Merge pull request #219 from hanlhan/feature/baidu
Browse files- deep_translator/__init__.py +2 -0
- deep_translator/baidu.py +120 -0
- deep_translator/constants.py +34 -0
- deep_translator/exceptions.py +13 -0
- docs/README.rst +60 -0
- tests/test_baidu.py +65 -0
deep_translator/__init__.py
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
|
3 |
__copyright__ = "Copyright (C) 2020 Nidhal Baccouri"
|
4 |
|
|
|
5 |
from deep_translator.chatgpt import ChatGptTranslator
|
6 |
from deep_translator.deepl import DeeplTranslator
|
7 |
from deep_translator.detection import batch_detection, single_detection
|
@@ -31,6 +32,7 @@ __all__ = [
|
|
31 |
"LibreTranslator",
|
32 |
"PapagoTranslator",
|
33 |
"ChatGptTranslator",
|
|
|
34 |
"single_detection",
|
35 |
"batch_detection",
|
36 |
]
|
|
|
2 |
|
3 |
__copyright__ = "Copyright (C) 2020 Nidhal Baccouri"
|
4 |
|
5 |
+
from deep_translator.baidu import BaiduTranslator
|
6 |
from deep_translator.chatgpt import ChatGptTranslator
|
7 |
from deep_translator.deepl import DeeplTranslator
|
8 |
from deep_translator.detection import batch_detection, single_detection
|
|
|
32 |
"LibreTranslator",
|
33 |
"PapagoTranslator",
|
34 |
"ChatGptTranslator",
|
35 |
+
"BaiduTranslator",
|
36 |
"single_detection",
|
37 |
"batch_detection",
|
38 |
]
|
deep_translator/baidu.py
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"""
|
2 |
+
baidu translator API
|
3 |
+
"""
|
4 |
+
|
5 |
+
__copyright__ = "Copyright (C) 2020 Nidhal Baccouri"
|
6 |
+
|
7 |
+
import hashlib
|
8 |
+
import os
|
9 |
+
import random
|
10 |
+
from typing import List, Optional
|
11 |
+
|
12 |
+
import requests
|
13 |
+
|
14 |
+
from deep_translator.base import BaseTranslator
|
15 |
+
from deep_translator.constants import (
|
16 |
+
BAIDU_APPID_ENV_VAR,
|
17 |
+
BAIDU_APPKEY_ENV_VAR,
|
18 |
+
BAIDU_LANGUAGE_TO_CODE,
|
19 |
+
BASE_URLS,
|
20 |
+
)
|
21 |
+
from deep_translator.exceptions import (
|
22 |
+
ApiKeyException,
|
23 |
+
BaiduAPIerror,
|
24 |
+
ServerException,
|
25 |
+
TranslationNotFound,
|
26 |
+
)
|
27 |
+
from deep_translator.validate import is_empty, is_input_valid
|
28 |
+
|
29 |
+
|
30 |
+
class BaiduTranslator(BaseTranslator):
|
31 |
+
"""
|
32 |
+
class that wraps functions, which use the BaiduTranslator translator
|
33 |
+
under the hood to translate word(s)
|
34 |
+
"""
|
35 |
+
|
36 |
+
def __init__(
|
37 |
+
self,
|
38 |
+
source: str = "en",
|
39 |
+
target: str = "zh",
|
40 |
+
appid: Optional[str] = os.getenv(BAIDU_APPID_ENV_VAR, None),
|
41 |
+
appkey: Optional[str] = os.getenv(BAIDU_APPKEY_ENV_VAR, None),
|
42 |
+
**kwargs
|
43 |
+
):
|
44 |
+
"""
|
45 |
+
@param appid: your baidu cloud api appid.
|
46 |
+
Get one here: https://fanyi-api.baidu.com/choose
|
47 |
+
@param appkey: your baidu cloud api appkey.
|
48 |
+
@param source: source language
|
49 |
+
@param target: target language
|
50 |
+
"""
|
51 |
+
if not appid:
|
52 |
+
raise ApiKeyException(env_var=BAIDU_APPID_ENV_VAR)
|
53 |
+
|
54 |
+
if not appkey:
|
55 |
+
raise ApiKeyException(env_var=BAIDU_APPKEY_ENV_VAR)
|
56 |
+
|
57 |
+
self.appid = appid
|
58 |
+
self.appkey = appkey
|
59 |
+
super().__init__(
|
60 |
+
base_url=BASE_URLS.get("BAIDU"),
|
61 |
+
source=source,
|
62 |
+
target=target,
|
63 |
+
languages=BAIDU_LANGUAGE_TO_CODE,
|
64 |
+
**kwargs
|
65 |
+
)
|
66 |
+
|
67 |
+
def translate(self, text: str, **kwargs) -> str:
|
68 |
+
"""
|
69 |
+
@param text: text to translate
|
70 |
+
@return: translated text
|
71 |
+
"""
|
72 |
+
if is_input_valid(text):
|
73 |
+
if self._same_source_target() or is_empty(text):
|
74 |
+
return text
|
75 |
+
|
76 |
+
# Create the request parameters.
|
77 |
+
salt = random.randint(32768, 65536)
|
78 |
+
sign = hashlib.md5(
|
79 |
+
(self.appid + text + str(salt) + self.appkey).encode("utf-8")
|
80 |
+
).hexdigest()
|
81 |
+
headers = {"Content-Type": "application/x-www-form-urlencoded"}
|
82 |
+
payload = {
|
83 |
+
"appid": self.appid,
|
84 |
+
"q": text,
|
85 |
+
"from": self.source,
|
86 |
+
"to": self.target,
|
87 |
+
"salt": salt,
|
88 |
+
"sign": sign,
|
89 |
+
}
|
90 |
+
|
91 |
+
# Do the request and check the connection.
|
92 |
+
try:
|
93 |
+
response = requests.post(
|
94 |
+
self._base_url, params=payload, headers=headers
|
95 |
+
)
|
96 |
+
except ConnectionError:
|
97 |
+
raise ServerException(503)
|
98 |
+
if response.status_code != 200:
|
99 |
+
raise ServerException(response.status_code)
|
100 |
+
# Get the response and check is not empty.
|
101 |
+
res = response.json()
|
102 |
+
if not res:
|
103 |
+
raise TranslationNotFound(text)
|
104 |
+
# Process and return the response.
|
105 |
+
if "error_code" in res:
|
106 |
+
raise BaiduAPIerror(res["error_msg"])
|
107 |
+
if "trans_result" in res:
|
108 |
+
return "\n".join([s["dst"] for s in res["trans_result"]])
|
109 |
+
else:
|
110 |
+
raise TranslationNotFound(text)
|
111 |
+
|
112 |
+
def translate_file(self, path: str, **kwargs) -> str:
|
113 |
+
return self._translate_file(path, **kwargs)
|
114 |
+
|
115 |
+
def translate_batch(self, batch: List[str], **kwargs) -> List[str]:
|
116 |
+
"""
|
117 |
+
@param batch: list of texts to translate
|
118 |
+
@return: list of translations
|
119 |
+
"""
|
120 |
+
return self._translate_batch(batch, **kwargs)
|
deep_translator/constants.py
CHANGED
@@ -7,6 +7,8 @@ LIBRE_ENV_VAR = "LIBRE_API_KEY"
|
|
7 |
MSFT_ENV_VAR = "MICROSOFT_API_KEY"
|
8 |
QCRI_ENV_VAR = "QCRI_API_KEY"
|
9 |
YANDEX_ENV_VAR = "YANDEX_API_KEY"
|
|
|
|
|
10 |
|
11 |
|
12 |
BASE_URLS = {
|
@@ -23,6 +25,7 @@ BASE_URLS = {
|
|
23 |
"PAPAGO_API": "https://openapi.naver.com/v1/papago/n2mt",
|
24 |
"LIBRE": "https://libretranslate.com/",
|
25 |
"LIBRE_FREE": "https://libretranslate.de/",
|
|
|
26 |
}
|
27 |
|
28 |
GOOGLE_LANGUAGES_TO_CODES = {
|
@@ -605,3 +608,34 @@ LIBRE_LANGUAGES_TO_CODES = {
|
|
605 |
"Turkish": "tr",
|
606 |
"Vietnamese": "vi",
|
607 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
MSFT_ENV_VAR = "MICROSOFT_API_KEY"
|
8 |
QCRI_ENV_VAR = "QCRI_API_KEY"
|
9 |
YANDEX_ENV_VAR = "YANDEX_API_KEY"
|
10 |
+
BAIDU_APPID_ENV_VAR = "BAIDU_APPID"
|
11 |
+
BAIDU_APPKEY_ENV_VAR = "BAIDU_APPKEY"
|
12 |
|
13 |
|
14 |
BASE_URLS = {
|
|
|
25 |
"PAPAGO_API": "https://openapi.naver.com/v1/papago/n2mt",
|
26 |
"LIBRE": "https://libretranslate.com/",
|
27 |
"LIBRE_FREE": "https://libretranslate.de/",
|
28 |
+
"BAIDU": "https://fanyi-api.baidu.com/api/trans/vip/translate",
|
29 |
}
|
30 |
|
31 |
GOOGLE_LANGUAGES_TO_CODES = {
|
|
|
608 |
"Turkish": "tr",
|
609 |
"Vietnamese": "vi",
|
610 |
}
|
611 |
+
|
612 |
+
BAIDU_LANGUAGE_TO_CODE = {
|
613 |
+
"arabic": "ara",
|
614 |
+
"bulgarian": "bul",
|
615 |
+
"chinese (classical)": "wyw",
|
616 |
+
"chinese (simplified)": "zh",
|
617 |
+
"chinese (traditional)": "cht",
|
618 |
+
"czech": "cs",
|
619 |
+
"danish": "dan",
|
620 |
+
"dutch": "nl",
|
621 |
+
"english": "en",
|
622 |
+
"estonian": "est",
|
623 |
+
"finnish": "fin",
|
624 |
+
"french": "fra",
|
625 |
+
"german": "de",
|
626 |
+
"greek": "el",
|
627 |
+
"hungarian": "hu",
|
628 |
+
"italian": "it",
|
629 |
+
"japanese": "jp",
|
630 |
+
"korean": "kor",
|
631 |
+
"polish": "pl",
|
632 |
+
"portuguese": "pt",
|
633 |
+
"romanian": "ro",
|
634 |
+
"russian": "ru",
|
635 |
+
"slovenian": "slo",
|
636 |
+
"spanish": "spa",
|
637 |
+
"swedish": "swe",
|
638 |
+
"thai": "th",
|
639 |
+
"vietnamese": "vie",
|
640 |
+
"yueyu": "yue",
|
641 |
+
}
|
deep_translator/exceptions.py
CHANGED
@@ -180,3 +180,16 @@ class AuthorizationException(Exception):
|
|
180 |
def __init__(self, api_key, *args):
|
181 |
msg = "Unauthorized access with the api key " + api_key
|
182 |
super().__init__(msg, *args)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
def __init__(self, api_key, *args):
|
181 |
msg = "Unauthorized access with the api key " + api_key
|
182 |
super().__init__(msg, *args)
|
183 |
+
|
184 |
+
|
185 |
+
class BaiduAPIerror(Exception):
|
186 |
+
"""
|
187 |
+
exception thrown if Baidu API returns one of its errors
|
188 |
+
"""
|
189 |
+
|
190 |
+
def __init__(self, api_message):
|
191 |
+
self.api_message = str(api_message)
|
192 |
+
self.message = "Baidu API returned the following error"
|
193 |
+
|
194 |
+
def __str__(self):
|
195 |
+
return "{}: {}".format(self.message, self.api_message)
|
docs/README.rst
CHANGED
@@ -665,6 +665,66 @@ Libre Translator
|
|
665 |
translated = LibreTranslator(source='auto', target='en').translate_file('path/to/file')
|
666 |
|
667 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
668 |
|
669 |
Proxy usage
|
670 |
-------------
|
|
|
665 |
translated = LibreTranslator(source='auto', target='en').translate_file('path/to/file')
|
666 |
|
667 |
|
668 |
+
BaiduTranslator
|
669 |
+
-----------------
|
670 |
+
|
671 |
+
.. note::
|
672 |
+
|
673 |
+
In order to use the BaiduTranslator translator, you need to generate a secret_id and a secret_key.
|
674 |
+
deep-translator supports both Pro and free APIs. Just check the examples below.
|
675 |
+
Visit http://api.fanyi.baidu.com/product/113 for more information on how to generate your Baidu appid
|
676 |
+
and appkey.
|
677 |
+
|
678 |
+
- Simple translation
|
679 |
+
|
680 |
+
.. code-block:: python
|
681 |
+
|
682 |
+
text = 'Hello world'
|
683 |
+
translated = BaiduTranslator(appid="your-appid", appkey="your-appkey" source="en", target="zh").translate(text)
|
684 |
+
|
685 |
+
- Translate batch of texts
|
686 |
+
|
687 |
+
.. code-block:: python
|
688 |
+
=
|
689 |
+
texts = ["Hello world", "How are you?"]
|
690 |
+
translated = BaiduTranslator(appid="your-appid", appkey="your-appkey" source="en", target="zh").translate_batch(texts)
|
691 |
+
|
692 |
+
- Translate from a file:
|
693 |
+
|
694 |
+
.. code-block:: python
|
695 |
+
|
696 |
+
translated = BaiduTranslator(appid="your-appid", appkey="your-appkey" source="en", target="zh").translate_file('path/to/file')
|
697 |
+
|
698 |
+
BaiduTranslator
|
699 |
+
-----------------
|
700 |
+
|
701 |
+
.. note::
|
702 |
+
|
703 |
+
In order to use the BaiduTranslator translator, you need to generate a secret_id and a secret_key.
|
704 |
+
deep-translator supports both Pro and free APIs. Just check the examples below.
|
705 |
+
Visit http://api.fanyi.baidu.com/product/113 for more information on how to generate your Baidu appid
|
706 |
+
and appkey.
|
707 |
+
|
708 |
+
- Simple translation
|
709 |
+
|
710 |
+
.. code-block:: python
|
711 |
+
|
712 |
+
text = 'Hello world'
|
713 |
+
translated = BaiduTranslator(appid="your-appid", appkey="your-appkey" source="en", target="zh").translate(text)
|
714 |
+
|
715 |
+
- Translate batch of texts
|
716 |
+
|
717 |
+
.. code-block:: python
|
718 |
+
=
|
719 |
+
texts = ["Hello world", "How are you?"]
|
720 |
+
translated = BaiduTranslator(appid="your-appid", appkey="your-appkey" source="en", target="zh").translate_batch(texts)
|
721 |
+
|
722 |
+
- Translate from a file:
|
723 |
+
|
724 |
+
.. code-block:: python
|
725 |
+
|
726 |
+
translated = BaiduTranslator(appid="your-appid", appkey="your-appkey" source="en", target="zh").translate_file('path/to/file')
|
727 |
+
|
728 |
|
729 |
Proxy usage
|
730 |
-------------
|
tests/test_baidu.py
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from unittest.mock import Mock, patch
|
2 |
+
|
3 |
+
import pytest
|
4 |
+
|
5 |
+
from deep_translator import BaiduTranslator
|
6 |
+
from deep_translator.exceptions import BaiduAPIerror
|
7 |
+
|
8 |
+
|
9 |
+
@patch("deep_translator.baidu.requests")
|
10 |
+
def test_simple_translation(mock_requests):
|
11 |
+
translator = BaiduTranslator(
|
12 |
+
appid="this-is-an-valid-appid",
|
13 |
+
appkey="this-is-an-valid-appkey",
|
14 |
+
source="en",
|
15 |
+
target="zh",
|
16 |
+
)
|
17 |
+
# Set the request response mock.
|
18 |
+
mock_response = Mock()
|
19 |
+
mock_response.status_code = 200
|
20 |
+
mock_response.json.return_value = {
|
21 |
+
"from": "en",
|
22 |
+
"to": "zh",
|
23 |
+
"trans_result": [{"src": "hello", "dst": "你好"}],
|
24 |
+
}
|
25 |
+
mock_requests.post.return_value = mock_response
|
26 |
+
translation = translator.translate("hello")
|
27 |
+
assert translation == "你好"
|
28 |
+
|
29 |
+
|
30 |
+
@patch("deep_translator.baidu.requests.get")
|
31 |
+
def test_wrong_api_key(mock_requests):
|
32 |
+
translator = BaiduTranslator(
|
33 |
+
appid="this-is-a-wrong-appid",
|
34 |
+
appkey="this-is-a-wrong-appkey",
|
35 |
+
source="en",
|
36 |
+
target="zh",
|
37 |
+
)
|
38 |
+
# Set the response status_code only.
|
39 |
+
mock_response = Mock()
|
40 |
+
mock_response.status_code = 200
|
41 |
+
mock_response.json.return_value = {
|
42 |
+
"error_code": "54001",
|
43 |
+
"error_msg": "Invalid Sign",
|
44 |
+
}
|
45 |
+
mock_requests.post.return_value = mock_response
|
46 |
+
with pytest.raises(BaiduAPIerror):
|
47 |
+
translator.translate("Hello")
|
48 |
+
|
49 |
+
|
50 |
+
# the remaining tests are actual requests to Baidu translator API and use appid and appkey
|
51 |
+
# if appid and appkey variable is None, they are skipped
|
52 |
+
|
53 |
+
appid = None
|
54 |
+
appkey = None
|
55 |
+
|
56 |
+
|
57 |
+
@pytest.mark.skipif(
|
58 |
+
appid is None or appkey is None,
|
59 |
+
reason="appid or appkey is not provided",
|
60 |
+
)
|
61 |
+
def test_baidu_successful_post_onetarget():
|
62 |
+
posted = BaiduTranslator(
|
63 |
+
appid=appid, appkey=appkey, source="en", target="zh"
|
64 |
+
).translate("Hello! How are you?")
|
65 |
+
assert isinstance(posted, str)
|