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)
def delet_line(exp_res):
filename = "C:\\Users\\beher\\Desktop\\my.txt"
exp_res_sl = exp_res.splitlines()
#print('file name is ',filename)
with open(filename, "r") as f:
lines = f.readlines()
for expres_line in exp_res_sl:
print(expres_line)
with open(filename, "w") as f:
for line in lines:
if line.strip("\n") != expres_line:
f.write(line)
delet_line("Mohan\nmohan")
Here i am trying to delete the a multiline string passing as argument but it deletes only the last line of the passing argument pls help| thanks in advance.
Maybe like so:
def delete_line(skip_lines):
filename="C:\\Users\\beher\\Desktop\\my.txt"
with open(filename, "rt") as f:
lines = f.readlines()
with open(filename, "wt") as f:
for line in lines:
if line.strip('\n') not in skip_lines:
f.write(line)
delete_line(['Mohan', 'mohan'])
I have a script which reads each line from text file. but somehow it prints all at once. I want to run one line end and run next. here is the code.
f = open('textfile.txt', 'r')
file= f.read()
for x in file:
print(x, file.strip())
comSerialPort.write(x.encode('utf-8'))
Use readlines instead of read
with open('textfile.txt', 'r') as f:
lines = f.readlines()
for line in lines:
print(line)
# do stuff with each line
Use with statement and then iterate lines.
Ex:
with open('textfile.txt', 'r') as infile:
for line in infile:
print(line)
comSerialPort.write(line.strip().encode('utf-8'))
Note: read() reads the entire content of the file.
I'm trying to process a pipe separated text file with the following format:
18511|1|2587198|2004-03-31|0|100000|0|1.97|0.49988|100000||||
18511|2|2587198|2004-06-30|0|160000|0|3.2|0.79669|60000|60|||
18511|3|2587198|2004-09-30|0|160000|0|2.17|0.79279|0|0|||
18511|4|2587198|2004-09-30|0|160000|0|1.72|0.79118|0|0|||
18511|5|2587198|2005-03-31|0|0|0|0|0|-160000|-100|||19
18511|1|2587940|2004-03-31|0|240000|0|0.78|0.27327|240000||||
18511|2|2587940|2004-06-30|0|560000|0|1.59|0.63576|320000|133.33||24|
18511|3|2587940|2004-09-30|0|560000|0|1.13|0.50704|0|0|||
18511|4|2587940|2004-09-30|0|560000|0|0.96|0.50704|0|0|||
18511|5|2587940|2005-03-31|0|0|0|0|0|-560000|-100|||14
For each line I want to isolate the second field and write that line to a file with that field as part of the filename e.g issue1.txt, issue2.txt where the number is the second field in the above file excerpt. This number can be in the range 1 to 56. My code is shown below:
with open('d:\\tmp\issueholding.txt') as f, open('d:\\tmp\issue1.txt', 'w') as out_f1,\
open('d:\\tmp\issue2.txt', 'w') as out_f2,open('d:\\tmp\issue3.txt', 'w') as out_f3,\
open('d:\\tmp\issue4.txt', 'w') as out_f4,open('d:\\tmp\issue5.txt', 'w') as out_f5,\
open('d:\\tmp\issue6.txt', 'w') as out_f6,open('d:\\tmp\issue7.txt', 'w') as out_f7,\
open('d:\\tmp\issue8.txt', 'w') as out_f8,open('d:\\tmp\issue9.txt', 'w') as out_f9,\
open('d:\\tmp\issue10.txt', 'w') as out_f10,open('d:\\tmp\issue11.txt', 'w') as out_f11,\
open('d:\\tmp\issue12.txt', 'w') as out_f12,open('d:\\tmp\issue13.txt', 'w') as out_f13,\
open('d:\\tmp\issue14.txt', 'w') as out_f14,open('d:\\tmp\issue15.txt', 'w') as out_f15,\
open('d:\\tmp\issue16.txt', 'w') as out_f16,open('d:\\tmp\issue17.txt', 'w') as out_f17,\
open('d:\\tmp\issue18.txt', 'w') as out_f18,open('d:\\tmp\issue19.txt', 'w') as out_f19,\
open('d:\\tmp\issue20.txt', 'w') as out_f20,open('d:\\tmp\issue21.txt', 'w') as out_f21,\
open('d:\\tmp\issue22.txt', 'w') as out_f22,open('d:\\tmp\issue23.txt', 'w') as out_f23,\
open('d:\\tmp\issue24.txt', 'w') as out_f24,open('d:\\tmp\issue25.txt', 'w') as out_f25,\
open('d:\\tmp\issue32.txt', 'w') as out_f32,open('d:\\tmp\issue33.txt', 'w') as out_f33,\
open('d:\\tmp\issue34.txt', 'w') as out_f34,open('d:\\tmp\issue35.txt', 'w') as out_f35,\
open('d:\\tmp\issue36.txt', 'w') as out_f36,open('d:\\tmp\issue37.txt', 'w') as out_f37,\
open('d:\\tmp\issue38.txt', 'w') as out_f38,open('d:\\tmp\issue39.txt', 'w') as out_f39,\
open('d:\\tmp\issue40.txt', 'w') as out_f40,open('d:\\tmp\issue41.txt', 'w') as out_f41,\
open('d:\\tmp\issue42.txt', 'w') as out_f42,open('d:\\tmp\issue43.txt', 'w') as out_f43,\
open('d:\\tmp\issue44.txt', 'w') as out_f44,open('d:\\tmp\issue45.txt', 'w') as out_f45,\
open('d:\\tmp\issue46.txt', 'w') as out_f46,open('d:\\tmp\issue47.txt', 'w') as out_f47,\
open('d:\\tmp\issue48.txt', 'w') as out_f48,open('d:\\tmp\issue49.txt', 'w') as out_f49,\
open('d:\\tmp\issue50.txt', 'w') as out_f50,open('d:\\tmp\issue51.txt', 'w') as out_f51,\
open('d:\\tmp\issue52.txt', 'w') as out_f52,open('d:\\tmp\issue53.txt', 'w') as out_f53,\
open('d:\\tmp\issue54.txt', 'w') as out_f54,open('d:\\tmp\issue55.txt', 'w') as out_f55,\
open('d:\\tmp\issue56.txt', 'w') as out_f56:
for line in f:
field1_end = line.find('|') +1
field2_end = line.find('|',field1_end)
f2=line[field1_end:field2_end]
out_f56.write(line)
My two issue are:
1) When trying to run the above I get the following error message
File "", line unknown
SyntaxError: too many statically nested blocks
2) How do I change this line out_f56.write(line) so that I can use the variable f2 as part of the file descriptor rather than hard coding it.
I am running this in a jupyter notebook running python3 under Windows. To be clear, the input file has approx 235 Million records so performance is key.
Appreciate any help or suggestions
Try something like this (see comments in code for explanation):
with open(R"d:\tmp\issueholding.txt") as f:
for line in f:
# splitting line into list of strings at '|' character
fields = line.split('|')
# defining output file name according to issue code in second field
# NB: list-indexes are zero-based, therefore use 1
out_name = R"d:\tmp\issue%s.txt" % fields[1]
# opening output file and writing current line to it
# NB: make sure you use the 'a+' mode to append to existing file
with open(out_name, 'a+') as ff:
ff.write(line)
To avoid opening files repeatedly inside the reading loop, you could do the following:
from collections import defaultdict
with open(R"D:\tmp\issueholding.txt") as f:
# setting up dictionary to hold lines grouped by issue code
# using a defaultdict here to automatically create a list when inserting
# the first item
collected_issues = defaultdict(list)
for line in f:
# splitting line into list of strings at '|' character and retrieving
# current issue code from second token
issue_code = line.split('|')[1]
# appending current line to list of collected lines associated with
# current issue code
collected_issues[issue_code].append(line)
else:
for issue_code in collected_issues:
# defining output file name according to issue code
out_name = R"D:\tmp\issue%s.txt" % issue_code
# opening output file and writing collected lines to it
with open(out_name, 'a+') as ff:
ff.write("".join(collected_issues[issue_code]))
This of course creates an in-memory dictionary holding all lines retrieved from the input file. Given your specification this could very well be not feasible with your machine. An alternative would be to split up the input file and processing it chunk by chunk instead. This can be achieved in code by defining a corresponding generator that reads a defined amount of lines (here: 1000) from the input file. A possible final solution could then look like this:
from itertools import islice
from collections import defaultdict
def get_chunk_of_lines(file, N):
"""
Retrieves N lines from specified opened file.
"""
return [x.strip() for x in islice(file, N)]
def collect_issues(lines):
"""
Collects and groups issues from specified lines.
"""
collected_issues = defaultdict(list)
for line in lines:
# splitting line into list of strings at '|' character and retrieving
# current issue code from second token
issue_code = line.split('|')[1]
# appending current line to list of collected lines associated with
# current issue code
collected_issues[issue_code].append(line)
return collected_issues
def export_grouped_issues(issues):
"""
Exports collected and grouped issues.
"""
for issue_code in issues:
# defining output file name according to issue code
out_name = R"D:\tmp\issue%s.txt" % issue_code
# opening output file and writing collected lines to it
with open(out_name, 'a+') as f:
f.write("".join(issues[issue_code]))
with open(R"D:\tmp\issueholding.txt") as issue_src:
chunk_cnt = 0
while True:
# retrieving 1000 input lines at a time
line_chunk = get_chunk_of_lines(issue_src, 1000)
# exiting while loop if no more chunk is left
if not line_chunk:
break
chunk_cnt += 1
print("+ Working on chunk %d" % chunk_cnt)
# collecting, grouping and exporting issues
issues = collect_issues(line_chunk)
export_grouped_issues(issues)
I have written a maths quiz for school and the final task requires me to take scores from a file and order them in various ways. I was performing what I thought was a simple task of just writing to a file but it turned out to not work. Can someone please tell me what's missing from this.
with open("Class A.txt", "r") as f:
list(f)
How about this:
>>> with open("Class A.txt", "r") as f:
... content = f.read()
... content_list = content.split('\n') # split on space/comma/...
Read the content and then split it using whichever delimiter you have used, whether enter (\n), comma or anything else.
if the file is already in the format of a list i.e. [1,2,3,4,5], all you have to do is use the eval function. you could try one of the following:
with open("Class A.txt", "r") as f: #method 1, requires indentation
f1 = eval(f.read())
print(f1)
file = open("Class A.txt", "r") #method 2
f2 = eval(file.read())
file.close()
print(f2)
if your string is like this "6|Louis|Perry 2|Shiro|Ski 4|A|B", you could do
file = open("Class A.txt", "r")
f2 = file.read().split('|')
file.close()
print(f2)