python csv unicode codec 'ascii' não pode codificar caractere u '\ xf6' na posição 1: ordinal não está no intervalo (128)
Eu copiei este script do [site da web python] [1] Esta é outra questão, mas agora problema com a codificação:
import sqlite3
import csv
import codecs
import cStringIO
import sys
class UTF8Recoder:
"""
Iterator that reads an encoded stream and reencodes the input to UTF-8
"""
def __init__(self, f, encoding):
self.reader = codecs.getreader(encoding)(f)
def __iter__(self):
return self
def next(self):
return self.reader.next().encode("utf-8")
class UnicodeReader:
"""
A CSV reader which will iterate over lines in the CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
f = UTF8Recoder(f, encoding)
self.reader = csv.reader(f, dialect=dialect, **kwds)
def next(self):
row = self.reader.next()
return [unicode(s, "utf-8") for s in row]
def __iter__(self):
return self
class UnicodeWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
def writerow(self, row):
self.writer.writerow([s.encode("utf-8") for s in row])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and reencode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
for row in rows:
self.writerow(row)
Esse problema de tempo com codificação, quando eu corri isso me deu esse erro:
Traceback (most recent call last):
File "makeCSV.py", line 87, in <module>
uW.writerow(d)
File "makeCSV.py", line 54, in writerow
self.writer.writerow([s.encode("utf-8") for s in row])
AttributeError: 'int' object has no attribute 'encode'
Então eu converti todos os inteiros para string, mas desta vez eu recebi este erro:
Traceback (most recent call last):
File "makeCSV.py", line 87, in <module>
uW.writerow(d)
File "makeCSV.py", line 54, in writerow
self.writer.writerow([str(s).encode("utf-8") for s in row])
UnicodeEncodeError: 'ascii' codec can't encode character u'\xf6' in position 1: ordinal not in range(128)
Eu tenho implementado acima para lidar com caracteres unicode, mas isso me dá esse erro. Qual é o problema e como consertar isso?