python csv add column name - python

Can you help me please. how to add column name to csv file with python.
dirname = os.path.dirname(os.path.abspath(__file__))
csvfilename = os.path.join(dirname, 'csvfile.csv')
file_exists = os.path.isfile(csvfilename)
f = open(csvfilename,'a')
f.write(list[0] + ';' + '\r\n')
f.close()

may be you can add a header like this?
with open(csvfilename, 'wt', newline ='') as file:
write_header = csv.writer(file, delimiter=',')
write_header.writerow(i for i in list[0])

Since you just want to modify a single line of the file there isn't a need to run this all through a CSV processor. Its generally best not to read and write to the same file. You can create a temporary file and make the changes to the top of the file before copying the bulk.
import shutil
dirname = os.path.dirname(os.path.abspath(__file__))
csvfilename = os.path.join(dirname, 'csvfile.csv')
tmpfilename = os.path.join(dirname, 'csvfile.csv.tmp')
file_exists = os.path.isfile(csvfilename)
with open(csvfilename, 'rb') as f_in, open(tmpfilename, 'wb') as f_out:
# discard current header
next(f_in)
# write new header
f_out.write("colname\r\n".encode())
# copy the rest of the file
shutil.copyfileobj(f_in, f_out)
# replace original csv with fixed
shutil.move(tmpfilename, csvfilename)

Related

Move files listed in csv file?

I have been trying to use the following code to move files that are listed in a csv list. But at most it will copy the last file in the list but not the rest.
I keep hitting this wall with every example I have seen listed what am I doing wrong?
My CVS list will have a list like:
12355,12355.jpg
Here's my code
import os
import shutil
import csv
keys={}
with open('shuttle_image.csv', 'r') as f:
reader = csv.reader(f, delimiter = ',')
for rowDict in reader:
keys[rowDict[0]] = rowDict[1]
print (rowDict)
dir_src = 'C:\\Users\\Willie\\Desktop\\Suppliers Dropship\\hunting\\'
dir_dst = 'C:\\image\\'
for file in os.listdir(dir_src):
src_file = os.path.join(dir_src, file)
dst_file = os.path.join(dir_dst, file)
if file in rowDict[1]:
shutil.move(src_file, dst_file)
I think doing something like this will work (untested):
import os
import shutil
import csv
keys={}
with open('shuttle_image.csv', 'r') as f:
reader = csv.reader(f, delimiter=',')
for rowDict in reader:
keys[rowDict[0]] = rowDict[1]
print(rowDict) # if desired
valid_files = set(keys.values()) # file names found in csv
dir_src = 'C:\\Users\\Willie\\Desktop\\Suppliers Dropship\\hunting\\'
dir_dst = 'C:\\image\\'
for file in os.listdir(dir_src):
if file in valid_files:
src_file = os.path.join(dir_src, file)
dst_file = os.path.join(dir_dst, file)
shutil.move(src_file, dst_file)
As an optimization, unless you need the keys dictionary for other processing, you could change the first part so it just creates the valid_files set variable used in the second for loop:
valid_files = set() # empty set
with open('shuttle_image.csv', 'r') as f:
for rowDict in csv.reader(f, delimiter=','):
valid_files |= {rowDict[1]} # add file name to set
print(rowDict) # if desired
The reason why it's only the last file that could be copied (if it was) is because in this line:
if file in rowDict[1]:
you are referencing rowDict outside of the first for-loop. So at that execution moment, it contains the last value of this loop.
If I understand correctly what you are trying to do you could try something like this (untested code):
import os
import shutil
import csv
dir_src = 'C:\\Users\\Willie\\Desktop\\Suppliers Dropship\\hunting\\'
dir_dst = 'C:\\image\\'
with open('shuttle_image.csv', 'r') as f:
reader = csv.reader(f, delimiter = ',')
for rowDict in reader:
id, filename = rowDict
src_file = os.path.join(dir_src, filename)
if os.path.exists(src_file):
shutil.move(src_file, dir_dst)
So instead of:
Constructing a dictionary with all the values in your CSV file
Somehow check for every file in your source directory that it is included in your dictionary (which is what I interpreted you were trying to do)
And move it if it does.
You could:
For every file extracted from your CSV, check that it exists in your source directory.
If it does, you move it to the destination directory.
Is that what you were trying to do ?
[And if the filename stays the same, you only need to specify the destination directory for the second argument of shutil.move()]

grab headers from multiple tsv/csv files

I have a list of tsv files where I am looking to grab column headers for all the files.
with open(os.path.abspath('reference/file.tsv'), 'rU') as file:
reader = csv.reader(file)
row1 = next(reader)
Currently, this snippet only reads 1 file where I have a list of files that needs to be parsed.
dir_path = os.path.abspath('reference/')
files = os.listdir(dir_path)
The name of the files are listed in files. How do I loop through the list of files and grab only the column headers for each file?
I try this and it works.
import os
import csv
dir_path = os.path.abspath('reference/')
files = os.listdir(dir_path)
for f in files:
with open(dir_path +'/'+f, 'rU') as file:
reader = csv.reader(file)
row1 = next(reader)
print row1
The files variable in your code is the content of the reference folder, meaning all files and subfolders of the folder. They are returned in a list of strings, containing only the file or subfolder name. This means that you'll have to prefix the path yourself.
Example:
dir_path = os.path.abspath('reference/')
files = os.listdir(dir_path)
for file in files:
# Skip non-files
if not os.path.isfile(file):
continue
with open(os.path.join(dir_path, file), 'rU') as f:
reader = csv.reader(f)
row1 = next(reader)
An alternative using the pathlib module:
for file in Path('reference/').glob('*'):
if not file.is_file():
continue
with open(str(file.resolve()), 'rU') as f:
reader = csv.reader(f)
row1 = next(reader)
Wouldn't you be better off in reading the first line of each of those files, appending them to a list and then passing them to csvreader?
Example:
lines = []
with open(str(file.resolve()), 'rU') as f:
lines.append(f.readline())
reader = csv.reader(lines)
for row in reader:
# whatever you want to do with the parsed lines

How to rename file names using text file in python

I need to rename a bunch of files in a folder with new name reference from a text file. Can you please give an example for this.
My New Names In a Text file:
1BA
1BB
1BC
1BD
1BE
1BF
1C0
1C1
1C2
1C3
Like this.
Updated Code:
import csv
import os
with open('names.txt') as f2:
filedata = f2.read().split(",")
os.rename(filedata[0].strip(), filedata[1].strip())
f2.close()
f2 = open ('Lines.txt','w')
f2.write(filedata)
f2.close()
What about using a CSV (comma separated) file for input in the format oldPath, newPath and do the following:
import csv
import os
with open('names.csv') as csvfile:
reader = csv.reader(csvfile)
for row in reader:
oldPath = row[0]
newPath = row[1]
os.rename(oldPath, newPath)
Alternatively, if you want to move the file to another directory/filesystem you can have a look at shutil.move
# Create old.txt and rename.txt
# Do not include file path inside the txt files
# For each line, write a filename include the extension
from pathlib import Path
import os
import sys
print("enter path of folder")
path = input()
oldList = []
with open(path + "\\old.txt", "r", encoding="utf8", errors='ignore') as readtxt:
for f in readtxt:
fname = f.rstrip()
oldList.append(fname)
# i is index of oldList
i = 0
newList = []
with open(path + "\\rename.txt", "r", encoding="utf8", errors='ignore') as readtxt:
for f in readtxt:
newName = f.rstrip()
os.rename(path + "\\" + oldList[i], path + "\\" + newName)
i += 1

batch process text to csv using python

I need some help with converting a number of text files to csv files. All my text files are in one folder and I want to convert them to csv files into another folder. The names of individual files should remain the same. Below is the script I got so far...converting an individual file works fine but to work on all the files within a folder is where I am stuck. Any help will be appreciated.
import csv
import os
directory = raw_input("INPUT Folder:")
output = raw_input("OUTPUT Folder")
txt_files = directory
csv_files = output
try:
for txt_file in txt_files:
in_txt = csv.reader(open(txt_file, "rb"), delimiter = '=')
for csv_file in csv_files:
out_csv = csv.writer(open(csv_file, 'wb'))
out_csv.writerows(in_txt)
except:
print ()
glob.glob() is perfectly suited for the task. Also, use with context manager when working with files:
import csv
import glob
import os
directory = raw_input("INPUT Folder:")
output = raw_input("OUTPUT Folder:")
txt_files = os.path.join(directory, '*.txt')
for txt_file in glob.glob(txt_files):
with open(txt_file, "rb") as input_file:
in_txt = csv.reader(input_file, delimiter='=')
filename = os.path.splitext(os.path.basename(txt_file))[0] + '.csv'
with open(os.path.join(output, filename), 'wb') as output_file:
out_csv = csv.writer(output_file)
out_csv.writerows(in_txt)

python shutil: only copy part of the file

The code is to read the xls file from a directory, convert it to csv file and copy it to another directory.
filePath = os.path.join('.', 'attachments')
filePaths = [f for f in os.listdir(filePath) if os.path.isfile(os.path.join(filePath, f)) and f.endswith('.xls')]
for f in filePaths:
wb = xlrd.open_workbook(os.path.join(filePath, f))
sheet = wb.sheet_by_index(0)
filename = f + '.csv'
fp = open(os.path.join(filePath, filename), 'wb')
wr = csv.writer(fp, quoting=csv.QUOTE_ALL)
for rownum in xrange(sheet.nrows):
wr.writerow(sheet.row_values(rownum))
fp.close
shutil.copy(os.path.join('.', 'attachments', filename), new_directory)
The result is:
The xls file is successfully converted to a csv file, but in the new_directory, the copied file only contains part of the csv file.
For example, the original csv file has 30 rows, but in the copied file, there is only 17 rows. Any idea of why this would happen?
Here's your problem:
fp.close
You need to call the close method, not just reference it as a method. So:
fp.close()
However, it will make your life easier if you use with statements instead of trying to figure out where to explicitly close everything:
with open(os.path.join(filePath, filename), 'wb') as fp:
wr = csv.writer(fp, quoting=csv.QUOTE_ALL)
for rownum in xrange(sheet.nrows):
wr.writerow(sheet.row_values(rownum))

Categories