There are 15 text files in a folder and I am trying to extract certain parts of each file and output them to a new file.
I am able to extract each file individually by just changing the file name and append each file to the output file but this means copying the same code 15 times and just changing the file name each time.
import glob,os
lst = []
filelist=glob.glob ('/C:/Users/bridaly/Documents/PythonTest/Python_Test_ENdata_3080_v20150914/input/*')
for file in filelist:
if os.path.isfile(file):
for line in filelist:
line = line.strip()
if not (
line.startswith("APPEND") or line.startswith("_") or
line.startswith("SAP") or line.startswith("~") or
line.startswith("INCLUDE") or line.startswith("ABAP")
or line.strip() == "" or line.startswith("Field") or
line.startswith("Short")
) :
y=line.replace(' ',' ')
#print(y)
z = y.replace('X','')
#print(z)
w = "|".join(z.split())
#print(w)
x = w.split("|",3)[:4]
#print(x)
x.insert(0,'./input/01BKPF')
#print(x)
if len(x) >=4:
t = [s.replace('|',' ') for s in x]
#print(t)
print("|".join(t))
lst.append("|".join(t))
#Output Script
output_file = open('Output_Final.txt', 'w')
for l in lst:
output_file.write(l)
output_file.write('\n')
output_file.close()
"""
The output should extract what's written in the code but for each file and append it to the output file. I have gotten the correct output by copying the code 15 times but I just want to use it once as it is more efficient.
files = glob.glob('path')
for file in files:
file_name = os.path.basename(file)
print(file_name)
you can iterate for each file
Related
I have a text file as "file_in.txt".I want read the first three lines from that
file and Write the those three lines read from "file_in.txt" to a new file
called "file_out.txt".
After write it, read "file_out.txt" and Print it's contents
file_in = "file_in.txt"
file_out = "file_out.txt"
data = ""
# read the first 3 lines of file_in.txt
with open(file_in, 'r') as f:
for i in range(3):
data += f.readline()
# write to file_out.txt
with open(file_out, 'w') as f:
f.write(data)
# read the content of file_out.txt
with open(file_out, 'r') as f:
content = f.read()
print(content)
My requirement is to find a file from a directory and then in that file find LOG_X_PARAMS and in that append a string after the first comma this is what i am having for now
import os, fnmatch
def findReplacelist(directory, finds, new_string, file):
line_number = 0
list_of_results = []
for path, dirs, files in os.walk(os.path.abspath(directory)):
if file in files:
filepath = os.path.join(path, file)
with open(filepath, 'r') as f:
for line in f:
line_number += 1
if finds in line:
list_of_results.append((line_number))
print(list_of_results)
def get_git_root(path):
Path = "E:\Code\modules"
file_list=["pb_sa_ch.c"]
for i in file_list:
findReplacelist(Path , "LOG_1_PARAMS", "instance", i)
The example line is below change
LOG_X_PARAMS(string 1, string 2); #string1 andd string2 is random
this to
LOG_X_PARAMS(string 1, new_string, string 2);
I can find the line number using LOG_X_PARAMS now using this line number I need to append a string in the same line can someone help solving it ?
This is how I would do the task. I would find the files I want to change, read then file line by line and if there is a change in the file, then write the file back out. Heres the approach:
def findReplacelist(directory, finds, new_string, file):
for path, dirs, files in os.walk(os.path.abspath(directory)):
if file in files:
filepath = os.path.join(path, file)
find_replace(finds, new_string, filepath)
def find_replace(tgt_phrase, new_string, file):
outfile = ''
chgflg = False
with open(file, 'r') as f:
for line in f:
if tgt_phrase in line:
outfile += line + new_string
chgflg = True
else:
outfile += line
if chgflg:
with open(file, 'w') as f:
f.write(outfile)
i am trying to write a script that compares a bunch of files based on a search word, in this case i searched for 106, then i want the code to match the words from file 1 to the words in file 2 and print a list with the ones that dont match.
For example in file A i have this line
106_LB01_GP61_HAL;LB01;10892;DIGITAL;0;0;0;0;;;Smutsigt tilluftsfilter;;
and in file B i have
"Prefix": "106_LB01_GP61",
those lines match and then i want it to ignore that tag
when the script find lines that dont match etc when a tag in file A cant fint its buddy in file B i want it to write those tags to a file,
for example:
Total unused tags:1
106_LB01_GP61
right now i am stuc at making it read to diffrent files at the same time
#!/usr/bin/env python
#Import os module
import os
# Ask the user to enter string to search
search_path = (".")
file_type = (".wpp")
search_str = input("Enter searchword: ")
resultsFile = "results.csv"
file_name = ("results.csv")
# Append a directory separator if not already present
if not (search_path.endswith("/") or search_path.endswith("\\") ):
search_path = search_path + "/"
# If path does not exist, set search path to current directory
if not os.path.exists(search_path):
search_path ="."
0
# Repeat for each file in the directory
for fname in os.listdir(path=search_path):
# Apply file type filter
if fname.endswith(file_type):
# Open file for reading
fo = open(search_path + fname)
# Read the first line from the file
line = fo.readline()
# Initialize counter for line number
line_no = 1
# Loop until EOF
wf = open(search_path + resultsFile, 'a')
while line != '' :
# Search for string in line
index = line.find(search_str)
if ( index != -1) :
print(fname, "[", line_no, ",", index, "] ", line, sep="")
wf.write(line + " ")
# Read next line
line = fo.readline()
# Increment line counter
line_no += 1
# Close the files
fo.close()
def check_if_string_in_file(file_name, string_to_search):
""" Check if any line in the file contains given string """
# Open the file in read only mode
with open(file_name, 'r') as read_obj:
# Read all lines in the file one by one
for line in read_obj:
# For each line, check if line contains the string
if string_to_search in line:
return True
return False
def check_if_string_in_file(file_name2, string_to_search):
""" Check if any line in the file contains given string """
# Open the file in read only mode
with open(file_name2, 'r') as read_obj:
# Read all lines in the file one by one
for line in read_obj:
# For each line, check if line contains the string
if string_to_search in line:
return True
return False
def search_string_in_file(file_name, string_to_search):
"""Search for the given string in file and return lines containing that string,
along with line numbers"""
line_number = 0
list_of_results = []
# Open the file in read only mode
with open(file_name, 'r') as read_obj:
# Read all lines in the file one by one
for line in read_obj:
# For each line, check if line contains the string
line_number += 1
if string_to_search in line:
# If yes, then add the line number & line as a tuple in the list
list_of_results.append((line_number, line.rstrip()))
# Return list of tuples containing line numbers and lines where string is found
return list_of_results
def search_multiple_strings_in_file(file_name, list_of_strings):
"""Get line from the file along with line numbers, which contains any string from the list"""
line_number = 0
list_of_results = []
# Open the file in read only mode
with open(file_name, 'r') as read_obj:
# Read all lines in the file one by one
for line in read_obj:
line_number += 1
# For each line, check if line contains any string from the list of strings
for string_to_search in list_of_strings:
if string_to_search in line:
# If any string is found in line, then append that line along with line number in list
list_of_results.append((string_to_search, line_number, line.rstrip()))
# Return list of tuples containing matched string, line numbers and lines where string is found
return list_of_results
def main():
print('*** Loading *** ')
matched_lines = search_string_in_file(file_name, search_str)
for elem in matched_lines:
print('Line Number = ', elem[0], ' :: Line = ', elem[1])
# search for given strings in the file 'sample.txt'
matched_lines = search_multiple_strings_in_file(file_name, [search_str])
print('*** Checking if', [search_str], 'exists in a file *** ')
print('Total Matched lines : ', len(matched_lines))
# Check if string 'is' is found in file 'sample.txt'
if check_if_string_in_file(file_name, search_str):
print('Yes, string found in file')
else:
print('String not found in file')
if __name__ == '__main__':
main()
I have a folder containing some other folders and each of them contains a lot of text files, about 32214 files. I want to print 5 words before and after a specific word and my code should read all of these files.The code below works but it takes about 8 hours to read all of the files and extracts sentences. How can I change the code so that it reads and prints the sentences just in a few minutes? (The language is Persian)
.
.
.
def extact_sentence ():
f= open ("پاکت", "w", encoding = "utf-8")
y = "پاکت"
text= normal_text(folder_path) # the first function to normalize the files
for i in text:
for line in i:
split_line = line.split()
if y in split_line:
index = split_line.index(y)
d = (' '.join(split_line[max(0,index-5):min(index+6,len(split_line))]))
f.write(d + "\n")
f.close()
enter image description here
Use os.walk to access all the files. Then use a rolling window over each file, and check the middle word of each window:
import os
def getRollingWindow(seq, w):
win = [next(seq) for _ in range(window_size)]
yield win
for e in seq:
win[:-1] = win[1:]
win[-1] = e
yield win
def extractSentences(rootDir, searchWord):
with open("پاکت", "w", encoding="utf-8") as outfile:
for root, _dirs, fnames in os.walk(rootDir):
for fname in fnames:
print("Looking in", os.path.join(root, fname))
with open(os.path.join(root, fname)) as infile:
for window in getRollingWindow(word for line in infile for word in line.split(), 11):
if window[5] != searchWord: continue
outfile.write(' '.join(window))
I have this script:
f = open("/ggg/darr/file/", "r+")
a = 0
for line in f:
if a ==58:
print (line)
line1 = "google.ca"
f.write(line1)
print line
a = a+1
f.close()
I want to keep my file but only to change what is written on line 58 to "google.ca"
then save it
using linux: mint-17.2
# Read data from file
with open('yourfile.txt', 'r') as file:
# read all line in the file to data array
data = file.readlines()
# change data on line 58 (array start from 0)
data[57] = 'Data you need to change'
# Write data back
with open('yourfile.txt', 'w') as file:
file.writelines(data)
You need to decide whether you want to write a new file (with print) or change the old file (with r+ mode and f.write). You will probably be happiest if you write a new file.
dataRead = []
f = open("/ggg/darr/file/", "r+")
a = 0
for line in f:
if a == 58:
line = "google.ca"
dataRead.append(line)
a = a+1
f.close()
f2 = open("/some/new/file","w")
for line in dataRead:
f2.write(line)
f2.close()
With the answer of Adisak Anusornsrirung I wrote it like this:
with open('sss.txt','r') as file:
data = file.readlines()
print (data[14])
file.close()
data[14] = "some data here"+"\n"
with open ("sss.txt", 'w') as file:
file.writelines(data)
file.close()
f = open("sss.txt", 'r')
print (f.read())
f.close()