Parser/OVI/EstraiLemmi.py

import re
import csv
import os

lemmi = []
basepath_lemmi = '/Users/alessiaspadi/Documents/RESTORE/temp_ovi/lemmi'
for entry in os.listdir(basepath_lemmi):
    if os.path.isfile(os.path.join(basepath_lemmi, entry)):
        ll = entry.split('.')[1].lstrip().split(' ')[0]
        if ll != '':
            lemmi.append([ll, entry])


iperlem_data = open('iperlem_Data.csv', 'w')
csvwriter = csv.writer(iperlem_data)

params = ["sigla", "file", "num", "iperlemma", "commento", "livello"]
csvwriter.writerow(params)


def write_lines(lines, sig, file):
    for line in lines:
        row = [sig, file]
        lem = re.split('\|', line)
        for l in lem:
            if "IPERLEMMA" in l:
                ll = l.replace("IPERLEMMA", " ")
            else:
                ll = l
            m = ll.rstrip()
            n = m.lstrip()
            row.append(n)
        csvwriter.writerow(row)


for x in range(len(lemmi)):
    sigla = lemmi[x][0]
    file_name = lemmi[x][1]
    f = open('/Users/alessiaspadi/Documents/RESTORE/temp_ovi/lemmi/' + file_name, "r", encoding='latin-1')
    lines = f.readlines()
    clean_lines = []
    for line in lines:
        if "IPERLEMMA" in line:
            clean_lines.append(line)
    write_lines(clean_lines, sigla, file_name)


f.close()

iperlem_data.close()