用特殊分隔符分割文本文件为多个部分 - python

Question

我有一个输入文件，内容如下：

This is a text block start
This is the end

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

我想要做的事情是按某个特殊的行来分段读取文件，在这个例子中，特殊的行是一个空行，比如说：[out]：

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

我通过这样的方法得到了想要的输出：

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)

但是如果这个特殊的行是以#开头的，比如：

# 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.

我就得这样做：

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)

如果我想让per_section()这个函数可以接受一个分隔符参数，我可以尝试这样：

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用把所有可能的分隔符都写死在代码里呢？

Answer 1

这样做怎么样呢？

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

输出结果：

[['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.']]

Answer 2

简单地这样做：

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

输出结果：

content content
more content
content conclusion

content again
more of it
content conclusion

content
content
contend done

Answer 3

那我们来看看怎么传递一个条件函数吧？

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