使用特殊分隔线将文本文件拆分为部分 - python

Question

我有一个这样的输入文件：

This is a text block start
This is the end

And this is another
with more than one line
and another line.

所需的任务是按由某些特殊行分隔的部分读取文件，在这种情况下，它是一个空行，例如[出]：

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

这样做我得到了想要的输出：

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)

但如果特殊行是以#开头的行，例如：

# 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.

我必须这样做：

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)

如果我允许per_section() 有一个分隔符参数，我可以试试这个：

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)

但是有没有办法让我不对所有可能的分隔符进行硬编码？

Answer 1

传递一个谓词怎么样？

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

用法：

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

只需这样做：

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

输出：

content content
more content
content conclusion

content again
more of it
content conclusion

content
content
contend done

Answer 3

这样的事情怎么样？

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.''', ('!', '$')))    

输出：

[['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.']]