def get_nc(line):
    temp = line.split('|')
    nc = temp[1][:temp[1].find('.') + 2]
    return nc
def get_organism_name(nc: str):
    try:
        base_url = 'https://www.ncbi.nlm.nih.gov/assembly/?term={}'
        pattern = 'lock">'

        response = requests.get(base_url.format(nc))
        s = str(response.content)
        pos = s.find(pattern)
        if pos == -1:
            return 'query'
        organism_name = ''
        i = pos + len(pattern)
        while i < len(s) and s[i] != '<':
            organism_name += s[i]
            i += 1
    except:
        return "query"
    return organism_name
def do_organism_modification(organism_name):
    if organism_name.rfind('(') == -1:
        organism_name = organism_name.replace(' ','_')
        organism_name = '|' + organism_name
    else:
        organism_name = '|' + organism_name[:organism_name.rfind('(')-1]
        organism_name = organism_name.replace(' ','_')
    return organism_name
def do_everything(input_file, output_file):
    with open(input_file, 'r') as inp:
        with open(output_file, 'w') as outp:
            for line in inp:
                if line.startswith('>'):
                    nc = get_nc(line)
                    organism_name = get_organism_name(nc)
                    org = do_organism_modification(organism_name)
                    print(line.rstrip() + org,file=outp)
                else:
                    print(line, end='',file=outp)