header in csv file printing every other line - python

I've been working this problem way too long, please explain to me why the header keeps repeating in my output csv.
I have an input csv with this data:
name,house
"Abbott, Hannah",Hufflepuff
"Bell, Katie",Gryffindor
"Bones, Susan",Hufflepuff
"Boot, Terry",Ravenclaw
The problem requires reversing last and first name, separate name into two columns, and make a new header with 3 columns for the output csv. Here's what I have:
while True:
try:
# open file
with open(sys.argv[1]) as file:
# make reader
reader = csv.reader(file)
# skip first line (header row)
next(reader)
# for each row
for row in reader:
# identify name
name = row[0]
# split at ,
name = name.split(", ")
# create var last and first, identify var house
last = name[0]
first = name[1]
house = row[1]
# writing the new csv
with open(sys.argv[2], "a") as after:
writer = csv.DictWriter(after, fieldnames=["first", "last", "house"])
# HEADER ONLY NEEDS TO OCCUR ONCE
writer.writeheader()
writer.writerow({"first": first, "last": last, "house": house})
sys.exit(0)
my output csv:
first,last,house
Hannah,Abbott,Hufflepuff
first,last,house
Katie,Bell,Gryffindor
first,last,house
Susan,Bones,Hufflepuff
I've tried removing the while loop, unindenting and indenting, writing a row manually with the header names (which caused errors). Please help. Thanks!

You can add a variable that hold whether a header was printed or not, ex write_header
while True:
try:
write_header = True
# open file
with open(sys.argv[1]) as file:
# make reader
reader = csv.reader(file)
# skip first line (header row)
next(reader)
# for each row
for row in reader:
# identify name
name = row[0]
# split at ,
name = name.split(", ")
# create var last and first, identify var house
last = name[0]
first = name[1]
house = row[1]
# writing the new csv
with open(sys.argv[2], "a") as after:
writer = csv.DictWriter(after, fieldnames=["first", "last", "house"])
# HEADER ONLY NEEDS TO OCCUR ONCE
if write_header:
writer.writeheader()
write_header = False
writer.writerow({"first": first, "last": last, "house": house})
sys.exit(0)
See how i used write_header
On an other note, you can refactor your code to open the csv writer before the for loop, write headers there, then write values as you do now without the need to reopen the file each time you want to write a row

Related

How to print only a the content of a cell in a specific row from a csv file in Python

I'm new to Python so excuse me if my question is kind of dumb.
I send some data into a csv file (I'm making a password manager). So I send this to this file (in this order), the name of the site, the e-mail corresponding and finally the password.
But I would like to print all the names already written in the csv file but here is my problem, for the first row it does print the whole row but for the following rows it works just well.
Here is my code, I hope u can help me with this.
csv_file = csv.reader(open('mycsvfile.csv', 'r'), delimiter=';')
try :
print("Here are all the sites you saved :")
for row in csv_file :
print(row[0])
except :
print("Nothing already saved")
Maybe it can help, but here is how I wrote my data into the csv file:
#I encrypt the email and the password thanks to fernet and an already written key
#I also make sure that the email is valid
file = open('key.key', 'rb')
key = file.read()
file.close()
f = Fernet(key)
website = input("web site name : \n")
restart = True
while restart :
mail = input("Mail:\n")
a = isvalidEmail(mail)
if a == True :
print("e-mail validated")
restart = False
else :
print("Wrong e-mail")
pws = input("password :\n")
psw_bytes = psw.encode()
mail_bytes = mail.encode()
psw_encrypted_in_bytes = f.encrypt(psw_bytes)
mail_encrypted_in_bytes = f.encrypt(mail_bytes)
mail_encrypted_str = mail_encrypted_in_bytes.decode()
psw_encrypted_str = psw_encrypted_in_bytes.decode()
f = open('a.csv', 'a', newline='')
tup1 = (website, mail_encrypted_str, psw_encrypted_str)
writer = csv.writer(f, delimiter = ';')
writer.writerow(tup1)
print("Saved ;)")
f.close()
return
And here is my output (I have already saved data)
Output (First, you see the name of the ws with the email and the psw encrypted then just the name which is what I want
I finally succeed, instead of using a csv.Reader, i used a csv.DictReader and as all the names i'm looking for are on the same column, i juste have to use the title of the columns.
So here is the code :
with open('mycsv.csv', newline='') as csvfile:
data = csv.DictReader(csvfile)
print("Websites")
print("---------------------------------")
for row in data:
print(row['The_title_of_my_column'])
make list from csv.reader()
rows = [row for row in csv_file]
and now you can get element by identifier using rows as list of lists
rows[id1][id2]

How to remove specifc row from csv file using python

I am working on one program and trying to achieve following functionalities.
add new student
Remove student based on id
here is my code
from csv import writer
import csv
def add(file_name, list_of_elem):
# Open file in append mode
with open(file_name, 'a+', newline='') as write_obj:
# Create a writer object from csv module
csv_writer = writer(write_obj)
# Add contents of list as last row in the csv file
csv_writer.writerow(list_of_elem)
def remove():
id = input("Enter ID : ")
with open('students.csv', 'rb') as inp, open('students.csv', 'wb') as out:
writer = csv.writer(out)
for row in csv.reader(inp):
if row[0] != id:
writer.writerow(row)
# List of strings
row_contents = [11,'mayur','Java','Tokyo','Morning']
# Append a list as new line to an old csv file
add('students.csv', row_contents)
remove()
add function works properly but when i tried remove function it removes all existing entries.Could anyone please help me.
First I will show the code and below I will left some comments about the changes.
from csv import writer
import csv
def add(file_name, list_of_elem):
# Open file in append mode
with open(file_name, 'a+', newline = '') as write_obj:
# Create a writer object from csv module
csv_writer = writer(write_obj)
# Add contents of list as last row in the csv file
csv_writer.writerow(list_of_elem)
def remove():
idt = input("Enter ID : ")
with open('students.csv', 'r') as inp:
newrows = []
data = csv.reader(inp)
for row in data:
if row[0] != idt:
newrows.append(row)
with open('students.csv', 'w') as out:
csv_writer = writer(out)
for row in newrows:
csv_writer.writerow(row)
def display():
with open('students.csv','r') as f:
data = csv.reader(f)
for row in data:
print(row)
# List of strings
row_contents = [10,'mayur','Java','Tokyo','Morning']
add('students.csv', row_contents)
row_contents = [11,'mayur','Java','Tokyo','Morning']
add('students.csv', row_contents)
row_contents = [12,'mayur','Java','Tokyo','Morning']
add('students.csv', row_contents)
# Append a list as new line to an old csv file
display()
remove()
If your file is a CSV, you should use a text file, instead of a binary one.
I changed the name of the variable id to ìdt because id is built-in to return the identity of an object and it's not a good practice overwrite built-in functions.
To remove only rows with an specific idt you should read all the file, store into a var (list), remove what you want to delete and only after that save the result.
You should use a temporary file instead of opening and writing to the same file simultaneously. Checkout this answer: https://stackoverflow.com/a/17646958/14039323

How to read a CSV and adapt + write every row to another CSV?

I tried this but it just writes "lagerungskissen kleinkind,44" several times instead of transferring every row.
keyword = []
rank = []
rank = list(map(int, rank))
data = []
with open("keywords.csv", "r") as file:
for line in file:
data = line.strip().replace('"', '').split(",")
keyword = data[0]
rank = data[3]
import csv
with open("mynew.csv", "w", newline="") as f:
thewriter = csv.writer(f)
thewriter.writerow(["Keyword", "Rank"])
for row in keyword:
thewriter.writerow([keyword, rank])
It should look like this
This is writing the same line in your output CSV because the final block is
for row in keyword:
thewriter.writerow([keyword, rank])
Note that the keyword variable doesn't change in the loop, but the row does. You're writing that same [keyword, rank] line len(keyword) times.
I would use the csv package to do the reading and the writing for this. Something like
import csv
input_file = '../keywords.csv'
output_file = '../mynew.csv'
# open the files
fIn = open(input_file, 'r', newline='')
fOut = open(output_file, 'w')
csvIn = csv.reader(fIn, quotechar='"') # check the keyword args in the docs!
csvOut = csv.writer(fOut)
# write a header, then write each row one at a time
csvOut.writerow(['Keyword', 'Rank'])
for row in csvIn:
keyword = row[0]
rank = row[3]
csvOut.writerow([keyword, rank])
# and close the files
fOut.close()
fIn.close()
As as side note, you could write the above using the with context manager (e.g. with open(...) as file:). The answer here shows how to do it with multiple files (in this case fIn and fOut).

Add data to new column and first row in CSV file

I have a python function that creates a CSV file using a Postgresql copy statement. I need to add a new column to this spreadsheet called 'UAL' with an example value in the first row of say 30,000, but without editing the copy statement. This is the current code:
copy_sql = 'COPY (
SELECT
e.name AS "Employee Name",
e.title AS "Job Title"
e.gross AS "Total Pay",
e.total AS "Total Pay & Benefits",
e.year AS "Year",
e.notes AS "Notes",
j.name AS "Agency",
e.status AS "Status"
FROM employee_employee e
INNER JOIN jurisdiction_jurisdiction j on e.jurisdiction_id = j.id
WHERE
e.year = 2011 AND
j.id = 4479
ORDER BY "Agency" ASC, "Total Pay & Benefits" DESC
)'
with open(path, 'w') as csvfile:
self.cursor.copy_expert(copy_sql, csvfile)
What I am trying to do is use something like csv.writer to add content like this:
with open(path, 'w') as csvfile:
self.cursor.copy_expert(copy_sql, csvfile)
writer = csv.writer(csvfile)
writer.writerow('test123')
But this is adding the text to the last row. I am also unsure how to add a new header column. Any advice?
adding a header is easy: write the header before the call to copy_expert.
with open(path, 'w') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(["my","super","header"])
self.cursor.copy_expert(copy_sql, csvfile)
But adding a column cannot be done without re-reading the file again and add your info on each row, so the above solution doesn't help much.
If the file isn't too big and fits in memory, you could write the sql output to a "fake" file:
import io
fakefile = io.StringIO()
self.cursor.copy_expert(copy_sql, fakefile)
now rewind the file and parse it as csv, add the extra column when writing it back
import csv
fakefile.seek(0)
with open(path, 'w', newline="") as csvfile:
writer = csv.writer(csvfile)
reader = csv.reader(fakefile) # works if copy_expert uses "," as separator, else change it
writer.writerow(["my","super","header","UAL"])
for row in reader:
writer.writerow(row+[30000])
or instead of the inner loop:
writer.writerows(row+[30000] for row in reader)
And if the file is too big, write it in a temp file, and proceed the same way (less performant)

Python: add value and write output

I need to get information from a list and add a column year from name. I still not sure how to add one field 'year' in record. Can I use append?
And about output file, I just need use outputcsv.writerow(records) isn't it?
This is a part of code that I stuck:
filenames = ('babyQld2010.csv',
'babyQld2011.csv',
'babyQld2012.csv',
'babyQld2012.csv',
'babyQld2014.csv')
outFile = open('babyQldAll.csv','w')
csvFile_out = csv.writer(outFile, delimiter=',')
for filename in filenames:
name, ext = filename.split('.')
year = name[-4:] #extract year from file names
records = extract_names(filename)
# Get (name, count, gender) from list "records",
# and add value of "year" and write into output file (using "for" loop )
Output file look like:
2010,Lola,69,Girl
And input, I have 5 file babyQld2010.csv, babyQld2011.csv, babyQld2012.csv, babyQld2012.csv, babyQld2014.csv which contains:
Mia,425,William,493
and I have to sort it in format and I already done it and save in list 'records'
Lola,69,Girl
now I need to add one field 'year' on 'record' list and export csv file.
This is my full code:
import csv
def extract_names(filename):
''' Extract babyname, count, gender from a csv file,
and return the data in a list.
'''
inFile = open(filename, 'rU')
csvFile = csv.reader(inFile, delimiter=',')
# Initialization
records = []
rowNum = 0
for row in csvFile:
if rowNum != 0:
# +++++ You code here ++++
# Read each row of csv file and save information in list 'records'
# as (name, count, gender)
records.append([row[0], row[1], "Female"])
records.append([row[2], row[3], "Male"])
print('Process each row...')
rowNum += 1
inFile.close()
return(records)
#### Start main program #####
filenames = ('babyQld2010.csv',
'babyQld2011.csv',
'babyQld2012.csv',
'babyQld2012.csv',
'babyQld2014.csv')
with open('babyQldAll.csv','w') as outFile:
csvFile_out = csv.writer(outFile, delimiter=',')
for filename in filenames:
name, ext = filename.split('.')
year = name.split('.')[0][-4:] #extract year from file names
records = extract_names(filename)
for record in records:
csvFile_out.write([year] + record)
print("Write in csv file...")
outFile.close()
To get the year from the csv file you can simply split the string at '.' and then take the last four characters from the first part of the split. Example -
>>> s = 'babyQld2010.csv'
>>> s.split('.')[0][-4:]
'2010'
Then just simply iterate over your list of records, which you say is correct, for each list within in, use list contatenation to create a new list with year at the start and write that to csv file.
I would also suggest that you use with statement for opening the file to write to (and even in the function where you are reading from the other csv files). Example -
filenames = ('babyQld2010.csv',
'babyQld2011.csv',
'babyQld2012.csv',
'babyQld2012.csv',
'babyQld2014.csv')
with open('babyQldAll.csv','w') as outFile:
csvFile_out = csv.writer(outFile, delimiter=',')
for filename in filenames:
name, ext = filename.split('.')
year = name.split('.')[0][-4:] #extract year from file names
records = extract_names(filename)
for record in records:
csvFile_out.writerow([year] + record)
Yes, you can just append the year column to each row as you read it in from your source files. You can read in & write out each row as a dictionary so that you can use your existing column headers to address the data if you need to massage it on the way through.
Using the csv.DictWriter() method you specify your headers (fieldnames) when you set it up. You can then write them out with the writeheader() method.
import csv
file_list = ['babyQld2010.csv',
'babyQld2011.csv',
'babyQld2012.csv',
'babyQld2012.csv',
'babyQld2014.csv']
outFile = open('babyQldAll.csv', 'wb')
csv_writer = csv.DictWriter(outFile,
fieldnames=['name','count','gender','year'])
csv_write_out.writeheader()
for a_file in file_list:
name,ext = a_file.split('.')
year = name[-4:]
with open(a_file, 'rb') as inFile:
csv_read_in = csv.DictReader(inFile)
for row in csv_read_in:
row['year'] = year
csv_writer.writerow(row)
outfile.close()
Hope this helps.

Categories