Lets say I have a Text file with the below content
fdsjhgjhg fdshkjhk Start Good Morning Hello World End dashjkhjk dsfjkhk
Now I need to write a Python code which will read the text file and copy the contents between Start and end to another file.
I wrote the following code.
inFile = open("data.txt")
outFile = open("result.txt", "w")
buffer = []
keepCurrentSet = True
for line in inFile:
buffer.append(line)
if line.startswith("Start"):
#---- starts a new data set
if keepCurrentSet:
outFile.write("".join(buffer))
#now reset our state
keepCurrentSet = False
buffer = []
elif line.startswith("End"):
keepCurrentSet = True
inFile.close()
outFile.close()
I’m not getting the desired output as expected
I’m just getting Start
What I want to get is all the lines between Start and End.
Excluding Start & End.
Answers:
Thank you for visiting the Q&A section on Magenaut. Please note that all the answers may not help you solve the issue immediately. So please treat them as advisements. If you found the post helpful (or not), leave a comment & I’ll get back to you as soon as possible.
Method 1
Just in case you have multiple “Start”s and “End”s in your text file, this will import all the data together, excluding all the “Start”s and “End”s.
with open('path/to/input') as infile, open('path/to/output', 'w') as outfile:
copy = False
for line in infile:
if line.strip() == "Start":
copy = True
continue
elif line.strip() == "End":
copy = False
continue
elif copy:
outfile.write(line)
Method 2
If the text files aren’t necessarily large, you can get the whole content of the file then use regular expressions:
import re
with open('data.txt') as myfile:
content = myfile.read()
text = re.search(r'Startn.*?End', content, re.DOTALL).group()
with open("result.txt", "w") as myfile2:
myfile2.write(text)
Method 3
I’m not a Python expert, but this code should do the job.
inFile = open("data.txt")
outFile = open("result.txt", "w")
keepCurrentSet = False
for line in inFile:
if line.startswith("End"):
keepCurrentSet = False
if keepCurrentSet:
outFile.write(line)
if line.startswith("Start"):
keepCurrentSet = True
inFile.close()
outFile.close()
Method 4
Using itertools.dropwhile, itertools.takewhile, itertools.islice:
import itertools
with open('data.txt') as f, open('result.txt', 'w') as fout:
it = itertools.dropwhile(lambda line: line.strip() != 'Start', f)
it = itertools.islice(it, 1, None)
it = itertools.takewhile(lambda line: line.strip() != 'End', it)
fout.writelines(it)
UPDATE: As inspectorG4dget commented, above code copies over the first block. To copy multiple blocks, use following:
import itertools
with open('data.txt', 'r') as f, open('result.txt', 'w') as fout:
while True:
it = itertools.dropwhile(lambda line: line.strip() != 'Start', f)
if next(it, None) is None: break
fout.writelines(itertools.takewhile(lambda line: line.strip() != 'End', it))
Method 5
Move the outFile.write call into the 2nd if:
inFile = open("data.txt")
outFile = open("result.txt", "w")
buffer = []
for line in inFile:
if line.startswith("Start"):
buffer = ['']
elif line.startswith("End"):
outFile.write("".join(buffer))
buffer = []
elif buffer:
buffer.append(line)
inFile.close()
outFile.close()
Method 6
import re
inFile = open("data.txt")
outFile = open("result.txt", "w")
buffer1 = ""
keepCurrentSet = True
for line in inFile:
buffer1=buffer1+(line)
buffer1=re.findall(r"(?<=Start) (.*?) (?=End)", buffer1)
outFile.write("".join(buffer1))
inFile.close()
outFile.close()
Method 7
I would handle it like this :
inFile = open("data.txt")
outFile = open("result.txt", "w")
data = inFile.readlines()
outFile.write("".join(data[data.index('Startn')+1:data.index('Endn')]))
inFile.close()
outFile.close()
Method 8
if one wants to keep the start and end lines/keywords while extracting the lines between 2 strings.
Please find below the code snippet that I used to extract sql statements from a shell script
def process_lines(in_filename, out_filename, start_kw, end_kw):
try:
inp = open(in_filename, 'r', encoding='utf-8', errors='ignore')
out = open(out_filename, 'w+', encoding='utf-8', errors='ignore')
except FileNotFoundError as err:
print(f"File {in_filename} not found", err)
raise
except OSError as err:
print(f"OS error occurred trying to open {in_filename}", err)
raise
except Exception as err:
print(f"Unexpected error opening {in_filename} is", repr(err))
raise
else:
with inp, out:
copy = False
for line in inp:
# first IF block to handle if the start and end on same line
if line.lstrip().lower().startswith(start_kw) and line.rstrip().endswith(end_kw):
copy = True
if copy: # keep the starts with keyword
out.write(line)
copy = False
continue
elif line.lstrip().lower().startswith(start_kw):
copy = True
if copy: # keep the starts with keyword
out.write(line)
continue
elif line.rstrip().endswith(end_kw):
if copy: # keep the ends with keyword
out.write(line)
copy = False
continue
elif copy:
# write
out.write(line)
if __name__ == '__main__':
infile = "/Users/testuser/Downloads/testdir/BTEQ_TEST.sh"
outfile = f"{infile}.sql"
statement_start_list = ['database', 'create', 'insert', 'delete', 'update', 'merge', 'delete']
statement_end = ";"
process_lines(infile, outfile, tuple(statement_start_list), statement_end)
Method 9
Files are iterators in Python, so this means you don’t need to hold a “flag” variable to tell you what lines to write. You can simply use another loop when you reach the start line, and break it when you reach the end line:
with open("data.txt") as in_file, open("result.text", 'w') as out_file:
for line in in_file:
if line.strip() == "Start":
for line in in_file:
if line.strip() == "End":
break
out_file.write(line)
All methods was sourced from stackoverflow.com or stackexchange.com, is licensed under cc by-sa 2.5, cc by-sa 3.0 and cc by-sa 4.0