Python Documents have following code example on writing unicode to csv file. I think it has mentioned there that this is the way to do since csv module can't handle unicode strings.
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)
I am writing more than one file and to keep it simple I have only put the section of my code to demonstrate how I use above class in my code:
def write(self):
"""
Outputs the dataset to a csv.
"""
f = codecs.open(self.filename, 'a')
writer = UnicodeWriter(f)
#with open(self.filename, 'a', encoding='utf-8') as f:
if self.headers and not self.written:
writer.writerow(self.headers)
self.written = True
for record in self.records[self.last_written:]:
print record
writer.writerow(record)
self.last_written = len(self.records)
f.close()
This is a method inside a class coll dataset which prepare the dataset prior to writing to csv, previously I was using writer = csv.writer(f) but due to codec errors I change my code to use `UnicodeWriter class.
But my problem is that when I open the csv file, I get the following:
some_header
B,r,ë,k,ò,w,n,i,k,_,b,s
B,r,ë,k,ò,w,n,i,k,_,c,s
B,r,ë,k,ò,w,n,i,k,_,c,s,b
B,r,ë,k,ò,w,n,i,k,_,d,e
B,r,ë,k,ò,w,n,i,k,_,d,e,-,1
B,r,ë,k,ò,w,n,i,k,_,d,e,-,2
B,r,ë,k,ò,w,n,i,k,_,d,e,-,3
B,r,ë,k,ò,w,n,i,k,_,d,e,-,4
B,r,ë,k,ò,w,n,i,k,_,d,e,-,5
B,r,ë,k,ò,w,n,i,k,_,d,e,-,M
B,r,ë,k,ò,w,n,i,k,_,e,n
B,r,ë,k,ò,w,n,i,k,_,e,n,-,1
B,r,ë,k,ò,w,n,i,k,_,e,n,-,2
Where as these rows should actually should be something like Brëkòwnik_de-1 I am not really whats happening.
To give a basic idea of how the data has been generated I would add the following line:
title = unicode(row_page_title['page_title'], 'utf-8')
isinstance(row, basestring) == True(should be an array or tuple).