Check the integrity of labels after running the bash.sh script I wrote and piping it to a text file.

check_labels.py

from re import T


labels = ["frodo","sam","legolas","gimli","karim benzema"]

# Open a text file to write the bad labels to
with open("bad_labels.txt","w") as bad:

    # Open the text file with all of the data in it
    with open("test2_xml/test.txt") as file:
        temp_line = ""
        for line in file:
            if("filename" in line):
                temp_line = line
                print(temp_line)

            else:
                # There is probably a better way to get ahold of the string im interested in
                line_1_split = line.split(">")
                line_2_split = line_1_split[1].split("<")

                if(line_2_split[0].strip() in labels):
                    print(line_2_split[0] + " label okay.")
                else:
                    bad.write(temp_line)
                    bad.write(line)