问题描述
我有一个18,000行的越南数据集，我正尝试使用googletrans模块将其翻译成英文。
from googletrans import Translator
translator = Translator()
def trans_text(df,text_field):
df[text_field] = df[text_field].apply(translator.translate,src='vi',dest='en').apply(getattr,args=('text',))
return df
trans_text(df_train.sample(1),"question")
我最终遇到以下JSONDecode错误：
JSONDecodeError Traceback (most recent call last)
<ipython-input-21-d6791d78575e> in <module>()
24 df[text_field] = df[text_field].apply(translator.translate,))
25 return df
---> 26 trans_text(df_train.sample(1),"question")
27
28
<ipython-input-21-d6791d78575e> in trans_text(df,text_field)
22
23 def trans_text(df,text_field):
---> 24 df[text_field] = df[text_field].apply(translator.translate,))
25 return df
26 trans_text(df_train.sample(1),"question")
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/site-packages/pandas/core/series.py in apply(self,func,convert_dtype,args,**kwds)
4198 else:
4199 values = self.astype(object)._values
-> 4200 mapped = lib.map_infer(values,f,convert=convert_dtype)
4201
4202 if len(mapped) and isinstance(mapped[0],Series):
pandas/_libs/lib.pyx in pandas._libs.lib.map_infer()
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/site-packages/pandas/core/series.py in f(x)
4183
4184 def f(x):
-> 4185 return func(x,*args,**kwds)
4186
4187 else:
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/site-packages/googletrans/client.py in translate(self,text,dest,src)
170
171 origin = text
--> 172 data = self._translate(text,src)
173
174 # this code will be updated when the format is changed.
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/site-packages/googletrans/client.py in _translate(self,src)
79 r = self.session.get(url,params=params)
80
---> 81 data = utils.format_json(r.text)
82 return data
83
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/site-packages/googletrans/utils.py in format_json(original)
60 converted = json.loads(original)
61 except ValueError:
---> 62 converted = legacy_format_json(original)
63
64 return converted
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/site-packages/googletrans/utils.py in legacy_format_json(original)
52 text = text[:p] + states[j][1] + text[nxt:]
53
---> 54 converted = json.loads(text)
55 return converted
56
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/json/__init__.py in loads(s,encoding,cls,object_hook,parse_float,parse_int,parse_constant,object_pairs_hook,**kw)
352 parse_int is None and parse_float is None and
353 parse_constant is None and object_pairs_hook is None and not kw):
--> 354 return _default_decoder.decode(s)
355 if cls is None:
356 cls = JSONDecoder
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/json/decoder.py in decode(self,s,_w)
337
338 """
--> 339 obj,end = self.raw_decode(s,idx=_w(s,0).end())
340 end = _w(s,end).end()
341 if end != len(s):
/opt/anaconda3/envs/sam-pycaret/lib/python3.6/json/decoder.py in raw_decode(self,idx)
355 obj,end = self.scan_once(s,idx)
356 except stopiteration as err:
--> 357 raise JSONDecodeError("Expecting value",err.value) from None
358 return obj,end
JSONDecodeError: Expecting value: line 1 column 1 (char 0)
我了解这是由于我的IP禁令引起的。我研究了规避此问题的方法，发现使用VPN值得一试。我已经安装了HolaVPN。但是，作为这一切的新手，我不确定如何复制与hola的solution中相同的步骤。遵循明确程序的任何技巧都可以极大地帮助您。谢谢。
解决方法
该库发出请求，并且不检查状态码就假定请求成功：
79 r = self.session.get(url,params=params)
80
---> 81 data = utils.format_json(r.text)
现在，Google可能会由于任何原因而不喜欢您的请求，并返回带有匹配状态代码（4xx，5xx）的错误消息。该库仍尝试将正文解析为JSON，由于没有正文，该正文无法正常工作，并引发与原始问题无关的JSONDecodeError。您看不出真正的原因。
结论：googletrans库缺少重要的错误处理。您可能需要对其进行编辑，并自行添加错误处理。