Removing all BOMs from file with multiple BOMs - python

I have a text file containing multiple lines beginning with a byte order mark. Passing encoding='utf-8-sig' to open removes the BOM at the start of the file but all subsequent BOMs remain. Is there a more correct way to remove these than this:
import codecs
filepath = 'foo.txt'
bom_len = len(codecs.BOM_UTF8)
def remove_bom(s):
s = str.encode(s)
if codecs.BOM_UTF8 in s:
s = s[bom_len:]
return s.decode()
try:
with open(filepath, encoding='utf-8-sig') as file_object:
for line in file_object:
line = line.rstrip()
line = remove_bom(line)
if line != '':
print([line[0]])
except FileNotFoundError:
print('No file found at ' + filepath)

I'm having similar problems.
This kinda helped me:
import codecs
with open(path, "rb") as infile:
bytecontent = infile.read()
bytecontent = bytecontent.replace(codecs.BOM_UTF8, b"")

Related

How to replace two different lines of text?

I need to create a file that changes the date and name of a .txt, but I can only change one or the other with this code I found on the internet, can anyone give me any tips?
Print
import os
from ast import Str
file = open("example.txt", "r")
replacement = ""
data = "02/07/2022"
name = "Alan"
for line in file:
line = line.strip()
changes = line.replace("__/__/____", data)
replacement = replacement + changes + "\n"
file.close()
fout = open("final.txt", "w")
fout.write(replacement)
fout.close()
You don't need to do this a line a time. You can replace that entire program with this:
data = "02/07/2022"
name = "Alan"
text = open("example.txt", "r").read().replace("__/__/____", data)
open("final.txt", "w").write(text)

How to read a file and print it, skipping certain lines in python

I would like to read a file line by line but ignore any that contain a colon (:).
I'm currently opening one file, reading it, and trying to print it before eventually put it into a new file.
def shoppinglist():
infile = open('filename.txt')
contents = infile.readline()
output = open('outputfilename.txt', 'w')
while ":" not in contents:
contents = infile.readline()
else:
contentstr = contents.split()
print(contentstr)
output.write(contents)
infile.close()
output.close()
As it is, one line is repeated over and over and over.
Try:
def shoppinglist():
contents = ""
with open('filename.txt', 'r') as infile:
for line in infile.readlines():
if ":" not in line:
contents += line
with open('outputfilename.txt', 'w') as output_file:
output_file.write(contents)

replace line if found or append - python

I have text that is key-value pairs separated by '='. I would like to replace the line if the key matches. if not, i would like to append it at the bottom. I've tried several ways, including:
def split_command_key_and_value(command):
if '=' in command:
command2 = command.split('=')
return command2
def test(command, path):
command2 = split_command_key_and_value(command)
pattern = command2[0]
myfile = open(path,'r') # open file handle for read
# use r'', you don't need to replace '\' with '/'
result = open(path, 'w') # open file handle for write
for line in myfile:
line = line.strip() # it's always a good behave to strip what you read from files
if pattern in line:
line = command # if match, replace line
result.write(line) # write every line
myfile.close() # don't forget to close file handle
result.close()
I know the above is just to replace text, but it deletes the text in the file, and I can't see why. Could someone point me in the right direction?
Thanks
Update:
I'm almost there, but some of my lines have similar keys, so mutiple lines are matching when only 1 should. I've tried to incorporate a regex boundary in my loop with no luck. My code is below. Does anyone have a suggestion?
There is some text in the file that isn't key-value, so I would like to skip that.
def modify(self, name, value):
comb = name + ' ' + '=' + ' ' + value + '\n'
with open('/file/', 'w') as tmpstream:
with open('/file/', 'r') as stream:
for line in stream:
if setting_name in line:
tmpstream.write(comb)
else:
tmpstream.write(line)
I think I got it. See code below.
def modify(self, name, value):
comb = name + ' ' + '=' + ' ' + value + '\n'
mylist = []
with open('/file/', 'w') as tmpstream:
with open('/file/', 'r') as stream:
for line in stream:
a = line.split()
b = re.compile('\\b'+name+'\\b')
if len(a) > 0:
if b.search(a[0]):
tmpstream.write(comb)
else:
tmpstream.write(line)
I spoke too soon. It stops at the key-value I provide. So, it only writes one line, and doesn't write the lines that don't match.
def modify(name, value):
comb = name + ' ' + '=' + ' ' + value + '\n'
mylist = []
with open('/file1', 'w') as tmpstream:
with open('/file2', 'r') as stream:
for line in stream:
a = line.split()
b = re.compile('\\b'+name+'\\b')
if len(a) > 0:
if b.search(a[0]):
tmpstream.write(comb)
else:
tmpstream.write(line)
Can anyone see the issue?
Because when you open file for writing
result = open(path, 'w') # open file handle for write
you just erase it content. Try to write in different file and after all work done replace old file with new one. Or read all data into memory and then process it and write to file.
with open(path) as f:
data = f.read()
with open(path, 'w') as f:
for l in data:
# make job here
first of all you are reading an writing the same file ...
you could first read it all and the write line by line
with open(path,'r') as f:
myfile = f.read() # read everything in the variable "myfile"
result = open(path, 'w') # open file handle for write
for line in myfile.splitlines(): # process the original file content 1 line at a time
# as before
I strongly recommend reading python's documentation on how to read and write files.
If you open an existing file in write-mode open(path, 'w'), its content will be erased:
mode can be (...) 'w' for only writing (an existing file with the same name will be erased)
To replace a line in python you can have a look at this: Search and replace a line in a file in Python
Here is one the solutions provided there adapted to your context (tested for python3):
from tempfile import mkstemp
from shutil import move
from os import close
def test(filepath, command):
# Split command into key/value
key, _ = command.split('=')
matched_key = False
# Create a temporary file
fh, tmp_absolute_path = mkstemp()
with open(tmp_absolute_path, 'w') as tmp_stream:
with open(filepath, 'r') as stream:
for line in stream:
if key in line:
matched_key = True
tmp_stream.write(command + '\n')
else:
tmp_stream.write(line)
if not matched_key:
tmp_stream.write(command + '\n')
close(fh)
move(tmp_absolute_path, filepath)
Note that with the code above every line that matches key (key=blob or blob=key) will be replaced.

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")
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')
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")
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()

file crawler OSError

I want this to recursively call the next file, listed in a manually inputted file. It is the first word listed in the file.
The current error messege is:
OSError: [Errno 22] Invalid argument: 'file1.txt\n'.
This is my current code:
import os
def crawl(fname):
infile = open(fname, 'r')
if os.stat(fname)[6]==0:
return "Visiting {}".format(fname)
infile.close()
else:
print ("Visiting {}".format(fname))
lines = infile.read().splitlines()
nextfile = lines[0].strip()
for line in lines:
crawl(nextfile)
Try:
import os
def crawl(fname):
with open(fname, "r") as infile:
print("Visiting {}".format(fname))
if os.stat(fname).st_size:
lines = infile.read().splitlines()
for line in lines:
crawl(line)
I'm pretty sure the problem is that you're getting a newline at the end of the filename you are reading from the first file. You can easily fix it, by using the strip method to remove the newline:
nextfile = lines[0].strip()

Categories