stevazi/addon
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 3 Wiki Activity

Improvements channel Guardaserie.click, Fastsubita and support (#41)

Browse Source
This commit is contained in:
4l3x87
2019-05-31 20:56:36 +02:00
committed by mac12m99
parent c95617f707
commit a7effd0d7d
3 changed files with 117 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files
channels/fastsubita.py
+52 -143
View File
@@ -4,13 +4,10 @@
# Canale per fastsubita # Canale per fastsubita
# ------------------------------------------------------------ # ------------------------------------------------------------
import re
import channelselector
from core import scrapertools, httptools, tmdb, support from core import scrapertools, httptools, tmdb, support
from core.item import Item from core.item import Item
from core.support import log
from platformcode import config, logger from platformcode import config, logger
from specials import autoplay
__channel__ = 'fastsubita' __channel__ = 'fastsubita'
host = config.get_setting("channel_host", __channel__) host = config.get_setting("channel_host", __channel__)
@@ -19,9 +16,6 @@ list_language = IDIOMAS.values()
list_servers = ['verystream', 'openload', 'speedvideo', 'wstream', 'flashx', 'vidoza', 'vidtome'] list_servers = ['verystream', 'openload', 'speedvideo', 'wstream', 'flashx', 'vidoza', 'vidtome']
list_quality = ['default'] list_quality = ['default']
# checklinks = config.get_setting('checklinks', 'fastsubita')
# checklinks_number = config.get_setting('checklinks_number', 'fastsubita')
headers = [ headers = [
['Host', 'fastsubita.com'], ['Host', 'fastsubita.com'],
['User-Agent', 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0'], ['User-Agent', 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:60.0) Gecko/20100101 Firefox/60.0'],
@@ -39,32 +33,23 @@ PERPAGE = 15
def mainlist(item): def mainlist(item):
logger.info(item.channel+" mainlist") log()
itemlist = [] itemlist = []
support.menu(itemlist, 'Serie TV bold', 'lista_serie', host,'tvshow') support.menu(itemlist, 'Novità bold', 'pelicuals_tv', host, 'tvshow')
support.menu(itemlist, 'Novità submenu', 'pelicuals_tv', host,'tvshow') support.menu(itemlist, 'Serie TV bold', 'lista_serie', host, 'tvshow')
support.menu(itemlist, 'Archivio A-Z submenu', 'list_az', host,'tvshow',args=['serie']) support.menu(itemlist, 'Archivio A-Z submenu', 'list_az', host, 'tvshow', args=['serie'])
support.menu(itemlist, 'Cerca', 'search', host,'tvshow') support.menu(itemlist, 'Cerca', 'search', host, 'tvshow')
support.aplay(item, itemlist, list_servers, list_quality)
autoplay.init(item.channel, list_servers, list_quality) support.channel_config(item, itemlist)
autoplay.show_option(item.channel, itemlist)
itemlist.append(
Item(channel='setting',
action="channel_config",
title=support.typo("Configurazione Canale color lime"),
config=item.channel,
folder=False,
thumbnail=channelselector.get_thumb('setting_0.png'))
)
return itemlist return itemlist
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def cleantitle(scrapedtitle): def cleantitle(scrapedtitle):
scrapedtitle = scrapertools.decodeHtmlentities(scrapedtitle.strip()) scrapedtitle = scrapertools.decodeHtmlentities(scrapedtitle.strip())
scrapedtitle = scrapedtitle.replace('’', '\'').replace('×','x').replace('×','x') scrapedtitle = scrapedtitle.replace('’', '\'').replace('×', 'x').replace('×', 'x').replace('"', "'")
return scrapedtitle.strip() return scrapedtitle.strip()
@@ -73,7 +58,7 @@ def cleantitle(scrapedtitle):
def newest(categoria): def newest(categoria):
logger.info(__channel__+" newest" + categoria) log()
itemlist = [] itemlist = []
item = Item() item = Item()
try: try:
@@ -96,15 +81,11 @@ def newest(categoria):
def pelicuals_tv(item): def pelicuals_tv(item):
logger.info(item.channel+" pelicuals_tv") log()
itemlist = [] itemlist = []
# Carica la pagina matches, data = support.match(item, r'<h3 class="entry-title title-font"><a href="([^"]+)" rel="bookmark">(.*?)<',
data = httptools.downloadpage(item.url, headers=headers).data headers=headers)
# Estrae i contenuti
patron = r'<h3 class="entry-title title-font"><a href="([^"]+)" rel="bookmark">(.*?)<'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedurl, scrapedtitle in matches: for scrapedurl, scrapedtitle in matches:
scrapedplot = "" scrapedplot = ""
@@ -123,7 +104,7 @@ def pelicuals_tv(item):
else: else:
scrapedurl = "http:" + scrapedurl scrapedurl = "http:" + scrapedurl
title = scraped_1+" - "+infoLabels['season']+"x"+infoLabels['episode']+" Sub-ITA" title = scraped_1 + " - " + infoLabels['season'] + "x" + infoLabels['episode'] + " Sub-ITA"
itemlist.append( itemlist.append(
Item(channel=item.channel, Item(channel=item.channel,
@@ -144,35 +125,20 @@ def pelicuals_tv(item):
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True) tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
# Paginazione # Paginazione
support.nextPage(itemlist,item,data,'<a class="next page-numbers" href="(.*?)">Successivi') support.nextPage(itemlist, item, data, '<a class="next page-numbers" href="(.*?)">Successivi')
return itemlist return itemlist
def serietv(): def serietv():
logger.info(__channel__+" serietv") log()
itemlist = [] itemlist = []
data = httptools.downloadpage("%s/" % host, headers=headers).data matches = support.match(Item(), r'<option class="level-([0-9]?)" value="([^"]+)">([^<]+)</option>',
# block = scrapertools.find_single_match(data, r'<div class="entry-content">(.*?)</div>') r'<select\s*?name="cat"\s*?id="cat"\s*?class="postform"\s*?>(.*?)</select>', headers,
block = scrapertools.find_single_match(data, r"<select\s*?name='cat'\s*?id='cat'\s*?class='postform'\s*?>(.*?)</select>") url="%s/" % host)[0]
# block = data
# Estrae i contenuti
# patron = r'<a style.*?href="([^"]+)">([^<]+)<\/a>'
# patron = r'<a.*?href="([^"]+)">([^<]+)<\/a>'
# matches = re.compile(patron, re.DOTALL).findall(block)
matches = re.compile(r'<option class="level-([0-9]?)" value="([^"]+)">([^<]+)</option>', re.DOTALL).findall(block)
index = 0 index = 0
# for scrapedurl, scrapedtitle in matches:
# scrapedtitle = cleantitle(scrapedtitle)
# if "http:" not in scrapedurl:
# scrapedurl = "http:" + scrapedurl
#
# if ('S' in scrapedtitle.strip().upper()[0] and len(scrapedtitle.strip()) == 3) or '02' == scrapedtitle:
# # itemlist[index -1][0]+='{|}'+scrapedurl
# continue
#
# itemlist.append([scrapedurl,scrapedtitle])
# index += 1
for level, cat, title in matches: for level, cat, title in matches:
title = cleantitle(title) title = cleantitle(title)
url = '%s?cat=%s' % (host, cat) url = '%s?cat=%s' % (host, cat)
@@ -183,12 +149,11 @@ def serietv():
itemlist.append([url, title]) itemlist.append([url, title])
index += 1 index += 1
logger.debug(itemlist)
return itemlist return itemlist
def lista_serie(item): def lista_serie(item):
logger.info(item.channel+" lista_serie") log()
itemlist = [] itemlist = []
p = 1 p = 1
@@ -196,16 +161,6 @@ def lista_serie(item):
item.url, p = item.url.split('{}') item.url, p = item.url.split('{}')
p = int(p) p = int(p)
# logger.debug(p)
# Carica la pagina
# data = httptools.downloadpage(item.url, headers=headers).data
#
# block = scrapertools.find_single_match(data,r'<div class="entry-content">(.*?)</div>')
#
# # Estrae i contenuti
# # patron = r'<a style.*?href="([^"]+)">([^<]+)<\/a>'
# patron = r'<a.*?href="([^"]+)">([^<]+)<\/a>'
# matches = re.compile(patron, re.DOTALL).findall(block)
if '||' in item.url: if '||' in item.url:
series = item.url.split('\n\n') series = item.url.split('\n\n')
matches = [] matches = []
@@ -235,76 +190,41 @@ def lista_serie(item):
contentType='episode', contentType='episode',
originalUrl=scrapedurl, originalUrl=scrapedurl,
folder=True)) folder=True))
# ii += 1
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True) tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
if len(series) >= p * PERPAGE: if len(series) >= p * PERPAGE:
scrapedurl = item.url + '{}' + str(p + 1) next_page = item.url + '{}' + str(p + 1)
itemlist.append( support.nextPage(itemlist, item, next_page=next_page)
Item(channel=item.channel,
action='lista_serie',
contentType=item.contentType,
title=support.typo(config.get_localized_string(30992), 'color kod bold'),
url=scrapedurl,
args=item.args,
extra=item.extra,
thumbnail=support.thumb()))
return itemlist return itemlist
def findvideos(item): def findvideos(item):
logger.info(item.channel+" findvideos") log()
itemlist = [] itemlist = []
data = httptools.downloadpage(item.url, headers=headers).data # data = httptools.downloadpage(item.url, headers=headers).data
bloque = scrapertools.find_single_match(data, '<div class="entry-content">(.*?)<footer class="entry-footer">') patron_block = '<div class="entry-content">(.*?)<footer class="entry-footer">'
# bloque = scrapertools.find_single_match(data, patron_block)
patron = r'<a href="([^"]+)">' patron = r'<a href="([^"]+)">'
matches = re.compile(patron, re.DOTALL).findall(bloque) # matches = re.compile(patron, re.DOTALL).findall(bloque)
matches, data = support.match(item, patron, patron_block, headers)
for scrapedurl in matches: for scrapedurl in matches:
if 'is.gd' in scrapedurl: if 'is.gd' in scrapedurl:
resp = httptools.downloadpage( resp = httptools.downloadpage(
scrapedurl, follow_redirects=False) scrapedurl, follow_redirects=False)
data += resp.headers.get("location", "") + '\n' data += resp.headers.get("location", "") + '\n'
return support.server(item, data)
itemlist = support.server(item,data)
# itemlist = servertools.find_video_items(data=data)
#
# for videoitem in itemlist:
# videoitem.title = item.title + videoitem.title
# videoitem.fulltitle = item.fulltitle
# videoitem.thumbnail = item.thumbnail
# videoitem.show = item.show
# videoitem.plot = item.plot
# videoitem.channel = item.channel
# videoitem.contentType = item.contentType
# videoitem.language = IDIOMAS['Italiano']
#
# # Requerido para Filtrar enlaces
#
# if checklinks:
# itemlist = servertools.check_list_links(itemlist, checklinks_number)
#
# # Requerido para FilterTools
#
# # itemlist = filtertools.get_links(itemlist, item, list_language)
#
# # Requerido para AutoPlay
#
# autoplay.start(itemlist, item)
return itemlist
def search(item, texto): def search(item, texto):
logger.info(item.channel + " " + item.url + " search " + texto) log(texto)
# item.url = "%s/?s=%s" % (host, texto)
# item.url = "%s/elenco-serie-tv/" % host
itemlist = [] itemlist = []
try: try:
series = serietv() series = serietv()
@@ -333,15 +253,15 @@ def search(item, texto):
logger.error("%s" % line) logger.error("%s" % line)
return [] return []
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def list_az(item): def list_az(item):
support.log(item.channel + " list_az") log()
itemlist = [] itemlist = []
alphabet = dict() alphabet = dict()
for i, (scrapedurl, scrapedtitle) in enumerate(serietv()): for i, (scrapedurl, scrapedtitle) in enumerate(serietv()):
letter = scrapedtitle[0].upper() letter = scrapedtitle[0].upper()
if letter not in alphabet: if letter not in alphabet:
@@ -358,37 +278,29 @@ def list_az(item):
return itemlist return itemlist
# ================================================================================================================ # ================================================================================================================
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def episodios(item,itemlist = []): def episodios(item, itemlist=[]):
support.log(item.channel + " episodios") log()
urls = item.url.split('{|}') urls = item.url.split('{|}')
# logger.debug(urls)
# Carica la pagina
data = httptools.downloadpage(urls[0], headers=headers).data
urls.pop(0)
# Estrae i contenuti
patron = r'<h3 class="entry-title title-font"><a href="([^"]+)" rel="bookmark">(.*?)<' patron = r'<h3 class="entry-title title-font"><a href="([^"]+)" rel="bookmark">(.*?)<'
matches = re.compile(patron, re.DOTALL).findall(data) matches, data = support.match(item, patron, headers=headers, url=urls[0])
urls.pop(0)
# logger.debug(matches)
for scrapedurl, scrapedtitle in matches: for scrapedurl, scrapedtitle in matches:
scrapedplot = "" scrapedplot = ""
scrapedthumbnail = "" scrapedthumbnail = ""
scrapedtitle = cleantitle(scrapedtitle) scrapedtitle = cleantitle(scrapedtitle)
episode = scrapertools.find_multiple_matches(scrapedtitle,r'((\d*)x(\d*))')[0] episode = scrapertools.find_multiple_matches(scrapedtitle, r'((\d*)x(\d*))')[0]
season = episode[1].lstrip('0') season = episode[1].lstrip('0').zfill(2)
# if season in seasons and '/page/' not in item.url: break
# logger.debug(scrapedtitle)
# logger.debug(episode)
# return False
infoLabels = {} infoLabels = {}
infoLabels['season'] = season infoLabels['season'] = season
infoLabels['episode'] = episode[2] infoLabels['episode'] = episode[2]
title = infoLabels['season']+'x'+infoLabels['episode']+" Sub-ITA" title = infoLabels['season'] + 'x' + infoLabels['episode'] + " Sub-ITA"
if "http:" not in scrapedurl: if "http:" not in scrapedurl:
scrapedurl = "http:" + scrapedurl scrapedurl = "http:" + scrapedurl
@@ -407,14 +319,11 @@ def episodios(item,itemlist = []):
infoLabels=infoLabels, infoLabels=infoLabels,
folder=True)) folder=True))
next_page = scrapertools.find_single_match(data, r'<a class="next page-numbers" href="(.*?)">Successivi')
next_page = scrapertools.find_single_match(data,r'<a class="next page-numbers" href="(.*?)">Successivi')
if next_page != "": if next_page != "":
urls.insert(0,next_page) urls.insert(0, next_page)
# logger.debug(urls) if len(urls) > 0:
if(len(urls) > 0):
item.url = '{|}'.join(urls) item.url = '{|}'.join(urls)
itemlist = episodios(item, itemlist) itemlist = episodios(item, itemlist)
else: else:
channels/guardaserieclick.py
+61 -103
View File
@@ -10,6 +10,7 @@ import channelselector
from core import httptools, scrapertools, servertools, support from core import httptools, scrapertools, servertools, support
from core import tmdb from core import tmdb
from core.item import Item from core.item import Item
from core.support import log
from platformcode import logger, config from platformcode import logger, config
from specials import autoplay from specials import autoplay
@@ -19,7 +20,7 @@ headers = [['Referer', host]]
IDIOMAS = {'Italiano': 'IT'} IDIOMAS = {'Italiano': 'IT'}
list_language = IDIOMAS.values() list_language = IDIOMAS.values()
list_servers = ['speedvideo','openload'] list_servers = ['speedvideo', 'openload']
list_quality = ['default'] list_quality = ['default']
headers = [['Referer', host]] headers = [['Referer', host]]
@@ -27,30 +28,20 @@ headers = [['Referer', host]]
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def mainlist(item): def mainlist(item):
support.log(item.channel+" mainlist") log()
itemlist = [] itemlist = []
# support.menu(itemlist, 'Serie TV bold')
support.menu(itemlist, 'Novità bold', 'serietvaggiornate', "%s/lista-serie-tv" % host,'tvshow')
support.menu(itemlist, 'Nuove serie', 'nuoveserie', "%s/lista-serie-tv" % host,'tvshow')
support.menu(itemlist, 'Serie inedite Sub-ITA', 'nuoveserie', "%s/lista-serie-tv" % host,'tvshow',args=['inedite'])
support.menu(itemlist, 'Da non perdere bold', 'nuoveserie', "%s/lista-serie-tv" % host,'tvshow',args=['tv','da non perdere'])
support.menu(itemlist, 'Classiche bold', 'nuoveserie', "%s/lista-serie-tv" % host,'tvshow',args=['tv','classiche'])
support.menu(itemlist, 'Anime', 'lista_serie', "%s/category/animazione/" % host,'tvshow')
support.menu(itemlist, 'Categorie', 'categorie', host,'tvshow',args=['serie'])
support.menu(itemlist, 'Cerca', 'search', host,'tvshow',args=['serie'])
autoplay.init(item.channel, list_servers, list_quality) support.menu(itemlist, 'Novità bold', 'serietvaggiornate', "%s/lista-serie-tv" % host, 'tvshow')
autoplay.show_option(item.channel, itemlist) support.menu(itemlist, 'Nuove serie', 'nuoveserie', "%s/lista-serie-tv" % host, 'tvshow')
support.menu(itemlist, 'Serie inedite Sub-ITA', 'nuoveserie', "%s/lista-serie-tv" % host, 'tvshow', args=['inedite'])
itemlist.append( support.menu(itemlist, 'Da non perdere bold', 'nuoveserie', "%s/lista-serie-tv" % host, 'tvshow', args=['tv', 'da non perdere'])
Item(channel='setting', support.menu(itemlist, 'Classiche bold', 'nuoveserie', "%s/lista-serie-tv" % host, 'tvshow', args=['tv', 'classiche'])
action="channel_config", support.menu(itemlist, 'Anime', 'lista_serie', "%s/category/animazione/" % host, 'tvshow')
title=support.typo("Configurazione Canale color lime"), support.menu(itemlist, 'Categorie', 'categorie', host, 'tvshow', args=['serie'])
config=item.channel, support.menu(itemlist, 'Cerca', 'search', host, 'tvshow', args=['serie'])
folder=False, support.aplay(item, itemlist, list_servers, list_quality)
thumbnail=channelselector.get_thumb('setting_0.png')) support.channel_config(item, itemlist)
)
return itemlist return itemlist
@@ -59,7 +50,7 @@ def mainlist(item):
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def newest(categoria): def newest(categoria):
support.log(__channel__+" newest" + categoria) log()
itemlist = [] itemlist = []
item = Item() item = Item()
try: try:
@@ -85,7 +76,7 @@ def newest(categoria):
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def search(item, texto): def search(item, texto):
support.log(item.channel+" search") log(texto)
item.url = host + "/?s=" + texto item.url = host + "/?s=" + texto
try: try:
return lista_serie(item) return lista_serie(item)
@@ -100,28 +91,27 @@ def search(item, texto):
# ================================================================================================================ # ================================================================================================================
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def cleantitle(scrapedtitle): def cleantitle(scrapedtitle):
scrapedtitle = scrapertools.decodeHtmlentities(scrapedtitle.strip()).replace('"',"'") scrapedtitle = scrapertools.decodeHtmlentities(scrapedtitle.strip()).replace('"', "'")
return scrapedtitle.strip() return scrapedtitle.strip()
# ================================================================================================================ # ================================================================================================================
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def nuoveserie(item): def nuoveserie(item):
support.log(item.channel+" nuoveserie") log()
itemlist = [] itemlist = []
patron_block = '' patron_block = ''
if 'inedite' in item.args: if 'inedite' in item.args:
patron_block = r'<div\s*class="container container-title-serie-ined container-scheda" meta-slug="ined">(.*?)</div></div><div' patron_block = r'<div\sclass="container container-title-serie-ined container-scheda" meta-slug="ined">(.*?)</div></div><div'
elif 'da non perder' in item.args: elif 'da non perdere' in item.args:
patron_block = r'<div\s*class="container container-title-serie-danonperd container-scheda" meta-slug="danonperd">(.*?)</div></div><div' patron_block = r'<div\sclass="container container-title-serie-danonperd container-scheda" meta-slug="danonperd">(.*?)</div></div><div'
elif 'classiche' in item.args: elif 'classiche' in item.args:
patron_block = r'<div\s*class="container container-title-serie-classiche container-scheda" meta-slug="classiche">(.*?)</div></div><div' patron_block = r'<div\sclass="container container-title-serie-classiche container-scheda" meta-slug="classiche">(.*?)</div></div><div'
else: else:
patron_block = r'<div\s*class="container container-title-serie-new container-scheda" meta-slug="new">(.*?)</div></div><div' patron_block = r'<div\sclass="container container-title-serie-new container-scheda" meta-slug="new">(.*?)</div></div><div'
patron = r'<a\s*href="([^"]+)".*?>\s*<img\s*.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>' patron = r'<a\shref="([^"]+)".*?>\s<img\s.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>'
patron += r'[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p>' patron += r'[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p>'
matches = support.match(item, patron, patron_block, headers)[0] matches = support.match(item, patron, patron_block, headers)[0]
@@ -148,14 +138,14 @@ def nuoveserie(item):
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def serietvaggiornate(item): def serietvaggiornate(item):
support.log(item.channel+" serietvaggiornate") log()
itemlist = [] itemlist = []
patron_block = r'<div\s*class="container container-title-serie-lastep container-scheda" meta-slug="lastep">(.*?)</div></div><div' patron_block = r'<div\sclass="container container-title-serie-lastep container-scheda" meta-slug="lastep">(.*?)</div></div><div'
patron = r'<a\s*rel="nofollow" href="([^"]+)"[^>]+> <img\s*.*?src="([^"]+)"[^>]+>[^>]+>' patron = r'<a\srel="nofollow" href="([^"]+)"[^>]+> <img\s*.*?src="([^"]+)"[^>]+>[^>]+>'
patron += r'[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>' patron += r'[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>'
matches = support.match(item,patron, patron_block, headers)[0] matches = support.match(item, patron, patron_block, headers)[0]
for scrapedurl, scrapedthumbnail, scrapedep, scrapedtitle in matches: for scrapedurl, scrapedthumbnail, scrapedep, scrapedtitle in matches:
episode = re.compile(r'^(\d+)x(\d+)', re.DOTALL).findall(scrapedep) # Prendo stagione ed episodioso episode = re.compile(r'^(\d+)x(\d+)', re.DOTALL).findall(scrapedep) # Prendo stagione ed episodioso
@@ -165,14 +155,15 @@ def serietvaggiornate(item):
if 'sub-ita' in scrapedep.strip().lower(): if 'sub-ita' in scrapedep.strip().lower():
contentlanguage = 'Sub-ITA' contentlanguage = 'Sub-ITA'
extra = r'<span\s*.*?meta-stag="%s" meta-ep="%s" meta-embed="([^"]+)"\s*.*?embed2="([^"]+)?"\s*.*?embed3="([^"]+)?"[^>]*>' % ( extra = r'<span\s.*?meta-stag="%s" meta-ep="%s" meta-embed="([^"]+)"\s.*?embed2="([^"]+)?"\s.*?embed3="([^"]+)?"[^>]*>' % (
episode[0][0], episode[0][1].lstrip("0")) episode[0][0], episode[0][1].lstrip("0"))
infoLabels = {} infoLabels = {}
infoLabels['episode'] = episode[0][1].lstrip("0") infoLabels['episode'] = episode[0][1].zfill(2)
infoLabels['season'] = episode[0][0] infoLabels['season'] = episode[0][0]
title = str("%s - %sx%s %s" % (scrapedtitle,infoLabels['season'],infoLabels['episode'],contentlanguage)).strip() title = str(
"%s - %sx%s %s" % (scrapedtitle, infoLabels['season'], infoLabels['episode'], contentlanguage)).strip()
itemlist.append( itemlist.append(
Item(channel=item.channel, Item(channel=item.channel,
@@ -197,49 +188,26 @@ def serietvaggiornate(item):
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def categorie(item): def categorie(item):
support.log(item.channel+" categorie") log()
itemlist = [] return support.scrape(item, r'<li>\s<a\shref="([^"]+)"[^>]+>([^<]+)</a></li>', ['url', 'title'], patron_block=r'<ul\sclass="dropdown-menu category">(.*?)</ul>', headers=headers, action="lista_serie")
matches = support.match(item, r'<li>\s*<a\s*href="([^"]+)"[^>]+>([^<]+)</a></li>', r'<ul\s*class="dropdown-menu category">(.*?)</ul>', headers)[0]
for scrapedurl, scrapedtitle in matches:
itemlist.append(
Item(channel=item.channel,
action="lista_serie",
title=scrapedtitle,
contentType="tvshow",
url="".join([host, scrapedurl]),
thumbnail=item.thumbnail,
extra="tv",
folder=True))
return itemlist
# ================================================================================================================ # ================================================================================================================
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def lista_serie(item): def lista_serie(item):
support.log(item.channel+" lista_serie") log()
itemlist = [] itemlist = []
# data = httptools.downloadpage(item.url, headers=headers).data patron_block = r'<div\sclass="col-xs-\d+ col-sm-\d+-\d+">(.*?)<div\sclass="container-fluid whitebg" style="">'
# patron = r'<a\shref="([^"]+)".*?>\s<img\s.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p></div>'
# patron = r'<a\s*href="([^"]+)".*?>\s*<img\s*.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p></div>'
# blocco = scrapertools.find_single_match(data,
# r'<div\s*class="col-xs-\d+ col-sm-\d+-\d+">(.*?)<div\s*class="container-fluid whitebg" style="">')
# matches = re.compile(patron, re.DOTALL).findall(blocco)
patron_block = r'<div\s*class="col-xs-\d+ col-sm-\d+-\d+">(.*?)<div\s*class="container-fluid whitebg" style="">'
patron = r'<a\s*href="([^"]+)".*?>\s*<img\s*.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p></div>'
matches, data = support.match(item, patron, patron_block, headers) matches, data = support.match(item, patron, patron_block, headers)
for scrapedurl, scrapedimg, scrapedtitle in matches: for scrapedurl, scrapedimg, scrapedtitle in matches:
scrapedtitle = cleantitle(scrapedtitle) scrapedtitle = cleantitle(scrapedtitle)
if scrapedtitle not in ['DMCA','Contatti','Lista di tutte le serie tv']: if scrapedtitle not in ['DMCA', 'Contatti', 'Lista di tutte le serie tv']:
itemlist.append( itemlist.append(
Item(channel=item.channel, Item(channel=item.channel,
action="episodios", action="episodios",
@@ -254,7 +222,7 @@ def lista_serie(item):
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True) tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
support.nextPage(itemlist,item,data,r"<link\s.*?rel='next'\shref='([^']*)'") support.nextPage(itemlist, item, data, r"<link\s.*?rel='next'\shref='([^']*)'")
return itemlist return itemlist
@@ -263,46 +231,40 @@ def lista_serie(item):
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def episodios(item): def episodios(item):
support.log(item.channel+" episodios") log()
itemlist = [] itemlist = []
# data = httptools.downloadpage(item.url, headers=headers).data patron = r'<div\sclass="[^"]+">\s([^<]+)<\/div>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+><p[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>'
patron += r'[^<]+[^"]+".*?serie="([^"]+)".*?stag="([0-9]*)".*?ep="([0-9]*)"\s'
patron = r'<div\s*class="[^"]+">\s*([^<]+)<\/div>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+><p[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>' patron += r'.*?embed="([^"]+)"\s.*?embed2="([^"]+)?"\s.*?embed3="([^"]+)?"?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>\s?'
patron += r'[^<]+[^"]+".*?serie="([^"]+)".*?stag="([0-9]*)".*?ep="([0-9]*)"\s*' patron += r'(?:<img\sclass="[^"]+" meta-src="([^"]+)"[^>]+>|<img\sclass="[^"]+" src="" data-original="([^"]+)"[^>]+>)?'
patron += r'.*?embed="([^"]+)"\s*.*?embed2="([^"]+)?"\s*.*?embed3="([^"]+)?"?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>\s*'
patron += r'(?:<img\s*class="[^"]+" meta-src="([^"]+)"[^>]+>|<img\s*class="[^"]+" src="" data-original="([^"]+)"[^>]+>)?'
# matches = re.compile(patron, re.DOTALL).findall(data)
# logger.debug(matches)
matches = support.match(item, patron, headers=headers)[0] matches = support.match(item, patron, headers=headers)[0]
for scrapedtitle, scrapedepisodetitle, scrapedplot, scrapedserie, scrapedseason, scrapedepisode, scrapedurl, scrapedurl2, scrapedurl3, scrapedthumbnail, scrapedthumbnail2 in matches:
for scrapedtitle, scrapedepisodetitle, scrapedplot, scrapedserie, scrapedseason, scrapedepisode, scrapedurl, scrapedurl2,scrapedurl3,scrapedthumbnail,scrapedthumbnail2 in matches:
scrapedtitle = cleantitle(scrapedtitle) scrapedtitle = cleantitle(scrapedtitle)
scrapedepisode = scrapedepisode.zfill(2) scrapedepisode = scrapedepisode.zfill(2)
scrapedepisodetitle = cleantitle(scrapedepisodetitle) scrapedepisodetitle = cleantitle(scrapedepisodetitle)
title = str("%sx%s %s" % (scrapedseason, scrapedepisode, scrapedepisodetitle)).strip() title = str("%sx%s %s" % (scrapedseason, scrapedepisode, scrapedepisodetitle)).strip()
if 'SUB-ITA' in scrapedtitle: if 'SUB-ITA' in scrapedtitle:
title +=" Sub-ITA" title += " Sub-ITA"
infoLabels = {} infoLabels = {}
infoLabels['season'] = scrapedseason infoLabels['season'] = scrapedseason
infoLabels['episode'] = scrapedepisode infoLabels['episode'] = scrapedepisode
itemlist.append( itemlist.append(
Item(channel=item.channel, Item(channel=item.channel,
action="findvideos", action="findvideos",
title=title, title=title,
fulltitle=scrapedtitle, fulltitle=scrapedtitle,
url=scrapedurl+"\r\n"+scrapedurl2+"\r\n"+scrapedurl3, url=scrapedurl + "\r\n" + scrapedurl2 + "\r\n" + scrapedurl3,
contentType="episode", contentType="episode",
plot=scrapedplot, plot=scrapedplot,
contentSerieName=scrapedserie, contentSerieName=scrapedserie,
contentLanguage='Sub-ITA' if 'Sub-ITA' in title else '', contentLanguage='Sub-ITA' if 'Sub-ITA' in title else '',
infoLabels=infoLabels, infoLabels=infoLabels,
thumbnail=scrapedthumbnail2 if scrapedthumbnail2 != '' else scrapedthumbnail, thumbnail=scrapedthumbnail2 if scrapedthumbnail2 != '' else scrapedthumbnail,
folder=True)) folder=True))
tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True) tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True)
@@ -315,22 +277,18 @@ def episodios(item):
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def findepvideos(item): def findepvideos(item):
support.log(item.channel+" findepvideos") log()
data = httptools.downloadpage(item.url, headers=headers).data data = httptools.downloadpage(item.url, headers=headers).data
matches = scrapertools.find_multiple_matches(data, item.extra) matches = scrapertools.find_multiple_matches(data, item.extra)
data = "\r\n".join(matches[0]) data = "\r\n".join(matches[0])
item.contentType = 'movie' item.contentType = 'movie'
itemlist = support.server(item, data=data) return support.server(item, data=data)
return itemlist
# ================================================================================================================ # ================================================================================================================
# ---------------------------------------------------------------------------------------------------------------- # ----------------------------------------------------------------------------------------------------------------
def findvideos(item): def findvideos(item):
support.log(item.channel+" findvideos") log()
logger.debug(item.url) logger.debug(item.url)
itemlist = support.server(item, data=item.url) return support.server(item, data=item.url)
return itemlist
core/support.py
+4 -4
View File
@@ -452,7 +452,7 @@ def match(item, patron='', patron_block='', headers='', url=''):
matches = [] matches = []
url = url if url else item.url url = url if url else item.url
data = httptools.downloadpage(url, headers=headers, ignore_response_code=True).data.replace("'", '"') data = httptools.downloadpage(url, headers=headers, ignore_response_code=True).data.replace("'", '"')
data = re.sub(r'\n|\t|\s\s', '', data) data = re.sub(r'\n|\t|\s\s', ' ', data)
log('DATA= ', data) log('DATA= ', data)
if patron_block: if patron_block:
@@ -500,11 +500,11 @@ def videolibrary(itemlist, item, typography='', function_level=1):
return itemlist return itemlist
def nextPage(itemlist, item, data, patron, function_level=1): def nextPage(itemlist, item, data='', patron='', function_level=1, next_page=''):
# Function_level is useful if the function is called by another function. # Function_level is useful if the function is called by another function.
# If the call is direct, leave it blank # If the call is direct, leave it blank
if next_page == '':
next_page = scrapertoolsV2.find_single_match(data, patron) next_page = scrapertoolsV2.find_single_match(data, patron)
if next_page != "": if next_page != "":
if 'http' not in next_page: if 'http' not in next_page: