playlist2userbouquet.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from __future__ import print_function
import io
import time
import re


class PLAYLIST(object):
    def __init__(self):
        self.m3u_dict = dict()

    def m3u_to_m3u_dict(self, filename_m3u):
        try:
            with io.open(filename_m3u, 'r', encoding='utf-8-sig') as m3u:
                for zeile in m3u:
                    if zeile[:7] == '#EXTINF' :
                        if not zeile[11] == '=' and not zeile[:1] == '=':
                            zeile = zeile.rstrip()
                            name = zeile.replace('#EXTINF:-1,','')
                            link = link = m3u.readline()
                            link = link.rstrip()
                            self.m3u_dict[name] = link

        except EnvironmentError:
            print ('Die Datei: >>' + filename_m3u + '<< existiert nicht!')
            pass # Ignore I/O errors.

class ANPASSEN():
    def __init__(self):
        self.PATTERNS = [
            r'\+\d',                            # +2, +7
            r'\d[+x]\d',                        # 1+1, 2x2
            r'(?<=\b)[A-ZА-Я]{1,2}\d{1,2}\b',   # A1, AB12
            r'\b[JT][ui][CJ][ei]',              # JuCe TV, TiJi
            r'[A-ZА-Я][a-zа-я]+\.?',            # Abzde, int.
            r'[A-Za-zА-Яа-я][A-ZА-Яa-zа-я]+\.?',# ABSDE, Int.
            r'(?<=\b)[A-ZА-Я]{1,2}(?=\b)',      # A, AB, ABC
            r'\d[A-ZА-Я]\b',                    # 1A
            r'\d\.?\d+',                        # 1234, 2.0, 3.123
            r'\d',
            ]
        self.SHORT_NAMES_TO_TITLE = {
            'geo', 'nat', 'дом', 'моя', 'кто', 'hit', 'box',
            'pro', 'doc', 'and', 'sci', 'fi', 'top', 'еда',
            'дон', 'мир', 'ля', 'на', 'раз', 'рен'
            }
        self.LONG_NAMES_TO_IGNORE = {
            'JuCe', 'TiJi', 'HITV', 'НСТВ', 'СССР', 'СТРК'
            }

    def split(patterns, liste):
        if isinstance(patterns, dict):
            patterns = patterns.values()
        pattern = re.compile('|'.join(patterns))
        for line in liste():
            line = re.sub('[\[\(][^\(\)\[\]]*[\]\)]', '', line)         # Klammer und deren Inhalt entfernen
            line = re.sub('(?<!(INT))(?<!(int))[_.-](?!\d)', ' ', line) # Unnötige Sonderzeichen entfernen
            line = line.rstrip()
            yield pattern.findall(line)

    def gross_klein_schreibung(parts):
        renamed_parts = []
        for part in parts:
            if len(part) <= 3:
                if part.lower() in self.SHORT_NAMES_TO_TITLE:
                    renamed_parts.append(part.title())
                else:
                    renamed_parts.append(part.upper())
            elif part in self.LONG_NAMES_TO_IGNORE:
                renamed_parts.append(part)
            else:
                renamed_parts.append(part.title())
        zeile = ' '.join(part for part in renamed_parts)
        print ('Das ist die zeile: ' + zeile)