读写utf-8格式文档
官方文档提供了csv支持unicode的代码,如下:
# -*- coding: utf-8 -*-
import csv, codecs, cStringIO
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)
读
input_path = 'xx'
reader = UnicodeReader(codecs.open(input_path, 'rb'), delimiter=',')
for row in reader:
# TODO
写
output_path = 'xx'
writer = UnicodeWriter(codecs.open(output_path, 'wb'), delimiter=',')
writer.writerow([xx])
为了解决csv读取unicode问题,你还可以使用unicodecsv
包,详见 Python2向文件写入Unicode字符
btw,当列的某个值中可能包含换行时,使用csv模块读取是个明智的选择。(相比较直接读文件、split而言)
Ref