I Would like to remove lines 3 to 15 from file 'Database.csv'. Please see my code below, this code is works only for one line i added range, but is didn't work. ;/
filename = 'Database.csv'
line_to_delete = [3:15]
initial_line = 1
file_lines = {}
with open(filename) as f:
content = f.readlines()
for line in content:
file_lines[initial_line] = line.strip()
initial_line += 1
f = open(filename, "w")
for line_number, line_content in file_lines.items():
if line_number != line_to_delete:
f.write('{}\n'.format(line_content))
f.close()
print('Deleted line: {}'.format(line_to_delete))
You can use csv library for doing this.
import csv
file=open("Database.csv",'rb')
final_file=open("Database_edited",'wb')
writer=csv.writer(final_file)
line_no=1 # for knowing the line number
for row in csv.reader(file):
if(line_no<=3 or line_no>=15):
writer.writerow(row)
line_no=line_no+1
file.close()
final_file.close()
This way Database_edited will have your required file
Here's an easy way to do using the csv module and the range() function:
mport csv
filename = 'Database.csv'
startline, endline = 3, 15 # Inclusive.
with open(filename, 'r', newline='') as f:
content = [row for i,row in enumerate(csv.reader(f), 1)
if i not in range(startline, endline+1)]
filename2 = 'Database2.csv' # Write to different file for testing.
with open(filename2, 'w', newline='') as f:
csv.writer(f).writerows(content)
print('lines deleted')
#Tested code on Python 3.6
import csv
filename = r'C:\Users\91852\Desktop\New folder (2)\lines.csv'
start_skip_row = 3
stop_skip_row = 13
def readCSVFile(file_name: str, start: int, stop: int) -> list:
with open(file_name, 'r') as file_content:
data_after_deletion = [line.replace('\n', '') for idx, line in enumerate(file_content) if
not start - 1 <= idx < stop]
print(data_after_deletion)
return data_after_deletion
def writeCSVFile(data: list) -> None:
with open('file_after_deletion', 'w', newline='') as csvFile:
writer = csv.writer(csvFile)
writer.writerows(data)
data_after_deletion = readCSVFile(filename, start_skip_row, stop_skip_row)
writeCSVFile(data_after_deletion)
Related
I have a csv file in which I want to change the written data. But when writing data, I get a blank line at the end of the file. How do I delete the last blank line?
import csv
accounts = []
account = []
sep = ";"
#get data to accounts
with open(filename, 'r') as csvfile:
csvreader = csv.reader(csvfile)
for row in csvreader:
text = [row]
uncuttext = sep.join(row)
account = uncuttext.split(sep)
accounts.append(account)
#edit data
def edit(position: str, rate: float):
for x in range(len(accounts)):
plat = float(ucty[x][5])
if accounts[x][7] == position:
plat = round(plat * rate)
accounts[x][5] = str(plat)
#save data
def save():
with open(filename, 'w', newline='') as csvfile:
csvwriter = csv.writer(csvfile, delimiter=sep, quoting=csv.QUOTE_NONE)
csvwriter.writerows(accounts)
I tried How write csv file without new line character in last line? but it didn't work.
Are you referring to something like this?
1,truck,purple
2,car,red
3,van,blue
--blank line
Try something like this where you remove the newline from the last record on read in.
with open(filename, 'r') as csvfile:
lines = csvfile.readlines()
last_line = lines[len(lines)-1]
lines[len(lines)-1] = last_line.rstrip()
for row in lines:
....
....
#save data
def save():
with open(filename, 'w', newline='', escapechar='', lineterminator='') as csvfile:
....
heres my little program. at the end i want to write the names and passwords
into csv file like this:
Jack,9978
Sara,1647
but i cant!? my program output is correct but when i write it into csv it goes like:
Jack9978,Sara1674
how will you fix it?
import hashlib
import csv
answer = []
usr_pas = []
with open('...', 'r') as f:
reader = csv.reader(f)
for word in reader:
usr_pas.append(word)
for i in range(999, 10000):
num = str(i)
m = hashlib.sha256()
m.update(num.encode('utf-8'))
hsh = m.hexdigest()
hash_dict = {hsh: num}
for key in list(hash_dict.items()):
for value in usr_pas:
if key[0] == value[1]:
answer.append(value[0] +','+ key[1])
file = open("...", 'w', newline='')
with file:
writer = csv.writer(file)
writer.writerow(i.strip().replace(',', '') for i in answer)
file.close()
what did i wrong!?
Try this (lines with comments are changed):
import hashlib
import csv
answer = []
usr_pas = []
with open('...', 'r') as f:
reader = csv.reader(f)
for word in reader:
usr_pas.append(word)
for i in range(999, 10000):
num = str(i)
m = hashlib.sha256()
m.update(num.encode('utf-8'))
hsh = m.hexdigest()
hash_dict = {hsh: num}
for key in list(hash_dict.items()):
for value in usr_pas:
if key[0] == value[1]:
answer.append(value[0] +','+ key[1] + '\n') #added '\n' at the end
file = open("...", 'w', newline='')
with file:
writer = csv.writer(file)
writer.writerow(i for i in answer) #removed i.replace
file.close()
I guess you want a csv file with multiple lines instead of one. If so, my suggestion is to use csv.csvwriter.writerows instead of csv.csvwriter.writerow. The latter is designed to write a single row. See the official document here. Indeed multiple lines might be created with \n manipulator, it means a single line with multiple elements that contains "new line", which seems awkward.
Since we can use the default delimiter (comma), we just need to manage each element in the line as a tuple (or a list). Answers should be added into list answer like this:
answer.append((value[0], key[1]))
while we write rows in this way:
writer.writerows(answer)
Let's put them together:
import hashlib
import csv
answer = []
usr_pas = []
with open('...', 'r') as f:
reader = csv.reader(f)
for word in reader:
usr_pas.append(word)
for i in range(999, 10000):
num = str(i)
m = hashlib.sha256()
m.update(num.encode('utf-8'))
hsh = m.hexdigest()
hash_dict = {hsh: num}
for key in list(hash_dict.items()):
for value in usr_pas:
if key[0] == value[1]:
# answer.append(value[0] +','+ key[1])
answer.append((value[0], key[1]))
file = open("...", 'w', newline='')
with file:
writer = csv.writer(file)
# writer.writerow(i.strip().replace(',', '') for i in answer)
writer.writerows(answer)
file.close()
I have a large csv file for which i need to split the file. I have
managed to split the file using the below python code:
import csv
divisor = 500000
outfileno = 1 outfile = None
with open('file_temp.txt', 'r') as infile:
for index, row in enumerate(csv.reader(infile)):
if index % divisor == 0:
if outfile is not None:
outfile.close()
outfilename = 'big-{}.csv'.format(outfileno)
outfile = open(outfilename, 'w')
outfileno += 1
writer = csv.writer(outfile)
writer.writerow(row)
The problem i'm facing is that the file header is not getting copied
to the rest of the files. Can you please let me know how can i modify
my code to add the headers in the different splitted files.
You just need to cache the header row and then write it out for each CSV file, something like:
import csv
divisor = 500000
outfileno = 1
outfile = None
try:
with open('file_temp.txt', 'r') as infile:
infile_iter = csv.reader(infile)
header = next(infile_iter)
for index, row in enumerate(infile_iter):
if index % divisor == 0:
if outfile is not None:
outfile.close()
outfilename = 'big-{}.csv'.format(outfileno)
outfile = open(outfilename, 'w')
outfileno += 1
writer = csv.writer(outfile)
writer.writerow(header)
writer.writerow(row)
finally:
# Don't forget to close the last file
if outfile is not None:
outfile.close()
Since you're only working with lines, you don't really need to use the CSV module, here's a version that works without it:
divisor = 500000
outfileno = 1
outfile = None
try:
with open('file_temp.txt', 'r') as infile:
header = next(infile)
for index, row in enumerate(infile):
if index % divisor == 0:
if outfile is not None:
outfile.close()
outfilename = 'big-{}.csv'.format(outfileno)
outfile = open(outfilename, 'w')
outfileno += 1
outfile.write(header)
outfile.write(row)
finally:
# Don't forget to close the last file
if outfile is not None:
outfile.close()
This is one file result.csv:
M11251TH1230
M11543TH4292
M11435TDS144
This is another file sample.csv:
M11435TDS144,STB#1,Router#1
M11543TH4292,STB#2,Router#1
M11509TD9937,STB#3,Router#1
M11543TH4258,STB#4,Router#1
Can I write a Python program to compare both the files and if line in result.csv matches with the first word in the line in sample.csv, then append 1 else append 0 at every line in sample.csv?
import pandas as pd
d1 = pd.read_csv("1.csv",names=["Type"])
d2 = pd.read_csv("2.csv",names=["Type","Col2","Col3"])
d2["Index"] = 0
for x in d1["Type"] :
d2["Index"][d2["Type"] == x] = 1
d2.to_csv("3.csv",header=False)
Considering "1.csv" and "2.csv" are your csv input files and "3.csv" is the result you needed
The solution using csv.reader and csv.writer (csv module):
import csv
newLines = []
# change the file path to the actual one
with open('./data/result.csv', newline='\n') as csvfile:
data = csv.reader(csvfile)
items = [''.join(line) for line in data]
with open('./data/sample.csv', newline='\n') as csvfile:
data = list(csv.reader(csvfile))
for line in data:
line.append(1 if line[0] in items else 0)
newLines.append(line)
with open('./data/sample.csv', 'w', newline='\n') as csvfile:
writer = csv.writer(csvfile)
writer.writerows(newLines)
The sample.csv contents:
M11435TDS144,STB#1,Router#1,1
M11543TH4292,STB#2,Router#1,1
M11509TD9937,STB#3,Router#1,0
M11543TH4258,STB#4,Router#1,0
With only one column, I wonder why you made it as a result.csv. If it is not going to have any more columns, a simple file read operation would suffice. Along with converting the data from result.csv to dictionary will help in quick run as well.
result_file = "result.csv"
sample_file = "sample.csv"
with open(result_file) as fp:
result_data = fp.read()
result_dict = dict.fromkeys(result_data.split("\n"))
"""
You can change the above logic, in case you have very few fields on csv like this:
result_data = fp.readlines()
result_dict = {}
for result in result_data:
key, other_field = result.split(",", 1)
result_dict[key] = other_field.strip()
"""
#Since sample.csv is a real csv, using csv reader and writer
with open(sample_file, "rb") as fp:
sample_data = csv.reader(fp)
output_data = []
for data in sample_data:
output_data.append("%s,%d" % (data, data[0] in result_dict))
with open(sample_file, "wb") as fp:
data_writer = csv.writer(fp)
data_writer.writerows(output_data)
The following snippet of code will work for you
import csv
with open('result.csv', 'rb') as f:
reader = csv.reader(f)
result_list = []
for row in reader:
result_list.extend(row)
with open('sample.csv', 'rb') as f:
reader = csv.reader(f)
sample_list = []
for row in reader:
if row[0] in result_list:
sample_list.append(row + [1])
else:
sample_list.append(row + [0]
with open('sample.csv', 'wb') as f:
writer = csv.writer(f)
writer.writerows(sample_list)
I have written a small python code where it will read a sample csv file and copy its first column to a temp csv file. Now when I try to compare that temporary file with another text file and try to write result to another file called result file, The file is created but with empty content.
But when i tested it in chunks, It is working fine
import csv
f = open("sample.csv", "r")
reader = csv.reader(f)
data = open("temp1.csv", "w")
w = csv.writer(data)
for row in reader:
my_row = []
my_row.append(row[0])
w.writerow(my_row)
with open('temp1.csv', 'r') as file1:
with open('serialNumber.txt', 'r') as file2:
same = set(file1).intersection(file2)
with open('result.txt', 'w') as file_out:
for line in same:
file_out.write(line)
print line
sample.csv
M11435TDS144,STB#1,Router#1
M11543TH4292,STB#2,Router#1
M11509TD9937,STB#3,Router#1
M11543TH4258,STB#4,Router#1
serialNumber.txt
G1A114042400571
M11543TH4258
M11251TH1230
M11435TDS144
M11543TH4292
M11509TD9937
You should close the output file (temp1.csv) before you can read data from it.
import csv
f = open("sample.csv", "r")
reader = csv.reader(f)
data = open("temp1.csv", "w")
w = csv.writer(data)
for row in reader:
my_row = []
my_row.append(row[0])
w.writerow(my_row)
data.close() # <--- Should close it before reading it in the same program !!
with open('temp1.csv', 'r') as file1:
with open('serialNumber.txt', 'r') as file2:
same = set(file1).intersection(file2)
with open('result.txt', 'w') as file_out:
for line in same:
file_out.write(line)
print line
Points regarding code:
data file handle is not closed. data.close() after writing to temp1.csv.
In your code, same = set(file1).intersection(file2), you are directly passing file handle file2 to intersection. It expects list. This is exact problem is. It should be same = set(file1.readlines()).intersection(file2.readlines())
Working Code:
import csv
f = open("sample.csv", "r")
reader = csv.reader(f)
data = open("temp1.csv", "wb")
w = csv.writer(data)
for row in reader:
my_row = []
if len(row) != 0:
my_row.append(row[0])
w.writerow(my_row)
#File should be closed
data.close()
with open('temp1.csv', 'r') as file1:
with open('serialNumber.txt', 'r') as file2:
tmp_list = (file1.readlines())
ser_list = (file2.readlines())
same = set(file1.readlines()).intersection(file2.readlines())
with open('result.txt', 'w') as file_out:
for line in same:
file_out.write(line)
Content of temp1.csv:
M11435TDS144
M11543TH4292
M11509TD9937
M11543TH4258
Content of result.txt :
M11543TH4258
M11543TH4292
M11435TDS144
You can use with for opening files sample.csv and temp1.csv as below.
import csv
with open("sample.csv") as f:
with open("temp1.csv",'wb') as data:
reader = csv.reader(f)
w = csv.writer(data)
for row in reader:
my_row = []
my_row.append(row[0])
w.writerow(my_row)
with open('temp1.csv', 'r') as file1:
with open('serialNumber.txt', 'r') as file2:
same = set(file1.readlines()).intersection(file2.readlines())
with open('result.txt', 'w') as file_out:
for line in same:
file_out.write(line)