gistfile1.txt

def process_file(filename, fields):
    classification_list = ['family', 'class', 'phylum','order','kingdom', 'genus']
    process_fields = fields.keys()
    data = []
    with open(filename, "r") as f:
        reader = csv.DictReader(f)
        for i in range(3):
            l = reader.next()

        for line in reader:
            new_dict = {}
            new_dict['classification'] = {}
            for field in fields:
                line[field] = line[field].strip()
                if fields[field] == 'label':
                    line[field] = re.sub(r'\([^)]*\)', '', line[field]).strip() #http://stackoverflow.com/questions/640001/how-can-i-remove-text-within-parentheses-with-a-regex
                    
                if fields[field] == 'name':
                    if line[field] == 'NULL' or re.search('[\W-]+', line[field]) != None:
                        line[field] = line['rdf-schema#label']
                if line[field] == 'NULL':
                    line[field] = None
                if fields[field] == 'synonym':
                    if line[field] != None:
                        syn_list = []
                        for i in line[field].split('|'):
                            syn_list.append(i.strip("{} *"))
                        line[field] = syn_list
                if fields[field] in classification_list:
                    new_dict['classification'][fields[field]] = line[field]
                else:
                    new_dict[fields[field]] = line[field]
            data.append(new_dict)
    return data