def orderalf(item):
logger.info("%s mainlist orderalf log: %s" % (__channel__, item))
itemlist = []
# scarico la pagina
data = httptools.downloadpage(item.url, headers=headers).data
# da qui fare le opportuni modifiche
patron = '<td class="mlnh-thumb"><a href="(.*?)".title="(.*?)".*?src="(.*?)".*?mlnh-3">(.*?)<.*?"mlnh-5">.<(.*?)<td' #scrapertools.find_single_match(data, '<td class="mlnh-thumb"><a href="(.*?)".title="(.*?)".*?src="(.*?)".*?mlnh-3">(.*?)<.*?"mlnh-5">.<(.*?)<td')
matches = scrapertools.find_multiple_matches(data, patron)
for scrapedurl, scrapedtitle, scrapedimg, scrapedyear, scrapedqualang in matches:
if 'sub ita' in scrapedqualang.lower():
scrapedlang = 'Sub-ita'
else:
scrapedlang = 'ITA'
itemlist.append(
Item(channel=item.channel,
action="findvideos_film",
contentTitle=scrapedtitle,
fulltitle=scrapedtitle,
url=scrapedurl,
infoLabels={'year': scrapedyear},
contenType="movie",
thumbnail=host + scrapedimg,
title="%s [%s]" % (scrapedtitle, scrapedlang),
language=scrapedlang,
context="buscar_trailer"))
# se il sito permette l'estrazione dell'anno del film aggiungere la riga seguente
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
# Paginazione
support.nextPage(itemlist, item, data,
'<span>[^<]+</span>[^<]+<a href="(.*?)">')
return itemlist
def peliculas_latest_ep(item):
patron = r'<article.*?"TPost C".*?href="([^"]+)".*?img.*?src="([^"]+)"'
patron += r'.*?class="ClB">([^<]+)<\/span>([^<]+).*?<h3.*?>([^<]+)'
data = httptools.downloadpage(item.url).data
matches = re.compile(patron, re.DOTALL).findall(data)
itemlist = []
for scrapedurl, scrapedthumbnail, scrapednum, scrapedep, scrapedtitle in matches:
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentType=item.contentType,
title="[B]" + scrapednum + "[/B]" + scrapedep + " - " +
scrapedtitle,
fulltitle=scrapedep + " " + scrapedtitle,
show=scrapedep + " " + scrapedtitle,
url=scrapedurl,
extra=item.extra,
thumbnail="http:" + scrapedthumbnail,
infoLabels=item.infoLabels))
support.nextPage(itemlist, item, data,
r'page-numbers current.*?href="([^"]+)"')
return itemlist
def peliculas(item):
log()
itemlist = []
blacklist = ['top 10 anime da vedere']
matches, data = support.match(
item,
r'<a class="[^"]+" href="([^"]+)" title="([^"]+)"><img[^s]+src="([^"]+)"[^>]+'
)
for url, title, thumb in matches:
title = scrapertoolsV2.decodeHtmlentities(title.strip()).replace(
"streaming", "")
lang = scrapertoolsV2.find_single_match(title, r"((?:SUB ITA|ITA))")
videoType = ''
if 'movie' in title.lower():
videoType = ' - (MOVIE)'
if 'ova' in title.lower():
videoType = ' - (OAV)'
cleantitle = title.replace(lang, "").replace(
'(Streaming & Download)',
'').replace('( Streaming & Download )',
'').replace('OAV',
'').replace('OVA',
'').replace('MOVIE',
'').strip()
if not videoType:
contentType = "tvshow"
action = "episodios"
else:
contentType = "movie"
action = "findvideos"
if not title.lower() in blacklist:
itemlist.append(
Item(channel=item.channel,
action=action,
contentType=contentType,
title=support.typo(cleantitle + videoType, 'bold') +
support.typo(lang, '_ [] color kod'),
fulltitle=cleantitle,
show=cleantitle,
url=url,
thumbnail=thumb))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
autorenumber.renumber(itemlist)
support.nextPage(itemlist, item, data,
r'<a class="next page-numbers" href="([^"]+)">')
return itemlist
def peliculas(item):
logger.info("%s mainlist peliculas log: %s" % (__channel__, item))
itemlist = []
# scarico la pagina
data = httptools.downloadpage(item.url, headers=headers).data
# da qui fare le opportuni modifiche
if item.args != 'orderalf':
if item.args == 'pellicola' or item.args == 'years':
bloque = scrapertools.find_single_match(
data,
'<div class="cover boxcaption">(.*?)<div id="right_bar">')
elif item.args == "search":
bloque = scrapertools.find_single_match(
data, '<div class="cover boxcaption">(.*?)</a>')
else:
bloque = scrapertools.find_single_match(
data,
'<div class="cover boxcaption">(.*?)<div class="page_nav">')
patron = '<h2>.<a href="(.*?)".*?src="(.*?)".*?class="trdublaj">(.*?)<div class="ml-item-hiden".*?class="h4">(.*?)<.*?label">(.*?)</span'
matches = scrapertools.find_multiple_matches(data, patron)
for scrapedurl, scrapedimg, scrapedqualang, scrapedtitle, scrapedyear in matches:
if 'sub ita' in scrapedqualang.lower():
scrapedlang = 'Sub-Ita'
else:
scrapedlang = 'ITA'
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentTitle=scrapedtitle,
fulltitle=scrapedtitle,
url=scrapedurl,
infoLabels={'year': scrapedyear},
contenType="movie",
thumbnail=host + scrapedimg,
title="%s [%s]" % (scrapedtitle, scrapedlang),
language=scrapedlang))
# poichè il sito ha l'anno del film con TMDB la ricerca titolo-anno è esatta quindi inutile fare lo scrap delle locandine
# e della trama dal sito che a volte toppano
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
# Paginazione
support.nextPage(itemlist, item, data,
'<span>[^<]+</span>[^<]+<a href="(.*?)">')
return itemlist
def peliculas(item):
support.log()
itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data
patron = r'<div class="cover_kapsul ml-mask".*?<a href="(.*?)">(.*?)<\/a>.*?<img .*?src="(.*?)".*?<div class="trdublaj">(.*?)<\/div>.(<div class="sub_ita">(.*?)<\/div>|())'
matches = scrapertoolsV2.find_multiple_matches(data, patron)
for scrapedurl, scrapedtitle, scrapedthumbnail, scrapedquality, subDiv, subText, empty in matches:
info = scrapertoolsV2.find_multiple_matches(
data,
r'<span class="ml-label">([0-9]+)+<\/span>.*?<span class="ml-label">(.*?)<\/span>.*?<p class="ml-cat".*?<p>(.*?)<\/p>.*?<a href="(.*?)" class="ml-watch">'
)
infoLabels = {}
for infoLabels['year'], duration, scrapedplot, checkUrl in info:
if checkUrl == scrapedurl:
break
infoLabels['duration'] = int(duration.replace(
' min', '')) * 60 # calcolo la durata in secondi
scrapedthumbnail = host + scrapedthumbnail
scrapedtitle = scrapertoolsV2.decodeHtmlentities(scrapedtitle)
fulltitle = scrapedtitle
if subDiv:
fulltitle += support.typo(subText + ' _ () color limegreen')
fulltitle += support.typo(scrapedquality.strip() + ' _ [] color kod')
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentType=item.contenType,
contentTitle=scrapedtitle,
contentQuality=scrapedquality.strip(),
plot=scrapedplot,
title=fulltitle,
fulltitle=scrapedtitle,
show=scrapedtitle,
url=scrapedurl,
infoLabels=infoLabels,
thumbnail=scrapedthumbnail))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
support.nextPage(itemlist, item, data,
'<span>[^<]+</span>[^<]+<a href="(.*?)">')
return itemlist
def peliculas(item):
logger.info("%s mainlist peliculas log: %s" % (__channel__, item))
itemlist = []
# scarico la pagina
data = httptools.downloadpage(item.url, headers=headers).data
# da qui fare le opportuni modifiche
patron = 'class="innerImage">.*?href="([^"]+)".*?src="([^"]+)".*?'\
'class="ml-item-title">([^"]+)</.*?class="ml-item-label">'\
'(.*?)<.*?class="ml-item-label">.*?class="ml-item-label">(.*?)</'
matches = scrapertools.find_multiple_matches(data, patron)
for scrapedurl, scrapedimg, scrapedtitle, scrapedyear, scrapedlang in matches:
if 'italiano' in scrapedlang.lower():
scrapedlang = 'ITA'
else:
scrapedlang = 'Sub-Ita'
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentTitle=scrapedtitle,
fulltitle=scrapedtitle,
url=scrapedurl,
infoLabels={'year': scrapedyear},
contenType="movie",
thumbnail=scrapedimg,
title="%s [%s]" % (scrapedtitle, scrapedlang),
language=scrapedlang,
context="buscar_trailer"))
# poichè il sito ha l'anno del film con TMDB la ricerca titolo-anno è esatta quindi inutile fare lo scrap delle locandine
# e della trama dal sito che a volte toppano
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
# Paginazione
support.nextPage(itemlist, item, data,
'<span>\d</span> <a href="([^"]+)">')
return itemlist
def lista_serie(item):
support.log(item.channel + " lista_serie")
itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data
patron = r'<div class="item">\s*<a href="([^"]+)" data-original="([^"]+)" class="lazy inner">'
patron += r'[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedurl, scrapedimg, scrapedtitle in matches:
infoLabels = {}
year = scrapertools.find_single_match(scrapedtitle, '\((\d{4})\)')
if year:
infoLabels['year'] = year
scrapedtitle = cleantitle(scrapedtitle)
itemlist.append(
Item(channel=item.channel,
action="episodios",
title=scrapedtitle,
fulltitle=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedimg,
show=scrapedtitle,
infoLabels=infoLabels,
contentType='tvshow',
folder=True))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
# Pagine
support.nextPage(itemlist, item, data,
'<li><a href="([^"]+)">Pagina successiva')
return itemlist