I currently have code that is writing to a csv file, however, it keesp replacing the first row of the file and overwriting it instead of writing of it.
NOTE: I have this function inside a for loop inside main().
def write_csv_report(filename, region, data, current, server1, server2=False):
if not os.path.exists(os.path.dirname(filename)):
try:
dir = os.makedirs(os.path.dirname(filename))
header = ['region','old_dns_server', 'proposed_dns_server1', 'proposed_dns_server2']
data = [region, current, server1, server2]
with open(filename, 'a') as file:
writer = csv.writer(file)
writer.writerow(header)
writer.writerow(data)
except OSError as exc:
if exc.errno != errno.EEXIST:
raise
When I run this function in my script, it writes to the file but only one entry is added.
Is there any suggestions or solution where I can add multiple entries? I have looked at other sage questions and googled but it looks like I already have the necessary changes needed to achieve this outcome, not sure what I'm missing.
For csv.writer (and csv.reader), you need to open the file with newline=''.
You also write the header every time, which is a bit odd.
Here's a minimal example that does more-or-less what you want:
import csv
header = ['region','old_dns_server', 'proposed_dns_server1', 'proposed_dns_server2']
data1 = ['foo', 'bar', 'bar', 'quux']
data2 = ['foo1', 'bar1', 'bar1', 'quux2']
filename = 'test.csv'
with open(filename, 'w', newline='') as file:
writer = csv.writer(file)
writer.writerow(header)
writer.writerow(data1)
with open(filename, 'a', newline='') as file:
writer = csv.writer(file)
writer.writerow(data2)
giving:
region,old_dns_server,proposed_dns_server1,proposed_dns_server2
foo,bar,bar,quux
foo1,bar1,bar1,quux2
Related
i am having troubles on this python error.
I want to save changing variables to an csv file, however while the code runs again with an different variable it overwrites the previous one. I do not have the variables predetermined, they are generated while the code runs, so every time the loop will loop the program there will a different email passed.
Here is my code:
import csv
def hello(hme):
header = ['email']
data = [hme]
with open('countries.csv', 'w', encoding='UTF8', newline='') as f:
writer = csv.writer(f)
writer.writerow(header)
writer.writerows(data)
hello(["test#icloud.com"])
Thank you!
you should open the file as append, instead of write:
'a' instead of 'w'
import csv
def hello(hme):
header = ['email']
data = [hme]
with open('countries.csv', 'a', encoding='UTF8', newline='') as f:
writer = csv.writer(f)
writer.writerow(header)
writer.writerows(data)
hello(["test#icloud.com"])
Just replace 'w' by 'a' where 'w' writes in file (override) while 'a' appends the file whenever you write in it.
with open('countries.csv', 'a', encoding='UTF8', newline='') as f:
For the header "email" just write it before you add the loop of emails to do not duplicate it
Read the file contents first; add the new data; write the data to a file.
def hello(hme):
try:
with open('countries.csv', encoding='UTF8', newline='') as f:
stuff = list(csv.reader(f))
except FileNotFoundError:
# this must be the first time the function was called
stuff = [['email']]
stuff.append([hme])
with open('countries.csv', 'w', encoding='UTF8', newline='') as f:
writer = csv.writer(f)
writer.writerows(stuff)
If your file really only has one column you don't really need to use the csv module. Just append the new line to the file.
# assumes header is present
def hello(hme):
with open('countries.csv', 'a', encoding='UTF8') as f:
f.write(hme + '\n')
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).
I am trying to attempt something that I have not before within python.
The code below collects data from my test database and put it into a text under my headers of 'Test1','Test2','Test3'. This is working fine.
What I am trying to attempt now is to add a header (on top of the current header) and footer to the file.
python code:
file = 'file.txt'
header_names = {'t1':'Test1', 't2': 'Test2','t3':'Test3'}
with open(file, 'w', newline='') as f:
w = csv.DictWriter(f, fieldnames=header_names.keys(), restval='', extrasaction='ignore')
w.writerow(header_names)
for doc in res['test']['test']:
my_dict = doc['test']
w.writerow(my_dict)
current file output using the above code.
file.txt
Test1,Test2,Test3
Bob,john,Male
Cat,Long,female
Dog,Short,Male
Case,Fast,Male
Nice,who,Male
ideal txt output.
{header}
Filename:file.txt
date:
{data}
Test1,Test2,Test3
Bob,john,Male
Cat,Long,female
Dog,Short,Male
Case,Fast,Male
Nice,who,Male
{Footer}
this file was generated by using python.
the {header}, {data} and {footer} is not needed within the file that is just to make clear what is needed. i hope this makes sense.
Something like this
import csv
from datetime import date
# prepare some sample data
data = [['Bob', 'John', 'Male'],
['Cat', 'Long', 'Female']]
fieldnames = ['test1', 'test2', 'test3']
data = [dict(zip(fieldnames, row)) for row in data]
# actual part that writes to a file
with open('spam.txt', 'w', newline='') as f:
f.write('filename:spam.txt\n')
f.write(f'date:{date.today().strftime("%Y%m%d")}\n\n')
wrtr = csv.DictWriter(f, fieldnames = fieldnames)
wrtr.writeheader()
wrtr.writerows(data)
f.write('\nwritten with python\n')
Output in the file:
filename:spam.txt
date:20190321
test1,test2,test3
Bob,John,Male
Cat,Long,Female
written with python
Now, all that said, do you really need to write header and footer. It will just break a nicely formatted csv file and would require extra effort later on when reading it.
Or if you prefer - is the csv format what best suits your needs? Maybe using json would be better...
vardate= datetime.datetime.now().strftime("%x")
file = 'file.txt'
header_names = {'t1':'Test1', 't2': 'Test2','t3':'Test3'}
with open(file, 'w', newline='') as f:
f.seek(0,0) //This will move cursor to start position of file
f.writelines("File Name: ", file)
f.writelines("date: ", vardate)
f.writelines(".Try out next..")
w = csv.DictWriter(f, fieldnames=header_names.keys(), restval='',
extrasaction='ignore')
w.writerow(header_names)
for doc in res['test']['test']:
my_dict = doc['test']
w.writerow(my_dict)
f.seek(0,2)
f.writelines("This is generated using Python")
I am pretty new to python and trying to run a script to edit csv files. The problem I am facing is that I need to split the csv files into smaller pieces(as they are large files and getting memory errors) and then run another script to edit the files but when im trying to append these two scripts and run the test, the script is reading only the first small file and not reading the rest of the files.
For example: When I split the main csv file, the files are getting split and the names come as big-1.csv,big-2.csv. Then when the script is picking up the files to edit, only big-1.csv is getting edited and rest are not getting edited.
The script is:
import csv
from csv import DictWriter
divisor = 990
outfileno = 1
outfile = None
with open('MOCK_DATA.csv', 'r', newline='') as infile:
infile_iter = csv.reader(infile, delimiter='\t')
header = next(infile_iter)
for index, row in enumerate(infile_iter):
if index % divisor == 0:
if outfile:
outfile.close()
outfilename = 'big-{}.csv'.format(outfileno)
outfile = open(outfilename, 'w', newline='')
outfileno += 1
writer = csv.writer(outfile, delimiter='\t', quoting=csv.QUOTE_NONE)
writer.writerow(header)
writer.writerow(row)
# Don't forget to close the last file
if outfile:
outfile.close()
#export the data
# with correct quoting, and that you are stuck with what you have.
for i in range(1,2):
with open("big-" + str(i) + ".csv") as people_file:
next(people_file)
corrected_people = []
for person_line in people_file:
chomped_person_line = person_line.rstrip()
person_tokens = chomped_person_line.split(",")
# check that each field has the expected type
try:
corrected_person = {
"id": person_tokens[0],
"first_name":person_tokens[1],
"last_name": "".join(person_tokens[2:-3]),
"email":person_tokens[-3],
"gender":person_tokens[-2],
"ip_address":person_tokens[-1]
}
if not corrected_person["ip_address"].startswith(
"") and corrected_person["ip_address"] !="n/a":
raise ValueError
corrected_people.append(corrected_person)
except (IndexError, ValueError):
# print the ignored lines, so manual correction can be performed later.
print("Could not parse line: " + chomped_person_line)
with open("fix-" + str(i) + ".csv", "w") as corrected_people_file:
writer = DictWriter(
corrected_people_file,
fieldnames=[
"id","first_name","last_name","email","gender","ip_address"
],delimiter=',')
writer.writeheader()
writer.writerows(corrected_people)
I think this maybe an issue with reading the smaller files in the for loop. The script is running without any error. Please help.
So I have a program that creates CSV from .Json.
First I load the json file.
f = open('Data.json')
data = json.load(f)
f.close()
Then I go through it, looking for a specific keyword, if I find that keyword. I'll write everything related to that in a .csv file.
for item in data:
if "light" in item:
write_light_csv('light.csv', item)
This is my write_light_csv function :
def write_light_csv(filename,dic):
with open (filename,'a') as csvfile:
headers = ['TimeStamp', 'light','Proximity']
writer = csv.DictWriter(csvfile, delimiter=',', lineterminator='\n',fieldnames=headers)
writer.writeheader()
writer.writerow({'TimeStamp': dic['ts'], 'light' : dic['light'],'Proximity' : dic['prox']})
I initially had wb+ as the mode, but that cleared everything each time the file was opened for writing. I replaced that with a and now every time it writes, it adds a header. How do I make sure that header is only written once?.
You could check if file is already exists and then don't call writeheader() since you're opening the file with an append option.
Something like that:
import os.path
file_exists = os.path.isfile(filename)
with open (filename, 'a') as csvfile:
headers = ['TimeStamp', 'light', 'Proximity']
writer = csv.DictWriter(csvfile, delimiter=',', lineterminator='\n',fieldnames=headers)
if not file_exists:
writer.writeheader() # file doesn't exist yet, write a header
writer.writerow({'TimeStamp': dic['ts'], 'light': dic['light'], 'Proximity': dic['prox']})
Just another way:
with open(file_path, 'a') as file:
w = csv.DictWriter(file, my_dict.keys())
if file.tell() == 0:
w.writeheader()
w.writerow(my_dict)
You can check if the file is empty
import csv
import os
headers = ['head1', 'head2']
for row in interator:
with open('file.csv', 'a') as f:
file_is_empty = os.stat('file.csv').st_size == 0
writer = csv.writer(f, lineterminator='\n')
if file_is_empty:
writer.writerow(headers)
writer.writerow(row)
I would use some flag and run a check before writing headers! e.g.
flag=0
def get_data(lst):
for i in lst:#say list of url
global flag
respons = requests.get(i)
respons= respons.content.encode('utf-8')
respons=respons.replace('\\','')
print respons
data = json.loads(respons)
fl = codecs.open(r"C:\Users\TEST\Desktop\data1.txt",'ab',encoding='utf-8')
writer = csv.DictWriter(fl,data.keys())
if flag==0:
writer.writeheader()
writer.writerow(data)
flag+=1
print "You have written % times"%(str(flag))
fl.close()
get_data(urls)
Can you change the structure of your code and export the whole file at once?
def write_light_csv(filename, data):
with open (filename, 'w') as csvfile:
headers = ['TimeStamp', 'light','Proximity']
writer = csv.DictWriter(csvfile, delimiter=',', lineterminator='\n',fieldnames=headers)
writer.writeheader()
for item in data:
if "light" in item:
writer.writerow({'TimeStamp': item['ts'], 'light' : item['light'],'Proximity' : item['prox']})
write_light_csv('light.csv', data)
You can use the csv.Sniffer Class and
with open('my.csv', newline='') as csvfile:
if csv.Sniffer().has_header(csvfile.read(1024))
# skip writing headers
While using Pandas: (for storing Dataframe data to CSV file)
just add this check before setting header property if you are using an index to iterate over API calls to add data in CSV file.
if i > 0:
dataset.to_csv('file_name.csv',index=False, mode='a', header=False)
else:
dataset.to_csv('file_name.csv',index=False, mode='a', header=True)
Here's another example that only depends on Python's builtin csv package. This method checks that the header is what's expected or it throws an error. It also handles the case where the file doesn't exist or does exist but is empty by writing the header. Hope this helps:
import csv
import os
def append_to_csv(path, fieldnames, rows):
is_write_header = not os.path.exists(path) or _is_empty_file(path)
if not is_write_header:
_assert_field_names_match(path, fieldnames)
_append_to_csv(path, fieldnames, rows, is_write_header)
def _is_empty_file(path):
return os.stat(path).st_size == 0
def _assert_field_names_match(path, fieldnames):
with open(path, 'r') as f:
reader = csv.reader(f)
header = next(reader)
if header != fieldnames:
raise ValueError(f'Incompatible header: expected {fieldnames}, '
f'but existing file has {header}')
def _append_to_csv(path, fieldnames, rows, is_write_header: bool):
with open(path, 'a') as f:
writer = csv.DictWriter(f, fieldnames=fieldnames)
if is_write_header:
writer.writeheader()
writer.writerows(rows)
You can test this with the following code:
file_ = 'countries.csv'
fieldnames_ = ['name', 'area', 'country_code2', 'country_code3']
rows_ = [
{'name': 'Albania', 'area': 28748, 'country_code2': 'AL', 'country_code3': 'ALB'},
{'name': 'Algeria', 'area': 2381741, 'country_code2': 'DZ', 'country_code3': 'DZA'},
{'name': 'American Samoa', 'area': 199, 'country_code2': 'AS', 'country_code3': 'ASM'}
]
append_to_csv(file_, fieldnames_, rows_)
If you run this once you get the following in countries.csv:
name,area,country_code2,country_code3
Albania,28748,AL,ALB
Algeria,2381741,DZ,DZA
American Samoa,199,AS,ASM
And if you run it twice you get the following (note, no second header):
name,area,country_code2,country_code3
Albania,28748,AL,ALB
Algeria,2381741,DZ,DZA
American Samoa,199,AS,ASM
Albania,28748,AL,ALB
Algeria,2381741,DZ,DZA
American Samoa,199,AS,ASM
If you then change the header in countries.csv and run the program again, you'll get a value error, like this:
ValueError: Incompatible header: expected ['name', 'area', 'country_code2', 'country_code3'], but existing file has ['not', 'right', 'fieldnames']