extracting from movie.nfo

movie-extract.py

#! /usr/bin/python

import sys
import os
import re
from pathlib import Path

info = []
my_dir = "<path>"
for item in Path(my_dir).glob('./**/*.nfo'):
    M = str(item)
    attributes = []
    genre = []
    directors = []
    codec = []
    tags = []
    with open(M, "r") as f:
        for i in f:
            for j in re.findall("<title>(.+)</title>", i):
                attributes.append(j)
            for j in re.findall("<rating>(.+)</rating>", i):
                attributes.append(j)
            for j in re.findall("<year>(.+)</year>", i):
                attributes.append(j)
            for j in re.findall("<runtime>(.+)</runtime>", i):
                attributes.append(j)

    with open(M, "r") as f:
        for i in f:
            for j in re.findall("<genre>(.+)</genre>", i):
                genre.append(j)
    attributes.append(', '.join(genre))

    with open(M, "r") as f:
        for i in f:
            for j in re.findall("<director>(.+)</director>", i):
                directors.append(j)
    attributes.append(', '.join(directors))

    with open(M, "r") as f:
        for i in f:
            for j in re.findall("<codec>(.+)</codec>", i):
                codec.append(j)
    attributes.append(' / '.join(codec))

    with open(M, "r") as f:
        for i in f:
            for j in re.findall("<tag>(.+)</tag>", i):
                tags.append(j)
    attributes.append(' - '.join(tags))

    info.append('_'.join(attributes))
with open("output", "w") as w:
    for i in info:
        w.write(i + "\n")
for i in info:
    print (i)