Extract text

[DeaD_EyE]

Example with a generator:

1. assign False to start_found
   
2. iterate line by line, which should be word for word
   
3. if start was found, change start_found to True
   
4. yield element if start_found is True
   
5. return from generator, if end is the element. This will also leave the for-loop
   
6. optional Exceptions:
   • if the for-loop was finished, but start_found is still False, then start-word was not found
     
   • if the for-loop was finished and start_found is True, then the end-word was not found
     

word_start = "yes"
word_end = "no"

words = """yes
ok
ok
ok
no""".splitlines()

def split(sequence, start, end):
    start_found = False

    for element in sequence:
        if element == word_start and not start_found:
            start_found = True
        elif element == word_end and start_found:
            return
            # close generator
        elif start_found:
            yield element

    # this point is reached, if the start or end was not found
    if start_found:
        # seen start, but no end
        raise ValueError(f"'{end}' was not the last element in sequence")
    else:
        # seen no start in the whole sequence
        raise ValueError(f"The start_word '{start}' was not found in sequence")

oks = list(split(words, word_start, word_end))
print(oks)

Here the Version, which includes start-word and stop-word.
It has no big difference compared to the previous generator-function.

word_start = "yes"
word_end = "no"

words = """yes
ok
ok
ok
no""".splitlines()

def split(sequence, start, end):
    start_found = False

    for element in sequence:
        if element == word_start and not start_found:
            start_found = True
            yield element
        elif element == word_end and start_found:
            yield element # yield the word_end
            return
            # close generator
        elif start_found:
            yield element

    # this point is reached, if the start or end was not found
    if start_found:
        # seen start, but no end
        raise ValueError(f"'{end}' was not the last element in sequence")
    else:
        # seen no start in the whole sequence
        raise ValueError(f"The start_word '{start}' was not found in sequence")

oks = list(split(words, word_start, word_end))
print(oks)