Ytukyg

I want to extract a certain part of a letter from a txt file with Python. The beginning and the ending is marked by clear beginning / ending expressions (letter_begin / letter_end). My problem is that the "recording" of the text needs to start at the very first occurence of any item in the letter_begin list and end at the very last item in the letter_end list (+3 lines buffer). I want to write the output text to file. Here is my sample text and my code so far:

sample_text = """Some random text right here 

.........

Dear Shareholders: We are pleased to provide this report to our shareholders and fellow shareholders. we thank you for your continued support.

Best regards, 

Douglas - Director





Other random text in this lines """



letter_begin = ["dear", "to our shareholders", "fellow shareholders"]

letter_end = ["best regards", "respectfully submitted", "thank you for your continued support"]



with open(filename, 'r', encoding="utf-8") as infile, open(xyz.txt, mode = 'w', encoding="utf-8") as f: 

        text = infile.read()

        lines = text.strip().split("n")

        target_start_idx = None

        target_end_idx = None

        for index, line in enumerate(lines):

            line = line.lower()

            if any(beg in line for beg in letter_begin):

                target_start_idx = index

                continue

            if any(end in line for end in letter_end):

                target_end_idx = index + 3

                break





        if target_start_idx is not None:

            target = "n".join(lines[target_start_idx : target_end_idx])

            f.write(str(target))

my desired output should be:

output = "Dear Shareholders: We are pleased to provide this report to our shareholders and fellow shareholders. we thank you for your continued support.

    Best regards, 

    Douglas - Director



    "

Your loop gives you the last occurrence of an opening sequence.

You should separate the read part into two loops, like this:

with open(filename, 'r', encoding="utf-8") as infile:



    text = infile.read()

    lines = text.strip().split("n")

    target_start_idx = None

    target_end_idx = None

    for index, line in enumerate(lines):

        line = line.lower()

        if any(beg in line for beg in letter_begin):

            target_start_idx = index

            break

    for index, line in enumerate(lines):

        if any(end in line for end in letter_end):

            target_end_idx = index + 3

            continue

In this way, you exit the loop when the first occurrence of an opening sequence appears.

What about regular expressions?

import re

sample_text = """Some random text right here 

.........

Dear Shareholders: We are pleased to provide this report to our shareholders 

and fellow shareholders. we thank you for your continued support.

Best regards, 

Douglas - Director





Other random text in this lines """







letter_begin = ["dear", "to our shareholders", "fellow shareholders"]

letter_end = ["best regards", "respectfully submitted", "thank you for your continued support"]



"""

# read from a file

with open(input_file, 'r') as fo:

    input_text = fo.read()

"""



input_text = sample_text



begin_pattern = re.compile(r'b(?:%s)b' % '|'.join(letter_begin), flags=re.IGNORECASE)

end_pattern = re.compile(r'b(?:%s)b' % '|'.join(letter_end), flags=re.IGNORECASE)



match_begin = re.findall(begin_pattern, input_text)

idx_begin = min(re.search(x, input_text).start() for x in match_begin)



match_end = re.findall(end_pattern, input_text)

idx_end = max(re.search(x, input_text).end() for x in match_end)



# add 3 lines, assuming that there are always enough extra lines

extra_lines = 'n'.join(input_text[idx_end:].split('n')[:4])

output_text = input_text[idx_begin:idx_end] + extra_lines



print(output_text)

# Dear Shareholders: We are pleased to provide this report to our shareholders 

# and fellow shareholders. we thank you for your continued support.

# Best regards, 

# Douglas - Director

#

#

"""

# write to a new file

with open(output_file, 'w') as fo:

    fo.write(output_text)

"""