I have an input file as such:
This is a text block start
This is the end
And this is another
with more than one line
and another line.
The
Simply do this:
with open('yorfileaname.txt') as f: #open desired file
data = f.read() #read the whole file and save to variable data
print(*(data.split('=========='))) #now split data when "=.." and print it
#usually it would ouput a list but if you use * it will print as string
Output:
content content
more content
content conclusion
content again
more of it
content conclusion
content
content
contend done
How about something like this?
from itertools import groupby
def per_section(s, delimiters=()):
def key(s):
return not s or s.isspace() or any(s.startswith(x) for x in delimiters)
for k, g in groupby(s.splitlines(), key=key):
if not k:
yield list(g)
if __name__ == '__main__':
print list(per_section('''This is a text block start
This is the end
And this is another
with more than one line
and another line.'''))
print list(per_section('''# Some comments, maybe the title of the following section
This is a text block start
This is the end
# Some other comments and also the title
And this is another
with more than one line
and another line.''', ('#')))
print list(per_section('''!! Some comments, maybe the title of the following section
This is a text block start
This is the end
$$ Some other comments and also the title
And this is another
with more than one line
and another line.''', ('!', '$')))
Output:
[['This is a text block start', 'This is the end'], ['And this is another', 'with more than one line', 'and another line.']]
[['This is a text block start', 'This is the end'], ['And this is another', 'with more than one line', 'and another line.']]
[['This is a text block start', 'This is the end'], ['And this is another', 'with more than one line', 'and another line.']]
How about pass a predicate?
def per_section(it, is_delimiter=lambda x: x.isspace()):
ret = []
for line in it:
if is_delimiter(line):
if ret:
yield ret # OR ''.join(ret)
ret = []
else:
ret.append(line.rstrip()) # OR ret.append(line)
if ret:
yield ret
Usage:
with open('/path/to/file.txt') as f:
sections = list(per_section(f)) # default delimiter
with open('/path/to/file.txt.txt') as f:
sections = list(per_section(f, lambda line: line.startswith('#'))) # comment