Found a Google Translate endpoint that doesn't require an API key. #268
Comments
|
This seems like a great discovery! I'll take a look at this shortly. Thank you so much! |
|
@ssut No problem! |
|
@theonefoster Glad to be of use! |
|
Stopped working for me (403) |
|
@shatteringlass Mentioned that in the initial post:
That's why I want this endpoint to be seamlessly integrated into |
|
I found another endpoint within the source code of one of the google translate extensions on VSCode too. "https://translate.googleapis.com/translate_a/single?client=gtx&dt=t + params"
// where the params are:
{
"sl": source language,
"tl": destination language,
"q": the text to translate
}The results looks something like this: [[["こんにちは、今日はお元気ですか？","Hello, how are you today?",null,null,3,null,null,[[]
]
,[[["9588ca5d94759e1e85ee26c1b641b1e3","kgmt_en_ja_2020q3.md"]
]
]
]
]
,null,"en",null,null,null,null,[]
]
And something like this: [[["Bonjour","Hello",null,null,1]
]
,null,"en",null,null,null,null,[]
]
When using it only to translate things, I would use it like so: from json import loads
from requests import get
request_result = get("https://translate.googleapis.com/translate_a/single?client=gtx&dt=t&sl=en&tl=fr&q=Hello")
translated_text = loads(request_result.text)[0][0][0]
print(translated_text) |
|
@Animenosekai Awesome, another endpoint to add. We should probably create a way to house all of these endpoints through one API, perhaps an interface that all of the endpoints implement? |
|
What am I doing wrong? word = 'لماذا تفعل هذا'
try:
request_result = requests.post("https://clients5.google.com/translate_a/t?client=dict-chrome-ex&sl=auto&tl=en&q="+ word).json()
print(request_result)
print('[In English]: '+ request_result['alternative_translations'][0]['alternative'][0]['word_postproc'])
print('[Language Dectected]: ' + request_result['src'])
except:
traceback.print_exc()Output: why is it outputting it like that? |
|
@NawtJ0sh Why are you making a POST request? It's a GET request you should be making. How does that even return a response? |
|
No idea, it does the exact same thing with requests.get() |
If you try to open it in a browser it seems to work fine: {"sentences":[{"trans":"Why are you doing this","orig":"لماذا تفعل هذا","backend":1},{"src_translit":"limadha tafeal hdha"}],"src":"ar","alternative_translations":[{"src_phrase":"لماذا تفعل هذا","alternative":[{"word_postproc":"Why are you doing this","score":1000,"has_preceding_space":true,"attach_to_next_token":false}],"srcunicodeoffsets":[{"begin":0,"end":14}],"raw_src_segment":"لماذا تفعل هذا","start_pos":0,"end_pos":0}],"confidence":1,"ld_result":{"srclangs":["ar"],"srclangs_confidences":[1],"extended_srclangs":["ar"]}}Might be a problem with the decoding, try to use the It might be because your terminal doesn't support arabic or something like that Also maybe try to url encode the text before sending it (and use GET as it should not work with POST) |
|
After some testing with the request headers, I found the solution for the garbled text. Example: import requests
word = 'لماذا تفعل هذا'
url = "https://clients5.google.com/translate_a/t?client=dict-chrome-ex&sl=auto&tl=en&q=" + word
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'
}
try:
request_result = requests.get(url, headers=headers).json()
print(request_result)
print('[In English]: ' + request_result['alternative_translations'][0]['alternative'][0]['word_postproc'])
print('[Language Dectected]: ' + request_result['src'])
except:
passResponse: |
|
@d4n3436 How interesting. It's almost like a form of copy protection. |
Maybe that they are retrieving the User-Agent to process some analytics in the bg and that without it it breaks something. But, I mean, still weird that it gives a gibberish response and that it accepted the |
It's weird... If you don't use User-Agent, the response will have an incorrect encoding (ASCII). About the |
|
if anyone wants to try and get this Bing translator to work that'd be awesome import requests
url = 'https://www.bing.com/ttranslatev3'
post_header = {}
post_header['Host'] = 'www.bing.com'
post_header['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0'
post_header['Accept'] = '*/*'
post_header['Accept-Language'] = 'en-US,en;q=0.5'
post_header['Accept-Encoding'] = 'gzip, deflate'
post_header['Referer'] = 'https://www.bing.com/'
post_header['Content-Type'] = 'application/x-www-form-urlencoded'
post_header['Connection'] = 'keep-alive'
parameters_payload = {'IG' : '839D27F8277F4AA3B0EDB83C255D0D70', 'IID' : 'translator.5033.3'}
data_payload = {'text':'Platypus', 'from':'en', 'to':'es'}
resp = requests.post(url, headers=post_header, params=parameters_payload, data=data_payload)
print(resp.json()) |
|
@NawtJ0sh Microsoft might have changed their API since I get back: {'statusCode': 400} # if this was a http status code, means bad request --> might be because the params don't work anymore(which is weird since the HTTP status code is 200) |
|
@NawtJ0sh I made a simple API wrapper for Bing Translator in C# some months ago. You can use it and port it. |
Nice! if you could try it with the Yandex translator, that'd be cool! |
All that was changed was the 'from' to 'fromLang' haha |
I actually made one, but unfortunately Yandex has a captcha protection that is triggered after a few uses of their API. |
Lmao, yea I just checked and it worked! [{'detectedLanguage': {'language': 'en', 'score': 1.0}, 'translations': [{'text': 'Ornitorrinco', 'to': 'es', 'sentLen': {'srcSentLen': [8], 'transSentLen': [12]}}]}] |
Well here you go: from json import loads
from requests import post
HEADERS = {
"Host": "www.bing.com",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0",
"Accept": "*/*",
"Accept-Language": "en-US,en;q=0.5",
"Accept-Encoding": "gzip, deflate",
"Referer": "https://www.bing.com/",
"Content-Type": "application/x-www-form-urlencoded",
"Connection": "keep-alive"
}
PARAMS = {'IG' : '839D27F8277F4AA3B0EDB83C255D0D70', 'IID' : 'translator.5033.3'}
def translate(text, to, fromLang="auto-detect"):
"""
Translates the given text to the given language using Microsoft's Bing Translation API (ttranslatev3)
"""
request = post("https://www.bing.com/ttranslatev3", headers=HEADERS, params=PARAMS, data={'text': str(text), 'fromLang': str(fromLang), 'to': str(to)})
if request.status_code < 400:
try:
return loads(request.text)[0]["translations"][0]["text"]
except:
return None
else:
return None
def language(text):
"""
Gives you back the ISO 639-1 Alpha-2 language code the text has been written in using Microsoft's Bing Translation API (ttranslatev3)
> The output is a tuple with the language code and the score (confidence)
"""
request = post("https://www.bing.com/ttranslatev3", headers=HEADERS, params=PARAMS, data={'text': str(text), 'fromLang': "auto-detect", 'to': "en"})
if request.status_code < 400:
try:
detectedLanguage = loads(request.text)[0]["detectedLanguage"]
return detectedLanguage["language"], detectedLanguage["score"]
except:
return None
else:
return NoneJust call translate("<your text>", "<the ISO 639-1 Alpha-2 language codes (I guess) of the output language>")Or if you want to know the language of a given text: language("<your text>")And it gives you back the result or
>>> translate("Hello", "ja")
'こんにちは'
>>> translate("Hello", "fr")
'Bonjour'
>>> translate("Hello", "fr", "en")
'Bonjour'
>>> language("Hello")
('en', 1.0)
>>> language("Hola")
('es', 1.0) |
|
Here is the yandex translate, I worked on last night its just like the bing.com one i posted. import requests
url = 'https://translate.yandex.net/api/v1/tr.json/translate?id=1308a84a.6016deed.0c4881a2.74722d74657874-3-0&srv=tr-text&lang=en&reason=auto&format=text'
post_header = {}
post_header['Accept'] = '*/*'
post_header['Accept-Encoding'] = 'gzip, deflate'
post_header['Accept-Language'] = 'en-US,en;q=0.9'
post_header['Cache-Control'] = 'no-cache'
post_header['Connection'] = 'keep-alive'
post_header['Content-Type'] = 'application/x-www-form-urlencoded'
post_header['Host'] = 'translate.yandex.com'
post_header['Referer'] = 'https://translate.yandex.com/'
post_header['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'
data_payload = {'text': search_str, 'options': '4'}
resp = requests.get(url, headers=post_header, data=data_payload).json()
print(str(resp) + '\n') |
I just made a repository which groups all of the APIs if you want (called
|
|
Nice you fixed it!! Thank you. |
|
@lokinmodar The only caveat is that it's the mobile version of Google Translate which tends to yield worse translations (based on previous observations, this might have changed and this page is slightly different than the normal Google Translate mobile page) |
i noticed this is much more faithful to the translations I used to get with the https://clients5.google.com/translate_a/t?client=dict-chrome-ex&sl=en&tl=it&q=body endpoint before they screwed it up |
|
I made a comparison of all (known) Google Translate API endpoints based on my findings while making my translation library, this may be useful if you don't know which API endpoint to use.
In conclusion, the second endpoint is currently the best free Google Translate API endpoint, unless someone manages to decipher the |
|
this is what the url is like now (on the Google Dictionary Extension) |
|
Does anyone understand what is |
|
https://translate.google.com/_/TranslateWebserverUi/data/batchexecu seems no longer to work, 404 now. |
|
https://translate.google.com/_/TranslateWebserverUi/data/batchexecute still OK. https://translate.google.cn/_/TranslateWebserverUi/data/batchexecute no longer works because translate.google.cn is dead (redirected to translate.google.com.hk in fact). |
|
Hello,everyone |
|
I know this is an older thread but just wanted to warn people that
|
I have found that The only drawback is that it splits the translation into multiple parts if the query is too long, which requires us to join them back together. It also provides far better translations compared to |
|
From testing various options from this discussion:
|
|
Don't forget |
|
Haven't tested that at first, but it actually seems to be a great option with only minor caveats! Added. |
@RemyJouni Maybe that's the case for some language combinations. I just tested
|
|
@tkefauver Here's the URL for your example request: |
|
@v1993 Ah ha! My mistake, its an issue with the tool I'm using ResXResourceManager. My bad, thank you |
|
Has anyone seen Google Translate has changed for the worse recently? About last 5–7 days, I noticed the result is confusing compare before. Currently, I find get directly translates from their website has the best results compare with call other API endpoints. |
Yes, I'm noticing the same thing too. And it goes back to a couple of weeks ago. |
|
I have installed the Google Translate extension and looked into the source code and managed to find a new endpoint, which has a way better translation than older endpoints mentioned here. But here is the catch, So if anyone can help with the second problem, I would greatly appreciate it. |
CORS headers cannot be circumvented in th browser. Consider using a proxy. This SO answer is a good starting point: https://stackoverflow.com/questions/43871637/no-access-control-allow-origin-header-is-present-on-the-requested-resource-whe/43881141#43881141 |
and others
While digging through the source code of Google's Google Dictionary Chrome extension, which has support for translating via Google Translate, I found the endpoint they use in order to do just that. Since
googletransfrequently runs into 5xx errors, it might be useful to switch off to another endpoint, although this one is also annoyingly touchy with 403s.Breakdown
Endpoint:
https://clients5.google.com/translate_a/tQuery Parameters
dict-chrome-exdict-chrome-exor else you'll get a 403 error.autoExample Response
{ "sentences": [ { "trans": "Hello", "orig": "bonjour", "backend": 1 } ], "dict": [ { "pos": "interjection", "terms": [ "Hello!", "Hi!", "Good morning!", "Good afternoon!", "How do you do?", "Hallo!", "Hullo!", "Welcome!" ], "entry": [ { "word": "Hello!", "reverse_translation": [ "Bonjour!", "Salut!", "Tiens!", "Allô!" ], "score": 0.7316156 }, { "word": "Hi!", "reverse_translation": [ "Salut!", "Bonjour!", "Hé!" ], "score": 0.084690653 }, { "word": "Good morning!", "reverse_translation": [ "Bonjour!" ], "score": 0.065957151 }, { "word": "Good afternoon!", "reverse_translation": [ "Bonjour!" ], "score": 0.02749503 }, { "word": "How do you do?", "reverse_translation": [ "Bonjour!", "Salut!", "Ça marche?" ] }, { "word": "Hallo!", "reverse_translation": [ "Bonjour!", "Tiens!", "Salut!", "Allô!" ] }, { "word": "Hullo!", "reverse_translation": [ "Tiens!", "Allô!", "Salut!", "Bonjour!" ] }, { "word": "Welcome!", "reverse_translation": [ "Salut!", "Bonjour!", "Soyez le bienvenu!" ] } ], "base_form": "Bonjour!", "pos_enum": 9 } ], "src": "fr", "alternative_translations": [ { "src_phrase": "bonjour", "alternative": [ { "word_postproc": "Hello", "score": 1000, "has_preceding_space": true, "attach_to_next_token": false } ], "srcunicodeoffsets": [ { "begin": 0, "end": 7 } ], "raw_src_segment": "bonjour", "start_pos": 0, "end_pos": 0 } ], "confidence": 0.96875, "ld_result": { "srclangs": [ "fr" ], "srclangs_confidences": [ 0.96875 ], "extended_srclangs": [ "fr" ] }, "query_inflections": [ { "written_form": "bonjour", "features": { "gender": 1, "number": 2 } }, { "written_form": "bonjours", "features": { "gender": 1, "number": 1 } }, { "written_form": "bonjour", "features": { "number": 2 } }, { "written_form": "bonjours", "features": { "number": 1 } } ] }The text was updated successfully, but these errors were encountered: