[python] How to convert a file to utf-8 in Python?

I need to convert a bunch of files to utf-8 in Python, and I have trouble with the "converting the file" part.

I'd like to do the equivalent of:

iconv -t utf-8 $file > converted/$file # this is shell code

Thanks!

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')

To guess what's the source encoding you can use the file *nix command.

Example:

$ file --mime jumper.xml

jumper.xml: application/xml; charset=utf-8

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))

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)

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))

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))

This is my brute force method. It also takes care of mingled \n and \r\n in the input.

    # open the CSV file
    inputfile = open(filelocation, 'rb')
    outputfile = open(outputfilelocation, 'w', encoding='utf-8')
    for line in inputfile:
        if line[-2:] == b'\r\n' or line[-2:] == b'\n\r':
            output = line[:-2].decode('utf-8', 'replace') + '\n'
        elif line[-1:] == b'\r' or line[-1:] == b'\n':
            output = line[:-1].decode('utf-8', 'replace') + '\n'
        else:
            output = line.decode('utf-8', 'replace') + '\n'
        outputfile.write(output)
    outputfile.close()
except BaseException as error:
    cfg.log(self.outf, "Error(18): opening CSV-file " + filelocation + " failed: " + str(error))
    self.loadedwitherrors = 1
    return ([])
try:
    # open the CSV-file of this source table
    csvreader = csv.reader(open(outputfilelocation, "rU"), delimiter=delimitervalue, quoting=quotevalue, dialect=csv.excel_tab)
except BaseException as error:
    cfg.log(self.outf, "Error(19): reading CSV-file " + filelocation + " failed: " + str(error))

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)

This is my brute force method. It also takes care of mingled \n and \r\n in the input.

    # open the CSV file
    inputfile = open(filelocation, 'rb')
    outputfile = open(outputfilelocation, 'w', encoding='utf-8')
    for line in inputfile:
        if line[-2:] == b'\r\n' or line[-2:] == b'\n\r':
            output = line[:-2].decode('utf-8', 'replace') + '\n'
        elif line[-1:] == b'\r' or line[-1:] == b'\n':
            output = line[:-1].decode('utf-8', 'replace') + '\n'
        else:
            output = line.decode('utf-8', 'replace') + '\n'
        outputfile.write(output)
    outputfile.close()
except BaseException as error:
    cfg.log(self.outf, "Error(18): opening CSV-file " + filelocation + " failed: " + str(error))
    self.loadedwitherrors = 1
    return ([])
try:
    # open the CSV-file of this source table
    csvreader = csv.reader(open(outputfilelocation, "rU"), delimiter=delimitervalue, quoting=quotevalue, dialect=csv.excel_tab)
except BaseException as error:
    cfg.log(self.outf, "Error(19): reading CSV-file " + filelocation + " failed: " + str(error))

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.

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')

To guess what's the source encoding you can use the file *nix command.

Example:

$ file --mime jumper.xml

jumper.xml: application/xml; charset=utf-8

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)

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.

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))