Afternoon,
I am having some trouble with a SQLite to CSV python script. I have searched high and I have searched low for an answer but none have worked for me, or I am having a problem with my syntax.
I want to replace characters within the SQLite database which fall outside of the ASCII table (larger than 128).
Here is the script I have been using:
#!/opt/local/bin/python
import sqlite3
import csv, codecs, cStringIO
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([unicode(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)
conn = sqlite3.connect('test.db')
c = conn.cursor()
# Select whichever rows you want in whatever order you like
c.execute('select ROWID, Name, Type, PID from PID')
writer = UnicodeWriter(open("ProductListing.csv", "wb"))
# Make sure the list of column headers you pass in are in the same order as your SELECT
writer.writerow(["ROWID", "Product Name", "Product Type", "PID", ])
writer.writerows(c)
I have tried to add the 'replace' as indicated here but have got the same error. Python: Convert Unicode to ASCII without errors for CSV file
The error is the UnicodeDecodeError.
Traceback (most recent call last):
File "SQLite2CSV1.py", line 53, in <module>
writer.writerows(c)
File "SQLite2CSV1.py", line 32, in writerows
self.writerow(row)
File "SQLite2CSV1.py", line 19, in writerow
self.writer.writerow([unicode(s).encode("utf-8") for s in row])
UnicodeDecodeError: 'ascii' codec can't decode byte 0xa0 in position 65: ordinal not in range(128)
Obviously I want the code to be robust enough that if it encounters characters outside of these bounds that it replaces it with a character such as '?' (\x3f).
Is there a way to do this within the UnicodeWriter class? And a way I can make the code robust that it won't produce these errors.
Your help is greatly appreciated.
