def anime(item):
log()
itemlist = []
seasons = support.match(item, r'<div class="sp-body[^"]+">(.*?)<\/div>')[0]
for season in seasons:
episodes = scrapertoolsV2.find_multiple_matches(
season, r'<a.*?href="([^"]+)"[^>]+>([^<]+)<\/a>(.*?)<(:?br|\/p)')
for url, title, urls, none in episodes:
urls = scrapertoolsV2.find_multiple_matches(
urls, '<a.*?href="([^"]+)"[^>]+>')
for url2 in urls:
url += url2 + '\n'
log('EP URL', url)
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentType=item.contentType,
title=support.typo(title + ' - ' + item.fulltitle,
'bold'),
url=url,
fulltitle=title + ' - ' + item.show,
show=item.show,
thumbnail=item.thumbnail,
args=item.args))
autorenumber.renumber(itemlist, item, 'bold')
support.videolibrary(itemlist, item, 'color kod bold')
return itemlist
def hdpass_get_servers(item):
# Carica la pagina
data = httptools.downloadpage(item.url).data.replace('\n', '')
patron = r'<iframe(?: id="[^"]+")? width="[^"]+" height="[^"]+" src="([^"]+)"[^>]+><\/iframe>'
url = scrapertoolsV2.find_single_match(data, patron).replace("?alta", "")
url = url.replace("&download=1", "")
if 'https' not in url:
url = 'https:' + url
if 'hdpass' or 'hdplayer' in url:
data = httptools.downloadpage(url).data
start = data.find('<div class="row mobileRes">')
end = data.find('<div id="playerFront">', start)
data = data[start:end]
patron_res = '<div class="row mobileRes">(.*?)</div>'
patron_mir = '<div class="row mobileMirrs">(.*?)</div>'
patron_media = r'<input type="hidden" name="urlEmbed" data-mirror="([^"]+)" id="urlEmbed"\s*value="([^"]+)"\s*/>'
res = scrapertoolsV2.find_single_match(data, patron_res)
itemlist = []
for res_url, res_video in scrapertoolsV2.find_multiple_matches(
res, '<option.*?value="([^"]+?)">([^<]+?)</option>'):
data = httptools.downloadpage(urlparse.urljoin(
url, res_url)).data.replace('\n', '')
mir = scrapertoolsV2.find_single_match(data, patron_mir)
for mir_url, server in scrapertoolsV2.find_multiple_matches(
mir, '<option.*?value="([^"]+?)">([^<]+?)</value>'):
data = httptools.downloadpage(urlparse.urljoin(
url, mir_url)).data.replace('\n', '')
for media_label, media_url in scrapertoolsV2.find_multiple_matches(
data, patron_media):
itemlist.append(
Item(channel=item.channel,
action="play",
title=item.title +
typo(server, '-- [] color kod') +
typo(res_video, '-- [] color kod'),
fulltitle=item.fulltitle,
quality=res_video,
show=item.show,
thumbnail=item.thumbnail,
contentType=item.contentType,
server=server,
url=url_decode(media_url)))
log("video -> ", res_video)
return controls(itemlist, item, AutoPlay=True, CheckLinks=True)
def episodios(item):
logger.info(item.channel + 'findvideos')
itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data
if 'accordion-item' in data:
block = scrapertoolsV2.find_single_match(
data, 'accordion-item.*?>(.*?)<div id="disqus_thread">')
patron = r'<img src="([^"]+)">.*?<li class="season-no">(.*?)<\/li>(.*?)<\/table>'
matches = scrapertoolsV2.find_multiple_matches(block, patron)
for scrapedthumb, scrapedtitle, scrapedurl in matches:
title = scrapedtitle + ' - ' + item.title
if title[0] == 'x':
title = '1' + title
itemlist.append(
Item(channel=item.channel,
action='findvideos',
contentType=item.contentType,
title=title,
fulltitle=title,
show=title,
quality=item.quality,
url=scrapedurl,
thumbnail=scrapedthumb))
else:
block = scrapertoolsV2.find_single_match(
data, '<div id="info" class="pad">(.*?)<div id="disqus_thread">'
).replace('</p>', '<br />').replace('×', 'x')
matches = scrapertoolsV2.find_multiple_matches(
block, r'<strong>(.*?)<\/strong>.*?<p>(.*?)<span')
for lang, seasons in matches:
lang = re.sub('.*?Stagione[^a-zA-Z]+', '', lang)
# patron = r'([0-9]+x[0-9]+) (.*?)<br'
season = scrapertoolsV2.find_multiple_matches(
seasons, r'([0-9]+x[0-9]+) (.*?)<br')
for title, url in season:
title = title + ' - ' + lang
itemlist.append(
Item(channel=item.channel,
title=title,
fulltitle=title,
show=title,
url=url,
contentType=item.contentType,
action='findvideos'))
return itemlist
def findvideos(item):
log()
# itemlist = []
if item.args == 'anime':
data = item.url
else:
data = httptools.downloadpage(item.url, headers=headers).data
# Check if is series
check = scrapertoolsV2.find_single_match(
data.replace('\t', '').replace('\n', ''),
r'<div class="category-film"><h3>([^<]+)<\/h3>')
if 'serie tv' in check.lower(): return episodios(item)
elif 'anime' in check.lower(): return anime(item)
if 'protectlink' in data:
urls = scrapertoolsV2.find_multiple_matches(
data, r'<iframe src="[^=]+=(.*?)"')
for url in urls:
url = url.decode('base64')
if '\t' in url:
url = url[:-1]
data += '\t' + url
if 'nodmca' in data:
page = httptools.downloadpage(url, headers=headers).data
data += '\t' + scrapertoolsV2.find_single_match(
page, '<meta name="og:url" content="([^=]+)">')
return support.server(item, data, headers=headers)
def dooplay_get_links(item, host):
# get links from websites using dooplay theme and dooplay_player
# return a list of dict containing these values: url, title and server
data = httptools.downloadpage(item.url).data.replace("'", '"')
patron = r'<li id="player-option-[0-9]".*?data-type="([^"]+)" data-post="([^"]+)" data-nume="([^"]+)".*?<span class="title".*?>([^<>]+)</span>(?:<span class="server">([^<>]+))?'
matches = scrapertoolsV2.find_multiple_matches(data, patron)
ret = []
for type, post, nume, title, server in matches:
postData = urllib.urlencode({
"action": "doo_player_ajax",
"post": post,
"nume": nume,
"type": type
})
dataAdmin = httptools.downloadpage(host + '/wp-admin/admin-ajax.php',
post=postData,
headers={
'Referer': item.url
}).data
link = scrapertoolsV2.find_single_match(dataAdmin,
"<iframe.*src='([^']+)'")
ret.append({'url': link, 'title': title, 'server': server})
return ret
def dooplay_get_episodes(item):
itemlist = []
item.contentType = "episode"
data = httptools.downloadpage(item.url).data.replace("'", '"')
patron = '<li class="mark-[0-9]">.*?<img.*?data-lazy-src="([^"]+).*?([0-9] - [0-9]).*?<a href="([^"]+)">([^<>]+).*?([0-9]{4})'
for scrapedthumb, scrapedep, scrapedurl, scrapedtitle, scrapedyear in scrapertoolsV2.find_multiple_matches(
data, patron):
scrapedep = scrapedep.replace(' - ', 'x')
infoLabels = {}
infoLabels['year'] = scrapedyear
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentType="episode",
title=scrapedep + " " + scrapedtitle,
fulltitle=scrapedtitle,
show=item.fulltitle,
url=scrapedurl,
thumbnail=scrapedthumb,
infoLabels=infoLabels))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
videolibrary(itemlist, item)
return itemlist
def findvideos(item):
logger.info(item.channel + 'findvideos')
itemlist = []
logger.info('TYPE= ' + item.contentType)
if item.contentType == 'movie':
data = httptools.downloadpage(item.url, headers=headers).data
logger.info('DATA= ' + data)
item.url = scrapertoolsV2.find_single_match(data,
r'<table>(.*?)<\/table>')
urls = scrapertoolsV2.find_multiple_matches(
item.url, r"<a href='([^']+)'.*?>.*?>.*?([a-zA-Z]+).*?<\/a>")
logger.info('EXTRA= ' + item.extra)
for url, server in urls:
itemlist.append(
Item(channel=item.channel,
action='play',
title=item.title + ' [COLOR blue][' + server + '][/COLOR]',
contentType="movie",
server=server,
url=url))
autoplay.start(itemlist, item)
return itemlist
def findvideos(item):
log()
itemlist = []
matches, data = support.match(item, r'class="tab.*?data-name="([0-9]+)">([^<]+)</span', headers=headers)
videoData = ''
for serverid, servername in matches:
block = scrapertoolsV2.find_multiple_matches(data,'data-id="'+serverid+'">(.*?)<div class="server')
id = scrapertoolsV2.find_single_match(str(block),r'<a data-id="([^"]+)" data-base="'+item.fulltitle+'"')
dataJson = httptools.downloadpage('%s/ajax/episode/info?id=%s&server=%s&ts=%s' % (host, id, serverid, int(time.time())), headers=[['x-requested-with', 'XMLHttpRequest']]).data
json = jsontools.load(dataJson)
log('JSON= ',json)
videoData +='\n'+json['grabber']
if serverid == '28':
itemlist.append(
Item(
channel=item.channel,
action="play",
title='diretto',
quality='',
url=json['grabber'],
server='directo',
show=item.show,
contentType=item.contentType,
folder=False))
return support.server(item, videoData, itemlist)
def search(item, texto):
logger.info("[casacinemaInfo.py] " + item.url + " search " + texto)
item.url = host + "?s=" + texto
data = httptools.downloadpage(item.url).data
itemlist = []
patron = '<li class="col-md-12 itemlist">.*?<a href="([^"]+)" title="([^"]+)".*?<img src="([^"]+)".*?Film dell\\\'anno: ([0-9]{4}).*?<p class="text-list">([^<>]+)</p>'
matches = scrapertoolsV2.find_multiple_matches(data, patron)
for scrapedurl, scrapedtitle, scrapedthumbnail, scrapedyear, scrapedplot in matches:
title = scrapertoolsV2.decodeHtmlentities(scrapedtitle)
cleantitle = title.replace('[Sub-ITA]', '').strip()
infoLabels = {
"plot": scrapertoolsV2.decodeHtmlentities(scrapedplot),
"year": scrapedyear
}
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentType="movie",
title=title,
url=scrapedurl,
thumbnail=scrapedthumbnail,
infoLabels=infoLabels,
fulltitle=cleantitle))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
return itemlist
def match(item, patron='', patronBlock='', headers='', url='', post=''):
matches = []
if type(item) == str:
data = item
else:
url = url if url else item.url
if post:
data = httptools.downloadpage(url,
headers=headers,
ignore_response_code=True,
post=post).data.replace("'", '"')
else:
data = httptools.downloadpage(
url, headers=headers,
ignore_response_code=True).data.replace("'", '"')
data = re.sub(r'\n|\t', ' ', data)
data = re.sub(r'>\s\s*<', '><', data)
log('DATA= ', data)
if patronBlock:
block = scrapertoolsV2.find_single_match(data, patronBlock)
log('BLOCK= ', block)
else:
block = data
if patron:
matches = scrapertoolsV2.find_multiple_matches(block, patron)
log('MATCHES= ', matches)
return matches, block
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 findvideos(item):
log()
itemlist =[]
matches, data = support.match(item, '<iframe class="metaframe rptss" src="([^"]+)"[^>]+>',headers=headers)
for url in matches:
html = httptools.downloadpage(url, headers=headers).data
data += str(scrapertoolsV2.find_multiple_matches(html, '<meta name="og:url" content="([^"]+)">'))
itemlist = support.server(item, data)
return itemlist
def episodios(item):
item.contentType = 'episode'
itemlist = []
data = httptools.downloadpage(item.url).data
matches = scrapertoolsV2.find_multiple_matches(
data,
r'(<div class="sp-head[a-z ]*?" title="Espandi">[^<>]*?</div>.*?)<div class="spdiv">\[riduci\]</div>'
)
for match in matches:
support.log(match)
blocks = scrapertoolsV2.find_multiple_matches(
match, '(?:<p>)(.*?)(?:</p>|<br)')
season = scrapertoolsV2.find_single_match(
match, r'title="Espandi">.*?STAGIONE\s+\d+([^<>]+)').strip()
for block in blocks:
episode = scrapertoolsV2.find_single_match(
block, r'([0-9]+(?:×|×)[0-9]+)').strip()
seasons_n = scrapertoolsV2.find_single_match(
block, r'<strong>STAGIONE\s+\d+([^<>]+)').strip()
if seasons_n:
season = seasons_n
if not episode: continue
season = re.sub(r'–|–', "-", season)
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentType=item.contentType,
title="[B]" + episode + "[/B] " + season,
fulltitle=episode + " " + season,
show=episode + " " + season,
url=block,
extra=item.extra,
thumbnail=item.thumbnail,
infoLabels=item.infoLabels))
support.videolibrary(itemlist, item)
return itemlist
def elenco_aggiornamenti_serietv(item):
"""
def per la lista degli aggiornamenti
"""
logger.info("%s elenco_aggiornamenti_serietv log: %s" %
(__channel__, item))
itemlist = []
# Carica la pagina
data = httptools.downloadpage(item.url).data
# Estrae i contenuti
#bloque = scrapertoolsV2.get_match(data, '<div class="entry">(.*?)<div class="clear"></div>')
bloque = scrapertoolsV2.find_single_match(
data, '<div class="entry">(.*?)<div class="clear"></div>')
patron = '<span class="serieTitle".*?>(.*?)<.*?href="(.*?)".*?>(.*?)<'
matches = scrapertoolsV2.find_multiple_matches(bloque, patron)
for scrapedtitle, scrapedurl, scrapedepisodies in matches:
if "(SUB ITA)" in scrapedepisodies.upper():
lang = "SUB ITA"
scrapedepisodies = scrapedepisodies.replace('(SUB ITA)', '')
else:
lang = "ITA"
scrapedepisodies = scrapedepisodies.replace(lang, '')
#num = scrapertoolsV2.find_single_match(scrapedepisodies, '(-\d+/)')
#if num:
# scrapedurl = scrapedurl.replace(num, "-episodi/")
scrapedtitle = scrapedtitle.replace("–",
"").replace('\xe2\x80\x93 ',
'').strip()
scrapedepisodies = scrapedepisodies.replace('\xe2\x80\x93 ',
'').strip()
itemlist.append(
Item(
channel=item.channel,
action="episodios",
contentType="tvshow",
title="%s" %
scrapedtitle, # %s" % (scrapedtitle, scrapedepisodies),
fulltitle="%s %s" % (scrapedtitle, scrapedepisodies),
text_color=color5,
url=scrapedurl,
#show = "%s %s" % (scrapedtitle, scrapedepisodies),
extra=item.extra,
#lang = lang,
#data = data,
folder=True))
# locandine e trama e altro da tmdb se presente l'anno migliora la ricerca
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True, idioma_busqueda='it')
return itemlist
def episodios(item):
logger.info("kod.mondoserietv episodios")
itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data
blocco = scrapertools.find_single_match(data, '<table>(.*?)</table>')
patron = "<tr><td><b>(.*?)(\d+)((?:x\d+| ))(.*?)<\/b>(.*?<tr>)"
matches = scrapertoolsV2.find_multiple_matches(blocco, patron)
for t1, s, e, t2, scrapedurl in matches:
if "x" not in e:
e = s
if e == s:
s = None
if s is None:
s = "1"
if s.startswith('0'):
s = s.replace("0", "")
if e.startswith('x'):
e = e.replace("x", "")
scrapedtitle = t1 + s + "x" + e + " " + t2
itemlist.append(
Item(channel=item.channel,
contentType="episode",
action="findvideos",
items=s,
iteme=e,
fulltitle=scrapedtitle,
show=scrapedtitle,
title="[COLOR azure]" + scrapedtitle + "[/COLOR]",
url=scrapedurl,
thumbnail=item.scrapedthumbnail,
plot=item.scrapedplot,
folder=True))
if config.get_videolibrary_support() and len(itemlist) != 0:
itemlist.append(
Item(channel=item.channel,
title="[COLOR lightblue]%s[/COLOR]" %
config.get_localized_string(30161),
url=item.url,
action="add_serie_to_library",
extra="episodios",
show=item.show))
return itemlist
def findvideos(item):
log()
itemlist = []
data = httptools.downloadpage(item.url).data
if 'keepem.online' in data:
urls = scrapertoolsV2.find_multiple_matches(
data, r'(https://keepem\.online/f/[^"]+)"')
for url in urls:
url = httptools.downloadpage(url).url
itemlist += servertools.find_video_items(data=url)
return support.server(item, data, itemlist)
def peliculas(item):
logger.info(item.channel + 'peliculas')
itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data
block = scrapertoolsV2.find_single_match(data,
r'<ul class="posts">(.*)<\/ul>')
patron = r'<li><a href="([^"]+)" data-thumbnail="([^"]+)">.*?<div class="title">([^<]+)<\/div>'
matches = scrapertoolsV2.find_multiple_matches(block, patron)
for scrapedurl, scrapedthumb, scrapedtitle in matches:
title = re.sub(r'.\(.*?\)|.\[.*?\]', '', scrapedtitle)
quality = scrapertoolsV2.find_single_match(scrapedtitle, r'\[(.*?)\]')
if not quality:
quality = 'SD'
longtitle = title + ' [COLOR blue][' + quality + '][/COLOR]'
if item.contentType == 'episode':
action = 'episodios'
else:
action = 'findvideos'
itemlist.append(
Item(channel=item.channel,
action=action,
contentType=item.contentType,
title=longtitle,
fulltitle=title,
show=title,
quality=quality,
url=scrapedurl,
thumbnail=scrapedthumb))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
next_page = scrapertoolsV2.find_single_match(data,
'<a href="([^"]+)">Pagina')
if next_page != "":
itemlist.append(
Item(channel=item.channel,
action="peliculas",
contentType=item.contentType,
title="[COLOR blue]" + config.get_localized_string(30992) +
" >[/COLOR]",
url=next_page,
thumbnails=thumb()))
return itemlist
def peliculas(item):
logger.info("[casacinemaInfo.py] peliculas")
itemlist = []
# Carica la pagina
data = httptools.downloadpage(item.url).data
# Estrae i contenuti
patron = '<div class="col-mt-5 postsh">[^<>]+<div class="poster-media-card">[^<>]+<a href="([^"]+)" title="([^"]+)".*?<img src="([^"]+)"'
matches = scrapertoolsV2.find_multiple_matches(data, patron)
for scrapedurl, scrapedtitle, scrapedthumbnail in matches:
title = scrapertoolsV2.decodeHtmlentities(scrapedtitle)
cleantitle = title.replace('[Sub-ITA]', '').strip()
itemlist.append(
Item(channel=item.channel,
action="findvideos",
contentType="movie",
title=title,
url=scrapedurl,
thumbnail=scrapedthumbnail,
fulltitle=cleantitle))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
## Paginación
next_page = scrapertoolsV2.find_single_match(
data, '<a href="([^"]+)"><i class="glyphicon glyphicon-chevron-right"'
) ### <- Regex rimosso spazio - precedente <li><a href="([^"]+)" >Pagina -> Continua. riga 221
if next_page != "":
itemlist.append(
Item(
channel=item.channel,
action="peliculas",
title="[COLOR lightgreen]" +
config.get_localized_string(30992) + "[/COLOR]",
url=next_page,
extra=item.extra,
thumbnail=
"http://2.bp.blogspot.com/-fE9tzwmjaeQ/UcM2apxDtjI/AAAAAAAAeeg/WKSGM2TADLM/s1600/pager+old.png"
))
return itemlist
def genre(item):
logger.info(item.channel + 'genre')
itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data
block = scrapertoolsV2.find_single_match(data, r'<ul class="table-list">(.*?)<\/ul>')
matches = scrapertoolsV2.find_multiple_matches(block, r'<a href="([^"]+)">.*?<\/span>(.*?)<\/a>')
for url, title in matches:
itemlist.append(
Item(channel=item.channel,
action='peliculas',
title=title,
url=host+url)
)
itemlist = thumb(itemlist)
return itemlist
def az(item):
logger.info(item.channel + 'genre')
itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data
block = scrapertoolsV2.find_single_match(data, r'<select class="cats">(.*?)<\/select>')
matches = scrapertoolsV2.find_multiple_matches(block, r'<option data-src="([^"]+)">(.*?)<\/option>')
for url, title in matches:
itemlist.append(
Item(channel=item.channel,
action='peliculas',
title=title,
url=url)
)
itemlist = thumb(itemlist)
return itemlist
def match(item, patron='', patron_block='', headers='', url=''):
url = url if url else item.url
data = httptools.downloadpage(url, headers=headers).data.replace("'", '"')
data = re.sub('\n|\t', '', data)
log('DATA= ', data)
if patron_block:
block = scrapertoolsV2.find_single_match(data, patron_block)
log('BLOCK= ', block)
else:
block = data
if patron:
matches = scrapertoolsV2.find_multiple_matches(block, patron)
log('MATCHES= ', matches)
return matches, data
def web_menu():
itemlist = []
data = httptools.downloadpage(host, headers=headers).data
matches = scrapertoolsV2.find_multiple_matches(
data, r'<li class="page_item.*?><a href="([^"]+)">(.*?)<\/a>')
blacklist = ['DMCA', 'Contatti', 'Attenzione NON FARTI OSCURARE']
for url, title in matches:
if not title in blacklist:
title = title.replace('Lista ', '') + ' bold'
if 'film' in title.lower():
contentType = 'movie'
else:
contentType = 'episode'
support.menu(itemlist,
title,
'peliculas',
url,
contentType=contentType)
return itemlist
def findvideos(item):
support.log()
itemlist = []
data = httptools.downloadpage(item.url).data
data = re.sub(r'\n|\t', ' ', data)
data = re.sub(r'>\s\s*<', '><', data)
patronBlock = r'LINK STREAMING(?P<block>.*?)LINK DOWNLOAD'
patron = r'href="(.+?)"'
block = scrapertoolsV2.find_single_match(data, patronBlock)
urls = scrapertoolsV2.find_multiple_matches(block, patron)
for url in urls:
lang = ''
if 'sub_ita' in url.lower():
lang = 'Sub-ITA'
else:
lang = 'ITA'
if 'keepem.online' in data:
urls = scrapertoolsV2.find_multiple_matches(
data, r'(https://keepem\.online/f/[^"]+)"')
for url in urls:
url = httptools.downloadpage(url).url
itemlist += servertools.find_video_items(data=url)
elif 'keepsetsu' in url.lower() or 'woof' in url.lower():
if 'keepsetsu' in url.lower():
support.log("keepsetsu url -> ", url)
data = httptools.downloadpage(url).url
support.log("LINK-DATA :", data)
data = httptools.downloadpage(data).data
support.log("LINK-DATA2 :", data)
video_urls = scrapertoolsV2.find_single_match(
data, r'<meta name="description" content="([^"]+)"')
else:
data = httptools.downloadpage(url).data
host_video = scrapertoolsV2.find_single_match(
data, r'var thisPageUrl = "(http[s]\:\/\/[^\/]+).+?"')
link = scrapertoolsV2.find_single_match(data,
r'<video src="([^"]+)"')
video_urls = host_video + link
title = support.typo(item.fulltitle, '_ bold') + support.typo(
lang, '_ [] color kod')
itemlist.append(
support.Item(
channel=item.channel,
action="play",
contentType=item.contentType,
title=title,
fulltitle=title,
show=title,
url=video_urls,
infoLabels=item.infoLabels,
thumbnail=item.thumbnail,
contentSerieName=item.contentSerieName,
contentTitle=title,
contentLanguage='ITA' if lang == [] else lang,
args=item.args,
server='directo',
))
return itemlist
def episodios(item):
#logger.info("%s episodios log: %s" % (__channel__, item))
itemlist = []
if not (item.lang):
lang_season = {'ITA': 0, 'SUB ITA': 0}
# Download pagina
data = httptools.downloadpage(item.url).data
#========
if 'clicca qui per aprire' in data.lower():
logger.info("%s CLICCA QUI PER APRIRE GLI EPISODI log: %s" %
(__channel__, item))
item.url = scrapertoolsV2.find_single_match(
data, '"go_to":"(.*?)"')
item.url = item.url.replace("\\", "")
# Carica la pagina
data = httptools.downloadpage(item.url).data
#logger.info("%s FINE CLICCA QUI PER APRIRE GLI EPISODI log: %s" % (__channel__, item))
elif 'clicca qui</span>' in data.lower():
logger.info("%s inizio CLICCA QUI</span> log: %s" %
(__channel__, item))
item.url = scrapertoolsV2.find_single_match(
data, '<h2 style="text-align: center;"><a href="(.*?)">')
data = httptools.downloadpage(item.url).data
#logger.info("%s fine CLICCA QUI</span> log: %s" % (__channel__, item))
#=========
data = scrapertoolsV2.decodeHtmlentities(data)
bloque = scrapertoolsV2.find_single_match(
data, '<div class="su-accordion">(.*?)<div class="clear"></div>')
patron = '<span class="su-spoiler-icon"></span>(.*?)</div>'
matches = scrapertoolsV2.find_multiple_matches(bloque, patron)
for scrapedseason in matches:
#logger.info("%s scrapedseason log: %s" % (__channel__, scrapedseason))
if "(SUB ITA)" in scrapedseason.upper():
lang = "SUB ITA"
lang_season['SUB ITA'] += 1
else:
lang = "ITA"
lang_season['ITA'] += 1
#logger.info("%s lang_dict log: %s" % (__channel__, lang_season))
for lang in sorted(lang_season):
if lang_season[lang] > 0:
itemlist.append(
Item(
channel=item.channel,
action="episodios",
#contentType = "episode",
contentSerieName=item.title,
title='%s (%s)' % (item.title, lang),
url=item.url,
fulltitle=item.title,
data=data,
lang=lang,
show=item.show,
folder=True,
))
# locandine e trama e altro da tmdb se presente l'anno migliora la ricerca
tmdb.set_infoLabels_itemlist(itemlist,
seekTmdb=True,
idioma_busqueda='it')
return itemlist
else:
# qui ci vanno le puntate delle stagioni
html = item.data
logger.info("%s else log: [%s]" % (__channel__, item))
if item.lang == 'SUB ITA':
item.lang = '\(SUB ITA\)'
logger.info("%s item.lang log: %s" % (__channel__, item.lang))
bloque = scrapertoolsV2.find_single_match(
html, '<div class="su-accordion">(.*?)<div class="clear"></div>')
patron = '<span class="su-spoiler-icon"></span>.*?' + item.lang + '</div>(.*?)</div>' # leggo tutte le stagioni
#logger.info("%s patronpatron log: %s" % (__channel__, patron))
matches = scrapertoolsV2.find_multiple_matches(bloque, patron)
for scrapedseason in matches:
#logger.info("%s scrapedseasonscrapedseason log: %s" % (__channel__, scrapedseason))
scrapedseason = scrapedseason.replace('<strong>',
'').replace('</strong>', '')
patron = '(\d+)×(\d+)(.*?)<(.*?)<br />' # stagione - puntanta - titolo - gruppo link
matches = scrapertoolsV2.find_multiple_matches(
scrapedseason, patron)
for scrapedseason, scrapedpuntata, scrapedtitolo, scrapedgroupurl in matches:
#logger.info("%s finale log: %s" % (__channel__, patron))
scrapedtitolo = scrapedtitolo.replace('–', '')
itemlist.append(
Item(
channel=item.channel,
action="findvideos",
contentType="episode",
#contentSerieName = item.contentSerieName,
contentTitle=scrapedtitolo,
title='%sx%s %s' %
(scrapedseason, scrapedpuntata, scrapedtitolo),
url=scrapedgroupurl,
fulltitle=item.fulltitle,
#show = item.show,
#folder = True,
))
logger.info("%s itemlistitemlist log: %s" % (__channel__, itemlist))
# Opción "Añadir esta película a la biblioteca de KODI"
if item.extra != "library":
if config.get_videolibrary_support(
) and len(itemlist) > 0 and item.extra != 'findvideos':
itemlist.append(
Item(channel=item.channel,
title="%s" % config.get_localized_string(30161),
text_color="green",
extra="episodios",
action="add_serie_to_library",
url=item.url,
thumbnail=get_thumb('videolibrary', auto=True),
contentTitle=item.contentSerieName,
lang=item.lang,
show=item.show,
data=html
#, infoLabels = item.infoLabels
))
return itemlist
def scrape(item,
patron='',
listGroups=[],
headers="",
blacklist="",
data="",
patron_block="",
patronNext="",
action="findvideos",
url_host="",
addVideolibrary=True):
# patron: the patron to use for scraping page, all capturing group must match with listGroups
# listGroups: a list containing the scraping info obtained by your patron, in order
# accepted values are: url, title, thumb, quality, year, plot, duration, genre, rating
# header: values to pass to request header
# blacklist: titles that you want to exclude(service articles for example)
# data: if you want to pass data manually, maybe because you need some custom replacement
# patron_block: patron to get parts of the page (to scrape with patron attribute),
# if you need a "block inside another block" you can create a list, please note that all matches
# will be packed as string
# patronNext: patron for scraping next page link
# action: if you want results perform an action different from "findvideos", useful when scraping film by genres
# url_host: string to prepend to scrapedurl, useful when url don't contain host
# example usage:
# import support
# itemlist = []
# patron = 'blablabla'
# headers = [['Referer', host]]
# blacklist = 'Request a TV serie!'
# return support.scrape(item, itemlist, patron, ['thumb', 'quality', 'url', 'title', 'year', 'plot'],
# headers=headers, blacklist=blacklist)
itemlist = []
if not data:
data = httptools.downloadpage(item.url,
headers=headers).data.replace("'", '"')
data = re.sub('\n|\t', ' ', data)
# replace all ' with " and eliminate newline, so we don't need to worry about
log('DATA =', data)
block = data
if patron_block:
if type(patron_block) == str:
patron_block = [patron_block]
for n, regex in enumerate(patron_block):
blocks = scrapertoolsV2.find_multiple_matches(block, regex)
block = ""
for b in blocks:
block += "\n" + b
log('BLOCK ', n, '=', block)
else:
block = data
if patron and listGroups:
matches = scrapertoolsV2.find_multiple_matches(block, patron)
log('MATCHES =', matches)
for match in matches:
if len(listGroups) > len(match): # to fix a bug
match = list(match)
match.extend([''] * (len(listGroups) - len(match)))
scrapedurl = url_host + match[listGroups.index(
'url')] if 'url' in listGroups else ''
scrapedtitle = match[listGroups.index(
'title')] if 'title' in listGroups else ''
scrapedthumb = match[listGroups.index(
'thumb')] if 'thumb' in listGroups else ''
scrapedquality = match[listGroups.index(
'quality')] if 'quality' in listGroups else ''
scrapedyear = match[listGroups.index(
'year')] if 'year' in listGroups else ''
scrapedplot = match[listGroups.index(
'plot')] if 'plot' in listGroups else ''
scrapedduration = match[listGroups.index(
'duration')] if 'duration' in listGroups else ''
scrapedgenre = match[listGroups.index(
'genre')] if 'genre' in listGroups else ''
scrapedrating = match[listGroups.index(
'rating')] if 'rating' in listGroups else ''
title = scrapertoolsV2.decodeHtmlentities(scrapedtitle)
plot = scrapertoolsV2.decodeHtmlentities(scrapedplot)
if scrapedquality:
longtitle = '[B]' + title + '[/B] [COLOR blue][' + scrapedquality + '][/COLOR]'
else:
longtitle = '[B]' + title + '[/B]'
if item.infoLabels[
"title"] or item.fulltitle: # if title is set, probably this is a list of episodes or video sources
infolabels = item.infoLabels
else:
infolabels = {}
if scrapedyear:
infolabels['year'] = scrapedyear
if scrapedplot:
infolabels['plot'] = plot
if scrapedduration:
matches = scrapertoolsV2.find_multiple_matches(
scrapedduration,
r'([0-9])\s*?(?:[hH]|:|\.|,|\\|\/|\||\s)\s*?([0-9]+)')
for h, m in matches:
scrapedduration = int(h) * 60 + int(m)
infolabels['duration'] = int(scrapedduration) * 60
if scrapedgenre:
genres = scrapertoolsV2.find_multiple_matches(
scrapedgenre, '[A-Za-z]+')
infolabels['genre'] = ", ".join(genres)
if scrapedrating:
infolabels['rating'] = scrapertoolsV2.decodeHtmlentities(
scrapedrating)
if not scrapedtitle in blacklist:
itemlist.append(
Item(channel=item.channel,
action=action,
contentType=item.contentType,
title=longtitle,
fulltitle=title,
show=title,
quality=scrapedquality,
url=scrapedurl,
infoLabels=infolabels,
thumbnail=scrapedthumb))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
if patronNext:
nextPage(itemlist, item, data, patronNext, 2)
if addVideolibrary and (item.infoLabels["title"] or item.fulltitle):
item.fulltitle = item.infoLabels["title"]
videolibrary(itemlist, item)
return itemlist
def scrapeBlock(item, args, block, patron, headers, action, pagination, debug,
typeContentDict, typeActionDict, blacklist, search, pag,
function, lang):
itemlist = []
log("scrapeBlock qui", block, patron)
matches = scrapertoolsV2.find_multiple_matches_groups(block, patron)
log('MATCHES =', matches)
if debug:
regexDbg(item, patron, headers, block)
known_keys = [
'url', 'title', 'title2', 'episode', 'thumb', 'quality', 'year',
'plot', 'duration', 'genere', 'rating', 'type', 'lang'
]
# lang = '' # aggiunto per gestire i siti con pagine di serietv dove si hanno i video in ita e in subita
for i, match in enumerate(matches):
if pagination and (pag - 1) * pagination > i: continue # pagination
if pagination and i >= pag * pagination: break # pagination
listGroups = match.keys()
match = match.values()
if len(listGroups) > len(match): # to fix a bug
match = list(match)
match.extend([''] * (len(listGroups) - len(match)))
scraped = {}
for kk in known_keys:
val = match[listGroups.index(kk)] if kk in listGroups else ''
if val and (kk == "url" or kk == 'thumb') and 'http' not in val:
val = scrapertoolsV2.find_single_match(
item.url, 'https?://[a-z0-9.-]+') + val
scraped[kk] = val
episode = re.sub(r'\s-\s|-|x|–|×', 'x',
scraped['episode']) if scraped['episode'] else ''
title = cleantitle(scraped['title']) if scraped['title'] else ''
title2 = cleantitle(scraped['title2']) if scraped['title2'] else ''
quality = scraped['quality'].strip() if scraped['quality'] else ''
Type = scraped['type'] if scraped['type'] else ''
plot = cleantitle(scraped["plot"]) if scraped["plot"] else ''
# make formatted Title [longtitle]
s = ' - '
title = episode + (s if episode and title else '') + title
longtitle = title + (s if title and title2 else '') + title2
longtitle = typo(longtitle, 'bold')
longtitle += (typo(Type, '_ () bold') if Type else '') + (typo(
quality, '_ [] color kod') if quality else '')
# # per togliere la voce [ITA] da liste che non siano titoli (es.: genere)
# if action != 'peliculas':
# lang, longtitle = scrapeLang(scraped, lang, longtitle)
# else:
# longtitle = longtitle.replace('[ITA]','')
# lang = ''
lang, longtitle = scrapeLang(scraped, lang, longtitle)
# if title is set, probably this is a list of episodes or video sources
# necessaria l'aggiunta di == scraped["title"] altrimenti non prende i gruppi dopo le categorie
if item.infoLabels["title"] == scraped["title"]:
infolabels = item.infoLabels
else:
infolabels = {}
if scraped['year']:
infolabels['year'] = scraped['year']
if scraped["plot"]:
infolabels['plot'] = plot
if scraped['duration']:
matches = scrapertoolsV2.find_multiple_matches(
scraped['duration'],
r'([0-9])\s*?(?:[hH]|:|\.|,|\\|\/|\||\s)\s*?([0-9]+)')
for h, m in matches:
scraped['duration'] = int(h) * 60 + int(m)
if not matches:
scraped['duration'] = scrapertoolsV2.find_single_match(
scraped['duration'], r'(\d+)')
infolabels['duration'] = int(scraped['duration']) * 60
if scraped['genere']:
genres = scrapertoolsV2.find_multiple_matches(
scraped['genere'], '[A-Za-z]+')
infolabels['genere'] = ", ".join(genres)
if scraped["rating"]:
infolabels['rating'] = scrapertoolsV2.decodeHtmlentities(
scraped["rating"])
AC = CT = ''
if typeContentDict:
for name, variants in typeContentDict.items():
if str(scraped['type']).lower() in variants:
CT = name
else:
CT = item.contentType
if typeActionDict:
for name, variants in typeActionDict.items():
if str(scraped['type']).lower() in variants:
AC = name
else:
AC = action
if (scraped["title"] not in blacklist) and (search.lower()
in longtitle.lower()):
it = Item(
channel=item.channel,
action=AC if AC else action,
contentType='episode'
if function == 'episodios' else CT if CT else item.contentType,
title=longtitle,
fulltitle=item.fulltitle if function == 'episodios' else title,
show=item.show if function == 'episodios' else title,
quality=quality,
url=scraped["url"],
infoLabels=infolabels,
thumbnail=item.thumbnail
if function == 'episodios' else scraped["thumb"],
args=item.args,
contentSerieName=title
if item.contentType != 'movie' and function != 'episodios' else
item.fulltitle if function == 'episodios' else '',
contentTitle=title if item.contentType == 'movie' else '',
contentLanguage=lang,
ep=episode if episode else '')
for lg in list(set(listGroups).difference(known_keys)):
it.__setattr__(lg, match[listGroups.index(lg)])
if 'itemHook' in args:
it = args['itemHook'](it)
itemlist.append(it)
return itemlist, matches
def scrape(item,
patron='',
listGroups=[],
headers="",
blacklist="",
data="",
patron_block="",
patronNext="",
action="findvideos",
addVideolibrary=True,
type_content_dict={},
type_action_dict={}):
# patron: the patron to use for scraping page, all capturing group must match with listGroups
# listGroups: a list containing the scraping info obtained by your patron, in order
# accepted values are: url, title, thumb, quality, year, plot, duration, genre, rating, episode, lang
# header: values to pass to request header
# blacklist: titles that you want to exclude(service articles for example)
# data: if you want to pass data manually, maybe because you need some custom replacement
# patron_block: patron to get parts of the page (to scrape with patron attribute),
# if you need a "block inside another block" you can create a list, please note that all matches
# will be packed as string
# patronNext: patron for scraping next page link
# action: if you want results perform an action different from "findvideos", useful when scraping film by genres
# url_host: string to prepend to scrapedurl, useful when url don't contain host
# example usage:
# import support
# itemlist = []
# patron = 'blablabla'
# headers = [['Referer', host]]
# blacklist = 'Request a TV serie!'
# return support.scrape(item, itemlist, patron, ['thumb', 'quality', 'url', 'title', 'title2', 'year', 'plot', 'episode', 'lang'],
# headers=headers, blacklist=blacklist)
# listGroups
# thumb = immagine, quality = qualità, url = link singolo o gruppo, title = titolo film o serie, title2 = titolo aggiuntivo
# year = anno del film o della serie, plot = descrizione film o serie, episode = numero stagione - numero episodio in caso di serie,
# lang = lingua del video
# 'type' is a check for typologies of content e.g. Film or TV Series
# 'episode' is a key to grab episode numbers if it is separated from the title
# IMPORTANT 'type' is a special key, to work need type_content_dict={} and type_action_dict={}
itemlist = []
if not data:
data = httptools.downloadpage(item.url,
headers=headers,
ignore_response_code=True).data.replace(
"'", '"')
data = re.sub('\n|\t', ' ', data)
# replace all ' with " and eliminate newline, so we don't need to worry about
log('DATA =', data)
block = data
if patron_block:
if type(patron_block) == str:
patron_block = [patron_block]
for n, regex in enumerate(patron_block):
blocks = scrapertoolsV2.find_multiple_matches(block, regex)
block = ""
for b in blocks:
block += "\n" + str(b)
log('BLOCK ', n, '=', block)
else:
block = data
if patron and listGroups:
matches = scrapertoolsV2.find_multiple_matches(block, patron)
log('MATCHES =', matches)
known_keys = [
'url', 'title', 'title2', 'episode', 'thumb', 'quality', 'year',
'plot', 'duration', 'genere', 'rating', 'type', 'lang'
] #by greko aggiunto episode
lang = '' # aggiunto per gestire i siti con pagine di serietv dove si hanno i video in ita e in subita
for match in matches:
if len(listGroups) > len(match): # to fix a bug
match = list(match)
match.extend([''] * (len(listGroups) - len(match)))
scraped = {}
for kk in known_keys:
val = match[listGroups.index(kk)] if kk in listGroups else ''
if val and (kk == "url"
or kk == 'thumb') and 'http' not in val:
val = scrapertoolsV2.find_single_match(
item.url, 'https?://[a-z0-9.-]+') + val
scraped[kk] = val
title = scrapertoolsV2.htmlclean(
scrapertoolsV2.decodeHtmlentities(scraped["title"])).replace(
'’', '\'').replace('"',
"'").strip() # fix by greko da " a '
plot = scrapertoolsV2.htmlclean(
scrapertoolsV2.decodeHtmlentities(scraped["plot"]))
longtitle = typo(title, 'bold')
if scraped['quality']:
longtitle = longtitle + typo(scraped['quality'],
'_ [] color kod')
if scraped['episode']:
scraped['episode'] = re.sub(r'\s-\s|-|x|–', 'x',
scraped['episode'])
longtitle = typo(scraped['episode'] + ' - ',
'bold') + longtitle
if scraped['title2']:
title2 = scrapertoolsV2.htmlclean(
scrapertoolsV2.decodeHtmlentities(
scraped["title2"])).replace('"', "'").strip()
longtitle = longtitle + typo(title2, 'bold _ -- _')
## Aggiunto/modificato per gestire i siti che hanno i video
## in ita e subita delle serie tv nella stessa pagina
if scraped['lang']:
if 'sub' in scraped['lang'].lower():
lang = 'Sub-ITA'
else:
lang = 'ITA'
if lang != '':
longtitle += typo(lang, '_ [] color kod')
if item.infoLabels[
"title"] or item.fulltitle: # if title is set, probably this is a list of episodes or video sources
infolabels = item.infoLabels
else:
infolabels = {}
if scraped["year"]:
infolabels['year'] = scraped["year"]
if scraped["plot"]:
infolabels['plot'] = plot
if scraped["duration"]:
matches = scrapertoolsV2.find_multiple_matches(
scraped["duration"],
r'([0-9])\s*?(?:[hH]|:|\.|,|\\|\/|\||\s)\s*?([0-9]+)')
for h, m in matches:
scraped["duration"] = int(h) * 60 + int(m)
if not matches:
scraped["duration"] = scrapertoolsV2.find_single_match(
scraped["duration"], r'(\d+)')
infolabels['duration'] = int(scraped["duration"]) * 60
if scraped["genere"]:
genres = scrapertoolsV2.find_multiple_matches(
scraped["genere"], '[A-Za-z]+')
infolabels['genere'] = ", ".join(genres)
if scraped["rating"]:
infolabels['rating'] = scrapertoolsV2.decodeHtmlentities(
scraped["rating"])
if type_content_dict:
for name, variants in type_content_dict.items():
if scraped['type'] in variants:
item.contentType = name
if type_action_dict:
for name, variants in type_action_dict.items():
if scraped['type'] in variants:
action = name
if inspect.stack()[1][3] == 'episodios':
item.contentType = 'episode'
if scraped["title"] not in blacklist:
it = Item(channel=item.channel,
action=action,
contentType=item.contentType,
title=longtitle,
fulltitle=title,
show=title,
language=lang if lang != '' else '',
quality=scraped["quality"],
url=scraped["url"],
infoLabels=infolabels,
thumbnail=scraped["thumb"],
args=item.args)
for lg in list(set(listGroups).difference(known_keys)):
it.__setattr__(lg, match[listGroups.index(lg)])
itemlist.append(it)
checkHost(item, itemlist)
if (item.contentType == "tvshow" and (action != "findvideos" and action != "play")) \
or (item.contentType == "episode" and action != "play") \
or (item.contentType == "movie" and action != "play"):
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
else:
for it in itemlist:
it.infoLabels = item.infoLabels
if patronNext:
nextPage(itemlist, item, data, patronNext, 2)
if addVideolibrary and (item.infoLabels["title"] or item.fulltitle):
item.fulltitle = item.infoLabels["title"]
videolibrary(itemlist, item)
return itemlist
def scrapeBlock(item, args, block, patron, headers, action, pagination, debug,
typeContentDict, typeActionDict, blacklist, search, pag,
function, lang):
itemlist = []
log("scrapeBlock qui", block, patron)
matches = scrapertoolsV2.find_multiple_matches_groups(block, patron)
log('MATCHES =', matches)
if debug:
regexDbg(item, patron, headers, block)
known_keys = [
'url', 'title', 'title2', 'season', 'episode', 'thumb', 'quality',
'year', 'plot', 'duration', 'genere', 'rating', 'type', 'lang'
]
# Legenda known_keys per i groups nei patron
# known_keys = ['url', 'title', 'title2', 'season', 'episode', 'thumb', 'quality',
# 'year', 'plot', 'duration', 'genere', 'rating', 'type', 'lang']
# url = link relativo o assoluto alla pagina titolo film/serie
# title = titolo Film/Serie/Anime/Altro
# title2 = titolo dell'episodio Serie/Anime/Altro
# season = stagione in formato numerico
# episode = numero episodio, in formato numerico.
# thumb = linkrealtivo o assoluto alla locandina Film/Serie/Anime/Altro
# quality = qualità indicata del video
# year = anno in formato numerico (4 cifre)
# duration = durata del Film/Serie/Anime/Altro
# genere = genere del Film/Serie/Anime/Altro. Es: avventura, commedia
# rating = punteggio/voto in formato numerico
# type = tipo del video. Es. movie per film o tvshow per le serie. Di solito sono discrimanti usati dal sito
# lang = lingua del video. Es: ITA, Sub-ITA, Sub, SUB ITA.
# AVVERTENZE: Se il titolo è trovato nella ricerca TMDB/TVDB/Altro allora le locandine e altre info non saranno quelle recuperate nel sito.!!!!
stagione = '' # per quei siti che hanno la stagione nel blocco ma non nelle puntate
for i, match in enumerate(matches):
if pagination and (pag - 1) * pagination > i: continue # pagination
if pagination and i >= pag * pagination: break # pagination
listGroups = match.keys()
match = match.values()
if len(listGroups) > len(match): # to fix a bug
match = list(match)
match.extend([''] * (len(listGroups) - len(match)))
scraped = {}
for kk in known_keys:
val = match[listGroups.index(kk)] if kk in listGroups else ''
if val and (kk == "url" or kk == 'thumb') and 'http' not in val:
val = scrapertoolsV2.find_single_match(
item.url, 'https?://[a-z0-9.-]+') + val
scraped[kk] = val
if scraped['season'] != None:
season = scraped['season']
if stagione:
episode = season + 'x' + scraped['episode']
elif item.contentType == 'tvshow' and (scraped['episode'] == ''
and season == ''):
item.args = 'season_completed'
episode = ''
else:
episode = re.sub(r'\s-\s|-|x|–|×', 'x',
scraped['episode']) if scraped['episode'] else ''
#episode = re.sub(r'\s-\s|-|x|–|×', 'x', scraped['episode']) if scraped['episode'] else ''
title = cleantitle(scraped['title']) if scraped['title'] else ''
title2 = cleantitle(scraped['title2']) if scraped['title2'] else ''
quality = scraped['quality'].strip() if scraped['quality'] else ''
Type = scraped['type'] if scraped['type'] else ''
plot = cleantitle(scraped["plot"]) if scraped["plot"] else ''
# make formatted Title [longtitle]
s = ' - '
title = episode + (s if episode and title else '') + title
longtitle = title + (s if title and title2 else '') + title2
longtitle = typo(longtitle, 'bold')
longtitle += (typo(Type, '_ () bold') if Type else '') + (typo(
quality, '_ [] color kod') if quality else '')
lang1, longtitle = scrapeLang(scraped, lang, longtitle)
# if title is set, probably this is a list of episodes or video sources
# necessaria l'aggiunta di == scraped["title"] altrimenti non prende i gruppi dopo le categorie
if item.infoLabels["title"] == scraped["title"]:
infolabels = item.infoLabels
else:
infolabels = {}
if scraped['year']:
infolabels['year'] = scraped['year']
if scraped["plot"]:
infolabels['plot'] = plot
if scraped['duration']:
matches = scrapertoolsV2.find_multiple_matches(
scraped['duration'],
r'([0-9])\s*?(?:[hH]|:|\.|,|\\|\/|\||\s)\s*?([0-9]+)')
for h, m in matches:
scraped['duration'] = int(h) * 60 + int(m)
if not matches:
scraped['duration'] = scrapertoolsV2.find_single_match(
scraped['duration'], r'(\d+)')
infolabels['duration'] = int(scraped['duration']) * 60
if scraped['genere']:
genres = scrapertoolsV2.find_multiple_matches(
scraped['genere'], '[A-Za-z]+')
infolabels['genere'] = ", ".join(genres)
if scraped["rating"]:
infolabels['rating'] = scrapertoolsV2.decodeHtmlentities(
scraped["rating"])
AC = CT = ''
if typeContentDict:
for name, variants in typeContentDict.items():
if str(scraped['type']).lower() in variants:
CT = name
break
else:
CT = item.contentType
if typeActionDict:
for name, variants in typeActionDict.items():
if str(scraped['type']).lower() in variants:
AC = name
break
else:
AC = action
if (scraped["title"] not in blacklist) and (search.lower()
in longtitle.lower()):
it = Item(
channel=item.channel,
action=AC if AC else action,
contentType='episode'
if function == 'episodios' else CT if CT else item.contentType,
title=longtitle,
fulltitle=item.fulltitle if function == 'episodios' else title,
show=item.show if function == 'episodios' else title,
quality=quality,
url=scraped["url"],
infoLabels=infolabels,
thumbnail=item.thumbnail
if function == 'episodios' else scraped["thumb"],
args=item.args,
contentSerieName=scraped['title'] if item.contentType
or CT != 'movie' and function != 'episodios' else
item.fulltitle if function == 'episodios' else '',
contentTitle=scraped['title']
if item.contentType or CT == 'movie' else '',
contentLanguage=lang1,
contentEpisodeNumber=episode if episode else '')
for lg in list(set(listGroups).difference(known_keys)):
it.__setattr__(lg, match[listGroups.index(lg)])
if 'itemHook' in args:
it = args['itemHook'](it)
itemlist.append(it)
return itemlist, matches
