CODEWITHSUNDEEP
pythoncsvpython-3.xutf-8
user3024562
user3024562

Reputation: 27

Read many csv file and write it to encoding to utf8 using python

I'm using python code to read from many csv files and set encoding to utf8.I meet the problem when I read the file I can read all lines but when I write it, it can write only 1 line. Please help me to check my code as below:

def convert_files(files, ascii, to="utf-8"):
for name in files:
#print ("Convert {0} from {1} to {2}").format(name, ascii, to)
    with open(name) as f:
        print(name)
        count = 0
        lineno = 0
        #this point I want to write the below text into my each new file at the first line           
        #file_source.write('id;nom;prenom;nom_pere;nom_mere;prenom_pere;prenom_mere;civilite (1=homme 2=f);date_naissance;arrondissement;adresse;ville;code_postal;pays;telephone;email;civilite_demandeur (1=homme 2=f);nom_demandeur;prenom_demandeur;qualite_demandeur;type_acte;nombre_actes\n')
        for line in f.readlines():
            lineno +=1
            if lineno == 1 :
                continue
            file_source = open(name, mode='w', encoding='utf-8', errors='ignore')
            #pass
            #print (line)
            # start write data to to new file with encode

            file_source.write(line)
            #file_source.close

#print unicode(line, "cp866").encode("utf-8")   
csv_files = find_csv_filenames('./csv', ".csv")
convert_files(csv_files, "cp866")

Upvotes: 0

Views: 1340

Answers (3)

wcp
wcp

Reputation: 126

You can do this

def convert_files(files, ascii, to="utf-8"):
    for name in files:
        with open(name, 'r+') as f:
            data = ''.join(f.readlines())
            data.decode(ascii).encode(to)
            f.seek(0)
            f.write(data)
            f.truncate()

Upvotes: 0

jfs
jfs

Reputation: 414245

If all you need is to change the character encoding of the files then it doesn't matter that they are csv files unless the conversion may change what characters are interpreted as delimiter, quotechar, etc:

def convert(filename, from_encoding, to_encoding):
    with open(filename, newline='', encoding=from_encoding) as file:
        data = file.read().encode(to_encoding)
    with open(filename, 'wb') as outfile:
         outfile.write(data)

for path in csv_files:
    convert(path, "cp866", "utf-8")

Add errors parameter to change how encoding/decoding errors are handled.

If files may be large then you could convert data incrementally:

import os
from shutil import copyfileobj
from tempfile import NamedTemporaryFile

def convert(filename, from_encoding, to_encoding):
    with open(filename, newline='', encoding=from_encoding) as file:
        with NamedTemporaryFile('w', encoding=to_encoding, newline='', 
                                dir=os.path.dirname(filename)) as tmpfile:
            copyfileobj(file, tmpfile)
            tmpfile.delete = False
    os.replace(tmpfile.name, filename) # rename tmpfile -> filename

for path in csv_files:
    convert(path, "cp866", "utf-8")

Upvotes: 0

autodidacticon
autodidacticon

Reputation: 1358

You're reopening the file during every iteration.

for line in f.readlines():
        lineno +=1
        if lineno == 1 :
            continue
        #move the following line outside of the for block
        file_source = open(name, mode='w', encoding='utf-8', errors='ignore')

Upvotes: 1

Related Questions