fix cb01 -> sezione film (causa oscar..)

This commit is contained in:
marco
2020-01-20 19:30:55 +01:00
parent 55d615393e
commit d4f83a97bb
2 changed files with 4 additions and 25 deletions

View File

@@ -131,7 +131,7 @@ def peliculas(item):
# esclusione degli articoli 'di servizio'
blacklist = ['BENVENUTI', 'Richieste Serie TV', 'CB01.UNO ▶ TROVA L’INDIRIZZO UFFICIALE ',
'Aggiornamento Quotidiano Serie TV', 'OSCAR 2019 ▶ CB01.UNO: Vota il tuo film preferito! 🎬',
'Openload: la situazione. Benvenuto Verystream', 'Openload: lo volete ancora?']
'Openload: la situazione. Benvenuto Verystream', 'Openload: lo volete ancora?', 'OSCAR 2020 ▶ VOTA IL TUO FILM PREFERITO! 🎬']
# debug = True
if 'newest' in item.args:
if '/serietv/' not in item.url:

View File

@@ -39,30 +39,9 @@ def find_multiple_matches_groups(text, pattern):
# Convierte los codigos html "ñ" y lo reemplaza por "ñ" caracter unicode utf-8
def decodeHtmlentities(data):
entity_re = re.compile("&(#?)(\d{1,5}|\w{1,8})(;?)")
def substitute_entity(match):
ent = match.group(2) + match.group(3)
res = ""
while not ent in html5 and not ent.endswith(";") and match.group(1) != "#":
# Excepción para cuando '&' se usa como argumento en la urls contenidas en los datos
try:
res = ent[-1] + res
ent = ent[:-1]
except:
break
if match.group(1) == "#":
ent = unichr(int(ent.replace(";", "")))
return ent.encode('utf-8')
else:
cp = html5.get(ent)
if cp:
return cp.decode("unicode-escape").encode('utf-8') + res
else:
return match.group()
return entity_re.subn(substitute_entity, data)[0]
import HTMLParser
parser = HTMLParser.HTMLParser()
return parser.unescape(data)
def unescape(text):