We Keep Coding

os.write() appends file instead of overwriting, but O_APPEND isn't used [duplicate]

I have the following code:
import re
#open the xml file for reading:
file = open('path/test.xml','r+')
#convert to string:
data = file.read()
file.write(re.sub(r"<string>ABC</string>(\s+)<string>(.*)</string>",r"<xyz>ABC</xyz>\1<xyz>\2</xyz>",data))
file.close()
where I'd like to replace the old content that's in the file with the new content. However, when I execute my code, the file "test.xml" is appended, i.e. I have the old content follwed by the new "replaced" content. What can I do in order to delete the old stuff and only keep the new?

You need seek to the beginning of the file before writing and then use file.truncate() if you want to do inplace replace:
import re
myfile = "path/test.xml"
with open(myfile, "r+") as f:
data = f.read()
f.seek(0)
f.write(re.sub(r"<string>ABC</string>(\s+)<string>(.*)</string>", r"<xyz>ABC</xyz>\1<xyz>\2</xyz>", data))
f.truncate()
The other way is to read the file then open it again with open(myfile, 'w'):
with open(myfile, "r") as f:
data = f.read()
with open(myfile, "w") as f:
f.write(re.sub(r"<string>ABC</string>(\s+)<string>(.*)</string>", r"<xyz>ABC</xyz>\1<xyz>\2</xyz>", data))
Neither truncate nor open(..., 'w') will change the inode number of the file (I tested twice, once with Ubuntu 12.04 NFS and once with ext4).
By the way, this is not really related to Python. The interpreter calls the corresponding low level API. The method truncate() works the same in the C programming language: See http://man7.org/linux/man-pages/man2/truncate.2.html

file='path/test.xml'
with open(file, 'w') as filetowrite:
filetowrite.write('new content')
Open the file in 'w' mode, you will be able to replace its current text save the file with new contents.

Using truncate(), the solution could be
import re
#open the xml file for reading:
with open('path/test.xml','r+') as f:
#convert to string:
data = f.read()
f.seek(0)
f.write(re.sub(r"<string>ABC</string>(\s+)<string>(.*)</string>",r"<xyz>ABC</xyz>\1<xyz>\2</xyz>",data))
f.truncate()

import os#must import this library
if os.path.exists('TwitterDB.csv'):
os.remove('TwitterDB.csv') #this deletes the file
else:
print("The file does not exist")#add this to prevent errors
I had a similar problem, and instead of overwriting my existing file using the different 'modes', I just deleted the file before using it again, so that it would be as if I was appending to a new file on each run of my code.

See from How to Replace String in File works in a simple way and is an answer that works with replace
fin = open("data.txt", "rt")
fout = open("out.txt", "wt")
for line in fin:
fout.write(line.replace('pyton', 'python'))
fin.close()
fout.close()

in my case the following code did the trick
with open("output.json", "w+") as outfile: #using w+ mode to create file if it not exists. and overwrite the existing content
json.dump(result_plot, outfile)

Using python3 pathlib library:
import re
from pathlib import Path
import shutil
shutil.copy2("/tmp/test.xml", "/tmp/test.xml.bak") # create backup
filepath = Path("/tmp/test.xml")
content = filepath.read_text()
filepath.write_text(re.sub(r"<string>ABC</string>(\s+)<string>(.*)</string>",r"<xyz>ABC</xyz>\1<xyz>\2</xyz>", content))
Similar method using different approach to backups:
from pathlib import Path
filepath = Path("/tmp/test.xml")
filepath.rename(filepath.with_suffix('.bak')) # different approach to backups
content = filepath.read_text()
filepath.write_text(re.sub(r"<string>ABC</string>(\s+)<string>(.*)</string>",r"<xyz>ABC</xyz>\1<xyz>\2</xyz>", content))

Python _csv Error: line contains NULL byte

This is my code:
filepath = sys.argv[1]
csvdata = list(csv.reader(open(filepath)))
How can I fix it?
I saved my excel file as a csv and receieved this error:
_csv.Error: new-line character seen in unquoted field - do you need to open the file in universal-newline mode?

An Excel file is not a csv file. First export / save the file as csv.
There are differences between python versions about whether to open the file as binary or text. This has relevance to how newlines are handled.
In Python 2.x, open as binary: open(filepath, 'rb')
In Python 3.x, don't : open('file.csv', 'r')
The second part I learned from this link about reading in csv files
For some operating systems (Mac OS for sure) you need to open with the mode 'rU' See: this link with same problem specifically on Mac OS

try this (put actual location of csv file)...
with open('c:\pytest.csv', 'rb') as csvfile:
data = csv.reader(csvfile)
mylist = list (data)
print mylist

from tkFileDialog import askopenfilename
import csv
filename = askopenfilename()
with open(filename, 'rb') as csvfile:
data = csv.reader(csvfile)
mylist = list (data)
print mylist

Skip header when writing to an open CSV

I am compiling a load of CSVs into one. The first CSV contains the headers, which I am opening in write mode (maincsv). I am then making a list of all the others which live in a different folder and attempting to append them to the main one.
It works, however it just writes over the headings. I just want to start appending from line 2. I'm sure it's pretty simple but all the next(), etc. things I try just throw errors. The headings and data are aligned if that helps.
import os, csv
maincsv = open(r"C:\Data\OSdata\codepo_gb\CodepointUK.csv", 'w', newline='')
maincsvwriter = csv.writer(maincsv)
curdir = os.chdir(r"C:\Data\OSdata\codepo_gb\Data\CSV")
csvlist = os.listdir()
csvfiles = []
for file in csvlist:
path = os.path.abspath(file)
csvfiles.append(path)
for incsv in csvfiles:
opencsv = open(incsv)
csvreader = csv.reader(opencsv)
for row in csvreader:
maincsvwriter.writerow(row)
maincsv.close()

To simplify things I have the code load all the files in the directory the python code is run in. This will get the first line of the first .csv file and use it as the header.
import os
count=0
collection=open('collection.csv', 'a')
files=[f for f in os.listdir('.') if os.path.isfile(f)]
for f in files:
if ('.csv' in f):
solecsv=open(f,'r')
if count==0:
# assuming header is 1 line
header=solecsv.readline()
collection.write(header)
for x in solecsv:
if not (header in x):
collection.write(x)
collection.close()

Python csv not writing to file

I am trying to write to a .tsv file using python's CSV module, this is my code so far
file_name = "test.tsv"
TEMPLATE = "template.tsv"
fil = open(file_name, "w")
# Added suggested change
template = csv.DictReader(open(TEMPLATE, 'r'), delimiter='\t')
new_file = csv.DictWriter(fil, fieldnames=template.fieldnames, delimiter='\t')
new_file.writeheader()
basically TEMPLATE is a file that will contain the headers for the file, so i read the headers using DictReader and pass the fieldnames to DictWriter, as far as i know the code is fine, the file test.tsv is being created but for some reason the headers are not being written.
Any help as to why this is happening is appreciated, thanks.

DictReader's first argument should be a file object (create with open()), cf. http://docs.python.org/py3k/library/csv.html#csv.DictReader
You forgot open() for the TEMPLATE file.
import csv
file_name = "test.tsv"
TEMPLATE = "template.tsv"
fil = open(file_name, "w")
# you forgot this line, which will open the file
template_file = open(TEMPLATE, 'r')
template = csv.DictReader(template_file, delimiter='\t')
new_file = csv.DictWriter(fil, fieldnames=template.fieldnames, delimiter='\t')
new_file.writeheader()

Try to give DictReader opened file instead of file name:
csv.DictReader(open(TEMPLATE, 'r'), delimiter='\t')
Same for the writer, but opened for writing.

Add file name as last column of CSV file

I have a Python script which modifies a CSV file to add the filename as the last column:
import sys
import glob
for filename in glob.glob(sys.argv[1]):
file = open(filename)
data = [line.rstrip() + "," + filename for line in file]
file.close()
file = open(filename, "w")
file.write("\n".join(data))
file.close()
Unfortunately, it also adds the filename to the header (first) row of the file. I would like the string "ID" added to the header instead. Can anybody suggest how I could do this?

Have a look at the official csv module.

Here are a few minor notes on your current code:
It's a bad idea to use file as a variable name, since that shadows the built-in type.
You can close the file objects automatically by using the with syntax.
Don't you want to add an extra column in the header line, called something like Filename, rather than just omitting a column in the first row?
If your filenames have commas (or, less probably, newlines) in them, you'll need to make sure that the filename is quoted - just appending it won't do.
That last consideration would incline me to use the csv module instead, which will deal with the quoting and unquoting for you. For example, you could try something like the following code:
import glob
import csv
import sys
for filename in glob.glob(sys.argv[1]):
data = []
with open(filename) as finput:
for i, row in enumerate(csv.reader(finput)):
to_append = "Filename" if i == 0 else filename
data.append(row+[to_append])
with open(filename,'wb') as foutput:
writer = csv.writer(foutput)
for row in data:
writer.writerow(row)
That may quote the data slightly differently from your input file, so you might want to play with the quoting options for csv.reader and csv.writer described in the documentation for the csv module.
As a further point, you might have good reasons for taking a glob as a parameter rather than just the files on the command line, but it's a bit surprising - you'll have to call your script as ./whatever.py '*.csv' rather than just ./whatever.py *.csv. Instead, you could just do:
for filename in sys.argv[1:]:
... and let the shell expand your glob before the script knows anything about it.
One last thing - the current approach you're taking is slightly dangerous, in that if anything fails when writing back to the same filename, you'll lose data. The standard way of avoiding this is to instead write to a temporary file, and, if that was successful, rename the temporary file over the original. So, you might rewrite the whole thing as:
import csv
import sys
import tempfile
import shutil
for filename in sys.argv[1:]:
tmp = tempfile.NamedTemporaryFile(delete=False)
with open(filename) as finput:
with open(tmp.name,'wb') as ftmp:
writer = csv.writer(ftmp)
for i, row in enumerate(csv.reader(finput)):
to_append = "Filename" if i == 0 else filename
writer.writerow(row+[to_append])
shutil.move(tmp.name,filename)

You can try:
data = [file.readline().rstrip() + ",id"]
data += [line.rstrip() + "," + filename for line in file]

You can try changing your code, but using the csv module is recommended. This should give you the result you want:
import sys
import glob
import csv
filename = glob.glob(sys.argv[1])[0]
yourfile = csv.reader(open(filename, 'rw'))
csv_output=[]
for row in yourfile:
if len(csv_output) != 0: # skip the header
row.append(filename)
csv_output.append(row)
yourfile = csv.writer(open(filename,'w'),delimiter=',')
yourfile.writerows(csv_output)

Use the CSV module that comes with Python.
import csv
import sys
def process_file(filename):
# Read the contents of the file into a list of lines.
f = open(filename, 'r')
contents = f.readlines()
f.close()
# Use a CSV reader to parse the contents.
reader = csv.reader(contents)
# Open the output and create a CSV writer for it.
f = open(filename, 'wb')
writer = csv.writer(f)
# Process the header.
header = reader.next()
header.append('ID')
writer.writerow(header)
# Process each row of the body.
for row in reader:
row.append(filename)
writer.writerow(row)
# Close the file and we're done.
f.close()
# Run the function on all command-line arguments. Note that this does no
# checking for things such as file existence or permissions.
map(process_file, sys.argv[1:])
You can run this as follows:
blair#blair-eeepc:~$ python csv_add_filename.py file1.csv file2.csv

you can use fileinput to do in place editing
import sys
import glob
import fileinput
for filename in glob.glob(sys.argv[1]):
for line in fileinput.FileInput(filename,inplace=1) :
if fileinput.lineno()==1:
print line.rstrip() + " ID"
else
print line.rstrip() + "," + filename