Develop Reference

Txt file to excel conversion in python

I'm trying to convert text file to excel sheet in python. The txt file contains data in the below specified formart
Column names: reg no, zip code, loc id, emp id, lastname, first name. Each record has one or more error numbers. Each record have their column names listed above the values. I would like to create an excel sheet containing reg no, firstname, lastname and errors listed in separate rows for each record.
How can I put the records in excel sheet ? Should I be using regular expressions ? And how can I insert error numbers in different rows for that corresponding record?
Expected output:
Here is the link to the input file:
https://github.com/trEaSRE124/Text_Excel_python/blob/master/new.txt
Any code snippets or suggestions are kindly appreciated.

Here is a draft code. Let me know if any changes needed:
# import pandas as pd
from collections import OrderedDict
from datetime import date
import csv
with open('in.txt') as f:
with open('out.csv', 'wb') as csvfile:
spamwriter = csv.writer(csvfile, delimiter=',', quoting=csv.QUOTE_MINIMAL)
#Remove inital clutter
while("INPUT DATA" not in f.readline()):
continue
header = ["REG NO", "ZIP CODE", "LOC ID", "EMP ID", "LASTNAME", "FIRSTNAME", "ERROR"]; data = list(); errors = list()
spamwriter.writerow(header)
print header
while(True):
line = f.readline()
errors = list()
if("END" in line):
exit()
try:
int(line.split()[0])
data = line.strip().split()
f.readline() # get rid of \n
line = f.readline()
while("ERROR" in line):
errors.append(line.strip())
line = f.readline()
spamwriter.writerow(data + errors)
spamwriter.flush()
except:
continue
# while(True):
# line = f.readline()
Use python-2 to run. The errors are appended as subsequent columns. It's slightly complicated the way you want it. I can fix it if still needed
Output looks like:

You can do this using the openpyxl library which is capable of depositing items directly into a spreadsheet. This code shows how to do that for your particular situation.
NEW_PERSON, ERROR_LINE = 1,2
def Line_items():
with open('katherine.txt') as katherine:
for line in katherine:
line = line.strip()
if not line:
continue
items = line.split()
if items[0].isnumeric():
yield NEW_PERSON, items
elif items[:2] == ['ERROR', 'NUM']:
yield ERROR_LINE, line
else:
continue
from openpyxl import Workbook
wb = Workbook()
ws = wb.active
ws['A2'] = 'REG NO'
ws['B2'] = 'LASTNAME'
ws['C2'] = 'FIRSTNAME'
ws['D2'] = 'ERROR'
row = 2
for kind, data in Line_items():
if kind == NEW_PERSON:
row += 2
ws['A{:d}'.format(row)] = int(data[0])
ws['B{:d}'.format(row)] = data[-2]
ws['C{:d}'.format(row)] = data[-1]
first = True
else:
if first:
first = False
else:
row += 1
ws['D{:d}'.format(row)] = data
wb.save(filename='katherine.xlsx')
This is a screen snapshot of the result.

How to split code into smaller functions

I have an application that works. But in the interest of attempting to understand functions and python better. I am trying to split it out into various functions.
I"m stuck on the file_IO function. I'm sure the reason it does not work is because the main part of the application does not understand reader or writer. To better explain. Here is a full copy of the application.
Also I'm curious about using csv.DictReader and csv.DictWriter. Do either provide any advantages/disadvantages to the current code?
I suppose another way of doing this is via classes which honestly I would like to know how to do it that way as well.
#!/usr/bin/python
""" Description This script will take a csv file and parse it looking for specific criteria.
A new file is then created based of the original file name containing only the desired parsed criteria.
"""
import csv
import re
import sys
searched = ['aircheck', 'linkrunner at', 'onetouch at']
def find_group(row):
"""Return the group index of a row
0 if the row contains searched[0]
1 if the row contains searched[1]
etc
-1 if not found
"""
for col in row:
col = col.lower()
for j, s in enumerate(searched):
if s in col:
return j
return -1
#Prompt for File Name
def file_IO():
print "Please Enter a File Name, (Without .csv extension): ",
base_Name = raw_input()
print "You entered: ",base_Name
in_Name = base_Name + ".csv"
out_Name = base_Name + ".parsed.csv"
print "Input File: ", in_Name
print "OutPut Files: ", out_Name
#Opens Input file for read and output file to write.
in_File = open(in_Name, "rU")
reader = csv.reader(in_File)
out_File = open(out_Name, "wb")
writer = csv.writer(out_File, delimiter=',', quotechar='"', quoting=csv.QUOTE_ALL)
return (reader, writer)
file_IO()
# Read header
header = reader.next()
stored = []
writer.writerow([header[0], header[3]])
for i, row in enumerate(reader):
g = find_group(row)
if g >= 0:
stored.append((g, i, row))
stored.sort()
for g, i, row in stored:
writer.writerow([row[0], row[3]])
# Closing Input and Output files.
in_File.close()
out_File.close()

If I were you, I'd only separate find_group.
import csv
def find_group(row):
GROUPS = ['aircheck', 'linkrunner at', 'onetouch at']
for idx, group in enumerate(GROUPS):
if group in map(str.lower, row):
return idx
return -1
def get_filenames():
# this might be the only other thing you'd want to factor
# into a function, and frankly I don't really like getting
# user input this way anyway....
basename = raw_input("Enter a base filename (no extension): ")
infilename = basename + ".csv"
outfilename = basename + ".parsed.csv"
return infilename, outfilename
# notice that I don't open the files yet -- let main handle that
infilename, outfilename = get_filenames()
with open(infilename, 'rU') as inf, open(outfilename, 'wb') as outf:
reader = csv.reader(inf)
writer = csv.writer(outf, delimiter=',',
quotechar='"', quoting=csv.QUOTE_ALL)
header = next(reader)
writer.writerow([[header[0], header[3]])
stored = sorted([(find_group(row),idx,row) for idx,row in
enumerate(reader)) if find_group(row) >= 0])
for _, _, row in stored:
writer.writerow([row[0], row[3]])

Python search a file for text using input from another file

I'm new to python and programming. I need some help with a python script. There are two files each containing email addresses (more than 5000 lines). Input file contains email addresses that I want to search in the data file(also contains email addresses). Then I want to print the output to a file or display on the console. I search for scripts and was able to modify but I'm not getting the desired results. Can you please help me?
dfile1 (50K lines)
yyy#aaa.com
xxx#aaa.com
zzz#aaa.com
ifile1 (10K lines)
ccc#aaa.com
vvv#aaa.com
xxx#aaa.com
zzz#aaa.com
Output file
xxx#aaa.com
zzz#aaa.com
datafile = 'C:\\Python27\\scripts\\dfile1.txt'
inputfile = 'C:\\Python27\\scripts\\ifile1.txt'
with open(inputfile, 'r') as f:
names = f.readlines()
outputlist = []
with open(datafile, 'r') as fd:
for line in fd:
name = fd.readline()
if name[1:-1] in names:
outputlist.append(line)
else:
print "Nothing found"
print outputlist
New Code
with open(inputfile, 'r') as f:
names = f.readlines()
outputlist = []
with open(datafile, 'r') as f:
for line in f:
name = f.readlines()
if name in names:
outputlist.append(line)
else:
print "Nothing found"
print outputlist

Maybe I'm missing something, but why not use a pair of sets?
#!/usr/local/cpython-3.3/bin/python
data_filename = 'dfile1.txt'
input_filename = 'ifile1.txt'
with open(input_filename, 'r') as input_file:
input_addresses = set(email_address.rstrip() for email_address in input_file.readlines())
with open(data_filename, 'r') as data_file:
data_addresses = set(email_address.rstrip() for email_address in data_file.readlines())
print(input_addresses.intersection(data_addresses))

mitan8 gives the problem you have, but this is what I would do instead:
with open(inputfile, "r") as f:
names = set(i.strip() for i in f)
output = []
with open(datafile, "r") as f:
for name in f:
if name.strip() in names:
print name
This avoids reading the larger datafile into memory.
If you want to write to an output file, you could do this for the second with statement:
with open(datafile, "r") as i, open(outputfile, "w") as o:
for name in i:
if name.strip() in names:
o.write(name)

Here's what I would do:
names=[]
outputList=[]
with open(inputfile) as f:
for line in f:
names.append(line.rstrip("\n")
myEmails=set(names)
with open(outputfile) as fd, open("emails.txt", "w") as output:
for line in fd:
for name in names:
c=line.rstrip("\n")
if name in myEmails:
print name #for console
output.write(name) #for writing to file

I think your issue stems from the following:
name = fd.readline()
if name[1:-1] in names:
name[1:-1] slices each email address so that you skip the first and last characters. While it might be good in general to skip the last character (a newline '\n'), when you load the name database in the "dfile"
with open(inputfile, 'r') as f:
names = f.readlines()
you are including newlines. So, don't slice the names in the "ifile" at all, i.e.
if name in names:

I think you can remove name = fd.readline() since you've already got the line in the for loop. It'll read another line in addition to the for loop, which reads one line every time. Also, I think name[1:-1] should be name, since you don't want to strip the first and last character when searching. with automatically closes the files opened.
PS: How I'd do it:
with open("dfile1") as dfile, open("ifile") as ifile:
lines = "\n".join(set(dfile.read().splitlines()) & set(ifile.read().splitlines())
print(lines)
with open("ofile", "w") as ofile:
ofile.write(lines)
In the above solution, basically I'm taking the union (elements part of both sets) of the lines of both the files to find the common lines.

Want to read multiple csv file one by one and filepaths are stored in a text file using python

here is my code for readinng individual cell of one csv file. but want to read multiple csv file one by one from .txt file where csv file paths are located.
import csv
ifile = open ("C:\Users\BKA4ABT\Desktop\Test_Specification\RDBI.csv", "rb")
data = list(csv.reader(ifile, delimiter = ';'))
REQ = []
RES = []
n = len(data)
for i in range(n):
x = data[i][1]
y = data[i][2]
REQ.append (x)
RES.append (y)
i += 1
for j in range(2,n):
try:
if REQ[j] != '' and RES[j]!= '': # ignore blank cell
print REQ[j], ' ', RES[j]
except:
pass
j += 1
And csv file paths are stored in a .txt file like
C:\Desktop\Test_Specification\RDBI.csv
C:\Desktop\Test_Specification\ECUreset.csv
C:\Desktop\Test_Specification\RDTC.csv
and so on..

You can read stuff stored in files into variables. And you can use variables with strings in them anywhere you can use a literal string. So...
with open('mytxtfile.txt', 'r') as txt_file:
for line in txt_file:
file_name = line.strip() # or was it trim()? I keep mixing them up
ifile = open(file_name, 'rb')
# ... the rest of your code goes here
Maybe we can fix this up a little...
import csv
with open('mytxtfile.txt', 'r') as txt_file:
for line in txt_file:
file_name = line.strip()
csv_file = csv.reader(open(file_name, 'rb', delimiter=';'))
for record in csv_file[1:]: # skip header row
req = record[1]
res = record[2]
if len(req + res):
print req, ' ', res

you just need to add a while which will read your file containing your list of files & paths upon your first open statement, for example
from __future__ import with_statement
with open("myfile_which_contains_file_path.txt") as f:
for line in f:
ifile = open(line, 'rb')
# here the rest of your code

You need to use a raw string string your path contains \
import csv
file_list = r"C:\Users\BKA4ABT\Desktop\Test_Specification\RDBI.csv"
with open(file_list) as f:
for line in f:
with open(line.strip(), 'rb') as the_file:
reader = csv.reader(the_file, delimiter=';')
for row in reader:
req,res = row[1:3]
if req and res:
print('{0} {1}'.format(req, res))

Problems with Python's file.write() method and string handling

The problem I am having at this point in time (being new to Python) is writing strings to a text file. The issue I'm experiencing is one where either the strings don't have linebreaks inbetween them or there is a linebreak after every character. Code to follow:
import string, io
FileName = input("Arb file name (.txt): ")
MyFile = open(FileName, 'r')
TempFile = open('TempFile.txt', 'w', encoding='UTF-8')
for m_line in MyFile:
m_line = m_line.strip()
m_line = m_line.split(": ", 1)
if len(m_line) > 1:
del m_line[0]
#print(m_line)
MyString = str(m_line)
MyString = MyString.strip("'[]")
TempFile.write(MyString)
MyFile.close()
TempFile.close()
My input looks like this:
1 Jargon
2 Python
3 Yada Yada
4 Stuck
My output when I do this is:
JargonPythonYada YadaStuck
I then modify the source code to this:
import string, io
FileName = input("Arb File Name (.txt): ")
MyFile = open(FileName, 'r')
TempFile = open('TempFile.txt', 'w', encoding='UTF-8')
for m_line in MyFile:
m_line = m_line.strip()
m_line = m_line.split(": ", 1)
if len(m_line) > 1:
del m_line[0]
#print(m_line)
MyString = str(m_line)
MyString = MyString.strip("'[]")
#print(MyString)
TempFile.write('\n'.join(MyString))
MyFile.close()
TempFile.close()
Same input and my output looks like this:
J
a
r
g
o
nP
y
t
h
o
nY
a
d
a
Y
a
d
aS
t
u
c
k
Ideally, I would like each of the words to appear on a seperate line without the numbers in front of them.
Thanks,
MarleyH

You have to write the '\n' after each line, since you're stripping the original '\n';
Your idea of using '\n'.join() doesn't work because it will use\n to join the string, inserting it between each char of the string. You need a single \n after each name, instead.
import string, io
FileName = input("Arb file name (.txt): ")
with open(FileName, 'r') as MyFile:
with open('TempFile.txt', 'w', encoding='UTF-8') as TempFile:
for line in MyFile:
line = line.strip().split(": ", 1)
TempFile.write(line[1] + '\n')

fileName = input("Arb file name (.txt): ")
tempName = 'TempFile.txt'
with open(fileName) as inf, open(tempName, 'w', encoding='UTF-8') as outf:
for line in inf:
line = line.strip().split(": ", 1)[-1]
#print(line)
outf.write(line + '\n')
Problems:
the result of str.split() is a list (this is why, when you cast it to str, you get ['my item']).
write does not add a newline; if you want one, you have to add it explicitly.