How to convert a file to utf-8 in Python?
Solution 1:
You can use the codecs module, like this:
import codecs
BLOCKSIZE = 1048576 # or some other, desired size in bytes
with codecs.open(sourceFileName, "r", "your-source-encoding") as sourceFile:
with codecs.open(targetFileName, "w", "utf-8") as targetFile:
while True:
contents = sourceFile.read(BLOCKSIZE)
if not contents:
break
targetFile.write(contents)
EDIT: added BLOCKSIZE
parameter to control file chunk size.
Solution 2:
This worked for me in a small test:
sourceEncoding = "iso-8859-1"
targetEncoding = "utf-8"
source = open("source")
target = open("target", "w")
target.write(unicode(source.read(), sourceEncoding).encode(targetEncoding))
Solution 3:
Thanks for the replies, it works!
And since the source files are in mixed formats, I added a list of source formats to be tried in sequence (sourceFormats
), and on UnicodeDecodeError
I try the next format:
from __future__ import with_statement
import os
import sys
import codecs
from chardet.universaldetector import UniversalDetector
targetFormat = 'utf-8'
outputDir = 'converted'
detector = UniversalDetector()
def get_encoding_type(current_file):
detector.reset()
for line in file(current_file):
detector.feed(line)
if detector.done: break
detector.close()
return detector.result['encoding']
def convertFileBestGuess(filename):
sourceFormats = ['ascii', 'iso-8859-1']
for format in sourceFormats:
try:
with codecs.open(fileName, 'rU', format) as sourceFile:
writeConversion(sourceFile)
print('Done.')
return
except UnicodeDecodeError:
pass
def convertFileWithDetection(fileName):
print("Converting '" + fileName + "'...")
format=get_encoding_type(fileName)
try:
with codecs.open(fileName, 'rU', format) as sourceFile:
writeConversion(sourceFile)
print('Done.')
return
except UnicodeDecodeError:
pass
print("Error: failed to convert '" + fileName + "'.")
def writeConversion(file):
with codecs.open(outputDir + '/' + fileName, 'w', targetFormat) as targetFile:
for line in file:
targetFile.write(line)
# Off topic: get the file list and call convertFile on each file
# ...
(EDIT by Rudro Badhon: this incorporates the original try multiple formats until you don't get an exception as well as an alternate approach that uses chardet.universaldetector)
Solution 4:
Answer for unknown source encoding type
based on @Sébastien RoccaSerra
python3.6
import os
from chardet import detect
# get file encoding type
def get_encoding_type(file):
with open(file, 'rb') as f:
rawdata = f.read()
return detect(rawdata)['encoding']
from_codec = get_encoding_type(srcfile)
# add try: except block for reliability
try:
with open(srcfile, 'r', encoding=from_codec) as f, open(trgfile, 'w', encoding='utf-8') as e:
text = f.read() # for small files, for big use chunks
e.write(text)
os.remove(srcfile) # remove old encoding file
os.rename(trgfile, srcfile) # rename new encoding
except UnicodeDecodeError:
print('Decode Error')
except UnicodeEncodeError:
print('Encode Error')
Solution 5:
This is a Python3 function for converting any text file into the one with UTF-8 encoding. (without using unnecessary packages)
def correctSubtitleEncoding(filename, newFilename, encoding_from, encoding_to='UTF-8'):
with open(filename, 'r', encoding=encoding_from) as fr:
with open(newFilename, 'w', encoding=encoding_to) as fw:
for line in fr:
fw.write(line[:-1]+'\r\n')
You can use it easily in a loop to convert a list of files.