Das deutsche Python-Forum

Code: Alles auswählen

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

from playlist2userbouquet import PLAYLIST, ANPASSEN

playlist = PLAYLIST()
anpassen = ANPASSEN()
def DICTS_ERSTELLEN():
    filename_m3u = 'M3U.txt'
    playlist.NAME_DICT_LINK_DICT(filename_m3u)
def NAME_DICT_ANPASSEN():
    for key, value in playlist.m3u_name_dict.items():
        gen = anpassen.SPLIT(value)
        parts = next(gen)
        anpassen.GROSS_KLEIN_SCHREIBUNG(parts)
        playlist.m3u_name_dict[key] = anpassen.name_neu
def TEST():
    for keys, values in playlist.m3u_name_dict.items():
        print (
                str(keys) + ' - ' + 
                values + ' - ' + 
                playlist.m3u_link_dict[keys]
                )
def main():
    DICTS_ERSTELLEN()
    NAME_DICT_ANPASSEN()
    TEST()
if __name__ == '__main__':
    main()

Code: Alles auswählen

#!/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_name_dict = dict()
        self.m3u_link_dict = dict()
        
    def NAME_DICT_LINK_DICT(self, filename_m3u):
        try:
            with io.open(filename_m3u, 'r', encoding='utf-8-sig') as m3u:
                i = 1
                for zeile in m3u:                    
                    if zeile.startswith('#EXTINF'):
                        if zeile[11] != '=' and not zeile.endswith('='):
                            name = zeile.strip().replace('#EXTINF:-1,','')
                            link = m3u.readline().rstrip()
                            self.m3u_name_dict[i] = name
                            self.m3u_link_dict[i] = link
                            i += 1
                            
        except FileNotFoundError:
            msg = 'Die Datei {!r} existiert nicht!'
            print(msg.format(filename_m3u))
        except IOError as error:
            print('Fehler beim Öffnen:', error)

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(self, value):
        playlist = PLAYLIST()
        patterns = self.PATTERNS
        if isinstance(patterns, dict):
            patterns = patterns.values()
        pattern = re.compile('|'.join(patterns))
        value = re.sub('[\[\(][^\(\)\[\]]*[\]\)]', '', value) # Klammer und deren Inhalt entfernen
        value = re.sub('(?<!(INT))(?<!(int))[_.-](?!\d)', ' ', value) # Unnötige Sonderzeichen entfernen
        value = value.strip()
        yield pattern.findall(value)
    def GROSS_KLEIN_SCHREIBUNG(self, 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())
        self.name_neu = ' '.join(part for part in renamed_parts)