless Chrome by directly parsing the translation page.
+    """
+
+    def __init__(self, headless: bool = True, driver_wait: int = 3):
+        """
+        Initialize the translator.
+        :param headless: Run Chrome in headless mode.
+        """
+        self.headless = headless
+        self.driver_wait = driver_wait
+        options = uc.ChromeOptions()
+        if self.headless:
+            options.headless = True
+            options.add_argument("--headless=new")
+        options.add_argument("--disable-blink-features=AutomationControlled")
+        options.add_argument("--window-size=1200,800")
+
+        self.driver = uc.Chrome(options=options)
+        self.wait = WebDriverWait(self.driver, self.driver_wait)
+
+    def translate(self, text: str, source_lang: str = "auto", target_lang: str = "en") -> str:
+        """
+        Translate text using Google Translate by directly loading the translation page.
+        :param text: The text to translate.
+        :param source_lang: Source language (default: auto-detect).
+        :param target_lang: Target language.
+        :return: Full translated text.
+        """
+        if not text.strip():
+            return ""
+
+        encoded_text = urllib.parse.quote(text)
+
+        translate_url = f"https://translate.google.com/?hl=en&q={encoded_text}&sl={source_lang}&tl={target_lang}&text={encoded_text}&op=translate"
+
+        self.driver.get(translate_url)
+        #sleep(3)
+
+        try:
+            output_box_xpath = '//span[@class="ryNqvb"]'
+            translated_elements = self.wait.until(EC.presence_of_all_elements_located((By.XPATH, output_box_xpath)))
+
+            translated_text = " ".join([elem.text.strip() for elem in translated_elements if elem.text.strip()])
+            return translated_text if translated_text else "Translation not found"
+
+        except Exception:
+            return "Translation not found"
+
+
+    def close(self):
+        """Properly close the Selenium browser session."""
+        if self.driver:
+            try:
+                self.driver.quit()
+                del self.driver
+                self.driver = None
+            except Exception as e:
+                print(f"Warning: Issue while closing the browser: {e}")