How to write to a CSV line by line? - python

I have data which is being accessed via http request and is sent back by the server in a comma separated format, I have the following code :
site= 'www.example.com'
hdr = {'User-Agent': 'Mozilla/5.0'}
req = urllib2.Request(site,headers=hdr)
page = urllib2.urlopen(req)
soup = BeautifulSoup(page)
soup = soup.get_text()
text=str(soup)
The content of text is as follows:
april,2,5,7
may,3,5,8
june,4,7,3
july,5,6,9
How can I save this data into a CSV file.
I know I can do something along the lines of the following to iterate line by line:
import StringIO
s = StringIO.StringIO(text)
for line in s:
But i'm unsure how to now properly write each line to CSV
EDIT---> Thanks for the feedback as suggested the solution was rather simple and can be seen below.
Solution:
import StringIO
s = StringIO.StringIO(text)
with open('fileName.csv', 'w') as f:
for line in s:
f.write(line)


General way:
##text=List of strings to be written to file
with open('csvfile.csv','wb') as file:
for line in text:
file.write(line)
file.write('\n')
OR
Using CSV writer :
import csv
with open(<path to output_csv>, "wb") as csv_file:
writer = csv.writer(csv_file, delimiter=',')
for line in data:
writer.writerow(line)
OR
Simplest way:
f = open('csvfile.csv','w')
f.write('hi there\n') #Give your csv text here.
## Python will convert \n to os.linesep
f.close()


You could just write to the file as you would write any normal file.
with open('csvfile.csv','wb') as file:
for l in text:
file.write(l)
file.write('\n')
If just in case, it is a list of lists, you could directly use built-in csv module
import csv
with open("csvfile.csv", "wb") as file:
writer = csv.writer(file)
writer.writerows(text)


I would simply write each line to a file, since it's already in a CSV format:
write_file = "output.csv"
with open(write_file, "wt", encoding="utf-8") as output:
for line in text:
output.write(line + '\n')
I can't recall how to write lines with line-breaks at the moment, though :p
Also, you might like to take a look at this answer about write(), writelines(), and '\n'.


To complement the previous answers, I whipped up a quick class to write to CSV files. It makes it easier to manage and close open files and achieve consistency and cleaner code if you have to deal with multiple files.
class CSVWriter():
filename = None
fp = None
writer = None
def __init__(self, filename):
self.filename = filename
self.fp = open(self.filename, 'w', encoding='utf8')
self.writer = csv.writer(self.fp, delimiter=';', quotechar='"', quoting=csv.QUOTE_ALL, lineterminator='\n')
def close(self):
self.fp.close()
def write(self, elems):
self.writer.writerow(elems)
def size(self):
return os.path.getsize(self.filename)
def fname(self):
return self.filename
Example usage:
mycsv = CSVWriter('/tmp/test.csv')
mycsv.write((12,'green','apples'))
mycsv.write((7,'yellow','bananas'))
mycsv.close()
print("Written %d bytes to %s" % (mycsv.size(), mycsv.fname()))
Have fun


What about this:
with open("your_csv_file.csv", "w") as f:
f.write("\n".join(text))
str.join() Return a string which is the concatenation of the strings in iterable.
The separator between elements is
the string providing this method.


In my situation...
with open('UPRN.csv', 'w', newline='') as out_file:
writer = csv.writer(out_file)
writer.writerow(('Name', 'UPRN','ADMIN_AREA','TOWN','STREET','NAME_NUMBER'))
writer.writerows(lines)
you need to include the newline option in the open attribute and it will work
https://www.programiz.com/python-programming/writing-csv-files

Related

gzipped jsonlines file read and write in python

While this code reads and writes a jsonlines file. How to compress it? I tried directly using gzip.open but I am getting various errors.
import json
def dump_jsonl(data, output_path, append=False):
"""
Write list of objects to a JSON lines file.
"""
mode = 'a+' if append else 'w'
with open(output_path, mode, encoding='utf-8') as f:
for line in data:
json_record = json.dumps(line, ensure_ascii=False)
f.write(json_record + '\n')
print('Wrote {} records to {}'.format(len(data), output_path))
def load_jsonl(input_path) -> list:
"""
Read list of objects from a JSON lines file.
"""
data = []
with open(input_path, 'r', encoding='utf-8') as f:
for line in f:
data.append(json.loads(line.rstrip('\n|\r')))
print('Loaded {} records from {}'.format(len(data), input_path))
return data
This is what I am doing to compress but I am unable to read it.
def dump_jsonl(data, output_path, append=False):
with gzip.open(output_path, "a+") as f:
for line in data:
json_record = json.dumps(line, ensure_ascii = False)
encoded = json_record.encode("utf-8") + ("\n").encode("utf-8")
compressed = gzip.compress(encoded)
f.write(compressed)

Use the gzip module's compress function.
import gzip
with open('file.jsonl') as f_in:
with gzip.open('file.jsonl.gz', 'wb') as f_out:
f_out.writelines(f_in)
gzip.open() is for opening gzipped files, not jsonl.
Read:
gzip a file in Python
Python support for Gzip

Python requests data in file, line by line

I try to get the output of this request (https://api.opendota.com/api/players/7841909) in a file, line by line.
For some reason the output is stored in byte and not str, which I can change by str().
I tried to use a regualar expression to just store the information between the {} and also tried the csv module, which lead to just store digits.
What did I do wrong? The following version ignores the linebreak and the delimiters. :/
import requests
import csv
import re
dotaId = "7841909" #somit als string gespeichert
pfad = "https://api.opendota.com/api/players/" + dotaId + "/matches"
req = requests.get(pfad)
with open('%s.csv' % dotaId, 'w') as file:
clean_line = re.findall(r'\{(.*?)\}', req.text)
file.write(str(clean_line))

Your object clean_line is a list which you are writing as a one liner into the file.
It is better to use the csv writer module and write the content row by row:
with open('new_file.csv', 'w', newline='') as file:
writer = csv.writer(file, quotechar="'")
clean_lines = re.findall(r'\{(.*?)\}', req.text)
for line in clean_lines:
writer.writerow([str(line)])

How to convert CSV file to multiline JSON?

Here's my code, really simple stuff...
import csv
import json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("FirstName","LastName","IDNumber","Message")
reader = csv.DictReader( csvfile, fieldnames)
out = json.dumps( [ row for row in reader ] )
jsonfile.write(out)
Declare some field names, the reader uses CSV to read the file, and the filed names to dump the file to a JSON format. Here's the problem...
Each record in the CSV file is on a different row. I want the JSON output to be the same way. The problem is it dumps it all on one giant, long line.
I've tried using something like for line in csvfile: and then running my code below that with reader = csv.DictReader( line, fieldnames) which loops through each line, but it does the entire file on one line, then loops through the entire file on another line... continues until it runs out of lines.
Any suggestions for correcting this?
Edit: To clarify, currently I have: (every record on line 1)
[{"FirstName":"John","LastName":"Doe","IDNumber":"123","Message":"None"},{"FirstName":"George","LastName":"Washington","IDNumber":"001","Message":"Something"}]
What I'm looking for: (2 records on 2 lines)
{"FirstName":"John","LastName":"Doe","IDNumber":"123","Message":"None"}
{"FirstName":"George","LastName":"Washington","IDNumber":"001","Message":"Something"}
Not each individual field indented/on a separate line, but each record on it's own line.
Some sample input.
"John","Doe","001","Message1"
"George","Washington","002","Message2"

The problem with your desired output is that it is not valid json document,; it's a stream of json documents!
That's okay, if its what you need, but that means that for each document you want in your output, you'll have to call json.dumps.
Since the newline you want separating your documents is not contained in those documents, you're on the hook for supplying it yourself. So we just need to pull the loop out of the call to json.dump and interpose newlines for each document written.
import csv
import json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("FirstName","LastName","IDNumber","Message")
reader = csv.DictReader( csvfile, fieldnames)
for row in reader:
json.dump(row, jsonfile)
jsonfile.write('\n')

You can use Pandas DataFrame to achieve this, with the following Example:
import pandas as pd
csv_file = pd.DataFrame(pd.read_csv("path/to/file.csv", sep = ",", header = 0, index_col = False))
csv_file.to_json("/path/to/new/file.json", orient = "records", date_format = "epoch", double_precision = 10, force_ascii = True, date_unit = "ms", default_handler = None)

import csv
import json
file = 'csv_file_name.csv'
json_file = 'output_file_name.json'
#Read CSV File
def read_CSV(file, json_file):
csv_rows = []
with open(file) as csvfile:
reader = csv.DictReader(csvfile)
field = reader.fieldnames
for row in reader:
csv_rows.extend([{field[i]:row[field[i]] for i in range(len(field))}])
convert_write_json(csv_rows, json_file)
#Convert csv data into json
def convert_write_json(data, json_file):
with open(json_file, "w") as f:
f.write(json.dumps(data, sort_keys=False, indent=4, separators=(',', ': '))) #for pretty
f.write(json.dumps(data))
read_CSV(file,json_file)
Documentation of json.dumps()

I took #SingleNegationElimination's response and simplified it into a three-liner that can be used in a pipeline:
import csv
import json
import sys
for row in csv.DictReader(sys.stdin):
json.dump(row, sys.stdout)
sys.stdout.write('\n')

You can try this
import csvmapper
# how does the object look
mapper = csvmapper.DictMapper([
[
{ 'name' : 'FirstName'},
{ 'name' : 'LastName' },
{ 'name' : 'IDNumber', 'type':'int' },
{ 'name' : 'Messages' }
]
])
# parser instance
parser = csvmapper.CSVParser('sample.csv', mapper)
# conversion service
converter = csvmapper.JSONConverter(parser)
print converter.doConvert(pretty=True)
Edit:
Simpler approach
import csvmapper
fields = ('FirstName', 'LastName', 'IDNumber', 'Messages')
parser = CSVParser('sample.csv', csvmapper.FieldMapper(fields))
converter = csvmapper.JSONConverter(parser)
print converter.doConvert(pretty=True)

I see this is old but I needed the code from SingleNegationElimination however I had issue with the data containing non utf-8 characters. These appeared in fields I was not overly concerned with so I chose to ignore them. However that took some effort. I am new to python so with some trial and error I got it to work. The code is a copy of SingleNegationElimination with the extra handling of utf-8. I tried to do it with https://docs.python.org/2.7/library/csv.html but in the end gave up. The below code worked.
import csv, json
csvfile = open('file.csv', 'r')
jsonfile = open('file.json', 'w')
fieldnames = ("Scope","Comment","OOS Code","In RMF","Code","Status","Name","Sub Code","CAT","LOB","Description","Owner","Manager","Platform Owner")
reader = csv.DictReader(csvfile , fieldnames)
code = ''
for row in reader:
try:
print('+' + row['Code'])
for key in row:
row[key] = row[key].decode('utf-8', 'ignore').encode('utf-8')
json.dump(row, jsonfile)
jsonfile.write('\n')
except:
print('-' + row['Code'])
raise

Add the indent parameter to json.dumps
data = {'this': ['has', 'some', 'things'],
'in': {'it': 'with', 'some': 'more'}}
print(json.dumps(data, indent=4))
Also note that, you can simply use json.dump with the open jsonfile:
json.dump(data, jsonfile)

Use pandas and the json library:
import pandas as pd
import json
filepath = "inputfile.csv"
output_path = "outputfile.json"
df = pd.read_csv(filepath)
# Create a multiline json
json_list = json.loads(df.to_json(orient = "records"))
with open(output_path, 'w') as f:
for item in json_list:
f.write("%s\n" % item)

How about using Pandas to read the csv file into a DataFrame (pd.read_csv), then manipulating the columns if you want (dropping them or updating values) and finally converting the DataFrame back to JSON (pd.DataFrame.to_json).
Note: I haven't checked how efficient this will be but this is definitely one of the easiest ways to manipulate and convert a large csv to json.

As slight improvement to #MONTYHS answer, iterating through a tup of fieldnames:
import csv
import json
csvfilename = 'filename.csv'
jsonfilename = csvfilename.split('.')[0] + '.json'
csvfile = open(csvfilename, 'r')
jsonfile = open(jsonfilename, 'w')
reader = csv.DictReader(csvfile)
fieldnames = ('FirstName', 'LastName', 'IDNumber', 'Message')
output = []
for each in reader:
row = {}
for field in fieldnames:
row[field] = each[field]
output.append(row)
json.dump(output, jsonfile, indent=2, sort_keys=True)

def read():
noOfElem = 200 # no of data you want to import
csv_file_name = "hashtag_donaldtrump.csv" # csv file name
json_file_name = "hashtag_donaldtrump.json" # json file name
with open(csv_file_name, mode='r') as csv_file:
csv_reader = csv.DictReader(csv_file)
with open(json_file_name, 'w') as json_file:
i = 0
json_file.write("[")
for row in csv_reader:
i = i + 1
if i == noOfElem:
json_file.write("]")
return
json_file.write(json.dumps(row))
if i != noOfElem - 1:
json_file.write(",")
Change the above three parameter, everything will be done.

import csv
import json
csvfile = csv.DictReader('filename.csv', 'r'))
output =[]
for each in csvfile:
row ={}
row['FirstName'] = each['FirstName']
row['LastName'] = each['LastName']
row['IDNumber'] = each ['IDNumber']
row['Message'] = each['Message']
output.append(row)
json.dump(output,open('filename.json','w'),indent=4,sort_keys=False)

python csv write only certain fieldnames, not all

I must be missing something, but I don't get it. I have a csv, it has 1200 fields. I'm only interested in 30. How do you get that to work? I can read/write the whole shebang, which is ok, but i'd really like to just write out the 30. I have a list of the fieldnames and I'm kinda hacking the header.
How would I translate below to use DictWriter/Reader?
for file in glob.glob( os.path.join(raw_path, 'P12*.csv') ):
fileReader = csv.reader(open(file, 'rb'))
fileLength = len(file)
fileGeom = file[fileLength-7:fileLength-4]
table = TableValues[fileGeom]
filename = file.split(os.sep)[-1]
with open(out_path + filename, "w") as fileout:
for line in fileReader:
writer = csv.writer(fileout, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
if 'ID' in line:
outline = line.insert(0,"geometryTable")
else:
outline = line.insert(0,table) #"%s,%s\n" % (line, table)
writer.writerow(line)

Here's an example of using DictWriter to write out only fields you care about. I'll leave the porting work to you:
import csv
headers = ['a','b','d','g']
with open('in.csv','rb') as _in, open('out.csv','wb') as out:
reader = csv.DictReader(_in)
writer = csv.DictWriter(out,headers,extrasaction='ignore')
writer.writeheader()
for line in reader:
writer.writerow(line)
in.csv
a,b,c,d,e,f,g,h
1,2,3,4,5,6,7,8
2,3,4,5,6,7,8,9
Result (out.csv)
a,b,d,g
1,2,4,7
2,3,5,8

Read and overwrite a file in Python

Currently I'm using this:
f = open(filename, 'r+')
text = f.read()
text = re.sub('foobar', 'bar', text)
f.seek(0)
f.write(text)
f.close()
But the problem is that the old file is larger than the new file. So I end up with a new file that has a part of the old file on the end of it.

If you don't want to close and reopen the file, to avoid race conditions, you could truncate it:
f = open(filename, 'r+')
text = f.read()
text = re.sub('foobar', 'bar', text)
f.seek(0)
f.write(text)
f.truncate()
f.close()
The functionality will likely also be cleaner and safer using open as a context manager, which will close the file handler, even if an error occurs!
with open(filename, 'r+') as f:
text = f.read()
text = re.sub('foobar', 'bar', text)
f.seek(0)
f.write(text)
f.truncate()

The fileinput module has an inplace mode for writing changes to the file you are processing without using temporary files etc. The module nicely encapsulates the common operation of looping over the lines in a list of files, via an object which transparently keeps track of the file name, line number etc if you should want to inspect them inside the loop.
from fileinput import FileInput
for line in FileInput("file", inplace=1):
line = line.replace("foobar", "bar")
print(line)

Probably it would be easier and neater to close the file after text = re.sub('foobar', 'bar', text), re-open it for writing (thus clearing old contents), and write your updated text to it.

I find it easier to remember to just read it and then write it.
For example:
with open('file') as f:
data = f.read()
with open('file', 'w') as f:
f.write('hello')

To anyone who wants to read and overwrite by line, refer to this answer.
https://stackoverflow.com/a/71285415/11442980
filename = input("Enter filename: ")
with open(filename, 'r+') as file:
lines = file.readlines()
file.seek(0)
for line in lines:
value = int(line)
file.write(str(value + 1))
file.truncate()

Honestly you can take a look at this class that I built which does basic file operations. The write method overwrites and append keeps old data.
class IO:
def read(self, filename):
toRead = open(filename, "rb")
out = toRead.read()
toRead.close()
return out
def write(self, filename, data):
toWrite = open(filename, "wb")
out = toWrite.write(data)
toWrite.close()
def append(self, filename, data):
append = self.read(filename)
self.write(filename, append+data)

Try writing it in a new file..
f = open(filename, 'r+')
f2= open(filename2,'a+')
text = f.read()
text = re.sub('foobar', 'bar', text)
f.seek(0)
f.close()
f2.write(text)
fw.close()

Categories

Resources