Splitting textfile into section with special delimiter line - python

Question

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 desired task is to read the files by section delimited by some special line, in this case it's an empty line, e.g. [out]:

[['This is a text block start', 'This is the end'],
['And this is another','with more than one line', 'and another line.']]

I have been getting the desired output by doing so:

def per_section(it):
    """ Read a file and yield sections using empty line as delimiter """
    section = []
    for line in it:
        if line.strip('\n'):
            section.append(line)
        else:
            yield ''.join(section)
            section = []
    # yield any remaining lines as a section too
    if section:
        yield ''.join(section)

But if the special line is a line that starts with # e.g.:

# 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.

I have to do this:

def per_section(it):
    """ Read a file and yield sections using empty line as delimiter """
    section = []
    for line in it:
        if line[0] != "#":
            section.append(line)
        else:
            yield ''.join(section)
            section = []
    # yield any remaining lines as a section too
    if section:
        yield ''.join(section)

If i were to allow the per_section() to have a delimiter parameter, I could try this:

def per_section(it, delimiter== '\n'):
    """ Read a file and yield sections using empty line as delimiter """
    section = []
    for line in it:
        if line.strip('\n') and delimiter == '\n':
            section.append(line)
        elif delimiter= '\#' and line[0] != "#":
            section.append(line)
        else:
            yield ''.join(section)
            section = []
    # yield any remaining lines as a section too
    if section:
        yield ''.join(section)

But is there a way so that i don't hard-code all possible delimiters?

Answer 1

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

Answer 2

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

Answer 3

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.']]