Count TFM occurrences in a file and print them

search_one_file.py

import sys
import re

if len(sys.argv) != 3:
    print("Usage: python3 search_one_file.py <srt_file_path> <search_string>")
    sys.exit(1)

srt_file_path = sys.argv[1]
search_string = sys.argv[2]

if not srt_file_path.endswith('.srt'):
    print("Error: The provided file is not an .srt file.")
    sys.exit(1)

lines_to_print = []
timestamps = []

try:
    total = 0
    with open(srt_file_path, 'r', encoding='utf-8') as srt_file:

        prev_line = ''
        target_ts = ''

        for line in srt_file:

            if '-->' in line:
                timestamp_line = line
                ts_end = timestamp_line.find(',')
                target_ts = timestamp_line[:ts_end]

            elif re.search(search_string, line, re.IGNORECASE):

                # Use re.sub to replace the matched part with <b> ... </b>
                modified_line = re.sub(
                    re.escape(search_string),
                    f'<b>{search_string}</b>',
                    line,
                    flags=re.IGNORECASE
                )

                if '-->' in prev_line:
                    prev_line_partial = ''
                else:
                    prev_line_partial = prev_line[-10:].strip()

                # print("\n@" + target_ts + ": '..." + prev_line_partial + " ")
                # print("\n<br>@" + target_ts + " ==> '..." + prev_line_partial + " " + modified_line.strip() + "...'<br>")
                # prnt_line = "\n<br>@" + target_ts + " ==> '..." + prev_line_partial + " " + modified_line.strip() + "...'<br>"

                prnt_line = "\n@" + target_ts + " ==> '..." + prev_line_partial + " " + modified_line.strip() + "...'"
                lines_to_print += [ prnt_line ]

                timestamps += [ target_ts ]

                total += 1
                # print(prev_line)
                # print(modified_line.strip())

            prev_line = line

except FileNotFoundError:
    print(f"Error: File '{srt_file_path}' not found.")
    sys.exit(1)

# Check if the first item in lines_to_print starts with '\n'
if lines_to_print and lines_to_print[0].startswith('\n'):
    # Remove the leading '\n'
    lines_to_print[0] = lines_to_print[0][1:]

lines_to_print.insert(0, f"<h4>'{search_string}'</h4><h4>Total: {total}</h4>")
for i, line in enumerate(lines_to_print):
    print(line)

print ("\n\n")
print(f"Total of {total} '{search_string}':")
for i, line in enumerate(timestamps):
    print(line)