diff --git a/addon.xml b/addon.xml index 3542d0df..ece09699 100644 --- a/addon.xml +++ b/addon.xml @@ -5,7 +5,6 @@ - video diff --git a/channels/altadefinizione01_club.py b/channels/altadefinizione01_club.py index 2895bb93..d75f8edb 100644 --- a/channels/altadefinizione01_club.py +++ b/channels/altadefinizione01_club.py @@ -3,131 +3,98 @@ # -*- Riscritto per KOD -*- # -*- By Greko -*- # -*- last change: 04/05/2019 +# -*- doppione di altadefinizione01 - -from core import channeltools, servertools, support +from specials import autoplay +from core import servertools, support from core.item import Item from platformcode import config, logger -from specials import autoplay __channel__ = "altadefinizione01_club" host = config.get_channel_url(__channel__) -# ======== Funzionalità ============================= - -checklinks = config.get_setting('checklinks', __channel__) -checklinks_number = config.get_setting('checklinks_number', __channel__) - headers = [['User-Agent', 'Mozilla/50.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Firefox/45.0'], ['Referer', host]] -parameters = channeltools.get_channel_parameters(__channel__) -fanart_host = parameters['fanart'] -thumbnail_host = parameters['thumbnail'] -IDIOMAS = {'Italiano': 'IT'} -list_language = IDIOMAS.values() -list_servers = ['verystream','openload','supervideo','rapidvideo','streamango'] # per l'autoplay +list_servers = ['verystream','openload','rapidvideo','streamango'] list_quality = ['default'] -# =========== home menu =================== - +@support.menu def mainlist(item): - """ - Creo il menu principale del canale - :param item: - :return: itemlist [] - """ - logger.info("%s mainlist log: %s" % (__channel__, item)) - itemlist = [] + film = '' - # Menu Principale - support.menu(itemlist, 'Film Ultimi Arrivi bold', 'peliculas', host, args='pellicola') - support.menu(itemlist, 'Genere', 'categorie', host, args='genres') - support.menu(itemlist, 'Per anno submenu', 'categorie', host, args=['Film per Anno','years']) - support.menu(itemlist, 'Per lettera', 'categorie', host + '/catalog/a/', args=['Film per Lettera','orderalf']) - support.menu(itemlist, 'Al Cinema bold', 'peliculas', host + '/cinema/', args='pellicola') - support.menu(itemlist, 'Sub-ITA bold', 'peliculas', host + '/sub-ita/', args='pellicola') - support.menu(itemlist, 'Cerca film submenu', 'search', host, args = 'search') + filmSub = [ + ('Al Cinema', ['/cinema/', 'peliculas', 'pellicola']), + ('Generi', ['', 'categorie', 'genres']), + ('Lettera', ['/catalog/a/', 'categorie', 'orderalf']), + ('Anni', ['', 'categorie', 'years']), + ('Sub-ITA', ['/sub-ita/', 'peliculas', 'pellicola']) + ] - autoplay.init(item.channel, list_servers, list_quality) - autoplay.show_option(item.channel, itemlist) - - support.channel_config(item, itemlist) - - return itemlist + return locals() # ======== def in ordine di menu =========================== # =========== def per vedere la lista dei film ============= - +@support.scrape def peliculas(item): - logger.info("%s mainlist peliculas log: %s" % (__channel__, item)) - itemlist = [] +## import web_pdb; web_pdb.set_trace() + support.log('peliculas',item) - patron_block = r'
(.*?)
' + action="findvideos" if item.args == "search": - patron_block = r' (.*?)
' - patron = r'

.(.*?)

)[ ]
.*?

(.*?)

' + patronBlock = r'
(.*?)
' + else: + patronBlock = r'
(.*?)
' + patron = r'

..*?<.*?src="(?P[^"]+)"'\ + '.+?[^>]+>[^>]+
(?P[A-Z]+)<[^>]+>(?:.[^>]+>(?P.*?)<[^>]+>).*?'\ + '

(?P.*?)</p>[^>]+> [^>]+> [^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+> [^>]+> '\ + '[^>]+>[^>]+>(?P<year>\d{4})[^>]+>[^>]+> [^>]+>[^>]+>(?P<duration>\d+).+?>' - listGroups = ['url', 'thumb', 'lang', 'title', 'year'] + patronNext = '<span>\d</span> <a href="([^"]+)">' - patronNext = '<span>[^<]+</span>[^<]+<a href="(.*?)">' - - itemlist = support.scrape(item, patron=patron, listGroups=listGroups, - headers= headers, patronNext=patronNext,patron_block=patron_block, - action='findvideos') - - return itemlist + return locals() # =========== def pagina categorie ====================================== +@support.scrape def categorie(item): - logger.info("%s mainlist categorie log: %s" % (__channel__, item)) - itemlist = [] + support.log('categorie',item) +## import web_pdb; web_pdb.set_trace() + + if item.args != 'orderalf': action = "peliculas" + else: action = 'orderalf' + blacklist = 'Altadefinizione01' - # da qui fare le opportuni modifiche - patron = r'<li><a href="(.*?)">(.*?)</a>' - action = 'peliculas' if item.args == 'genres': - bloque = r'<ul class="kategori_list">(.*?)</ul>' - elif item.args[1] == 'years': - bloque = r'<ul class="anno_list">(.*?)</ul>' - elif item.args[1] == 'orderalf': - bloque = r'<div class="movies-letter">(.*)<div class="clearfix">' - patron = r'<a title=.*?href="(.*?)"><span>(.*?)</span>' - action = 'orderalf' - - listGroups = ['url', 'title'] - patronNext = '' - - itemlist = support.scrape(item, patron=patron, listGroups=listGroups, - headers= headers, patronNext=patronNext, patron_block = bloque, - action=action) - - return itemlist + patronBlock = r'<ul class="kategori_list">(.*?)</ul>' + patron = '<li><a href="(?P<url>[^"]+)">(?P<title>.*?)</a>' + elif item.args == 'years': + patronBlock = r'<ul class="anno_list">(.*?)</ul>' + patron = '<li><a href="(?P<url>[^"]+)">(?P<title>.*?)</a>' + elif item.args == 'orderalf': + patronBlock = r'<div class="movies-letter">(.*)<div class="clearfix">' + patron = '<a title=.*?href="(?P<url>[^"]+)"><span>(?P<title>.*?)</span>' + return locals() # =========== def pagina lista alfabetica =============================== - +@support.scrape def orderalf(item): - logger.info("%s mainlist orderalf log: %s" % (__channel__, item)) - itemlist = [] - listGroups = ['url', 'title', 'thumb', 'year', 'lang'] - patron = r'<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') - patronNext = r'<span>[^<]+</span>[^<]+<a href="(.*?)">' - - itemlist = support.scrape(item, patron=patron, listGroups=listGroups, - headers= headers, patronNext=patronNext, - action='findvideos') + support.log('orderalf',item) - return itemlist + action= 'findvideos' + patron = r'<td class="mlnh-thumb"><a href="(?P<url>[^"]+)".*?src="(?P<thumb>[^"]+)"'\ + '.+?[^>]+>[^>]+ [^>]+[^>]+ [^>]+>(?P<title>[^<]+).*?[^>]+>(?P<year>\d{4})<'\ + '[^>]+>[^>]+>(?P<quality>[A-Z]+)[^>]+> <td class="mlnh-5">(?P<lang>.*?)</td>' + patronNext = r'<span>[^<]+</span>[^<]+<a href="(.*?)">' + return locals() # =========== def pagina del film con i server per verderlo ============= def findvideos(item): - logger.info("%s mainlist findvideos_film log: %s" % (__channel__, item)) - itemlist = [] + support.log('findvideos', item) return support.server(item, headers=headers) # =========== def per cercare film/serietv ============= @@ -137,7 +104,7 @@ def search(item, text): itemlist = [] text = text.replace(" ", "+") item.url = host + "/index.php?do=search&story=%s&subaction=search" % (text) - #item.extra = "search" + item.args = "search" try: return peliculas(item) # Cattura la eccezione così non interrompe la ricerca globle se il canale si rompe! @@ -150,16 +117,18 @@ def search(item, text): # =========== def per le novità nel menu principale ============= def newest(categoria): - logger.info("%s mainlist newest log: %s" % (__channel__, categoria)) + + support.log(categoria) itemlist = [] item = Item() try: - item.url = host - item.action = "peliculas" - itemlist = peliculas(item) - if itemlist[-1].action == "peliculas": - itemlist.pop() + if categoria == "peliculas": + item.url = host + item.action = "peliculas" + itemlist = peliculas(item) + if itemlist[-1].action == "peliculas": + itemlist.pop() # Continua la ricerca in caso di errore except: import sys @@ -167,4 +136,4 @@ def newest(categoria): logger.error("{0}".format(line)) return [] - return itemlist + return itemlist \ No newline at end of file diff --git a/channels/altadefinizione01_link.json b/channels/altadefinizione01_link.json index 579853b4..610822e4 100644 --- a/channels/altadefinizione01_link.json +++ b/channels/altadefinizione01_link.json @@ -4,9 +4,9 @@ "active": true, "adult": false, "language": ["ita"], - "fanart": "https://altadefinizione01.estate/templates/Dark/img/nlogo.png", - "thumbnail": "https://altadefinizione01.estate/templates/Dark/img/nlogo.png", - "banner": "https://altadefinizione01.estate/templates/Dark/img/nlogo.png", + "fanart": "https://altadefinizione01.tools/templates/Dark/img/nlogo.png", + "thumbnail": "https://altadefinizione01.tools/templates/Dark/img/nlogo.png", + "banner": "https://altadefinizione01.tools/templates/Dark/img/nlogo.png", "fix" : "reimpostato url e modificato file per KOD", "change_date": "2019-30-04", "categories": [ @@ -18,7 +18,7 @@ "id": "channel_host", "type": "text", "label": "Host del canale", - "default": "https://altadefinizione01.estate/", + "default": "https://www.altadefinizione01.tools/", "enabled": true, "visible": true }, diff --git a/channels/altadefinizione01_link.py b/channels/altadefinizione01_link.py index 584e175b..d45e843f 100644 --- a/channels/altadefinizione01_link.py +++ b/channels/altadefinizione01_link.py @@ -2,7 +2,7 @@ # -*- Channel Altadefinizione01L Film - Serie -*- # -*- By Greko -*- -import channelselector +##import channelselector from specials import autoplay from core import servertools, support, jsontools from core.item import Item @@ -11,88 +11,66 @@ from platformcode import config, logger __channel__ = "altadefinizione01_link" # ======== def per utility INIZIO ============================ +host = config.get_setting("channel_host", __channel__) list_servers = ['supervideo', 'streamcherry','rapidvideo', 'streamango', 'openload'] list_quality = ['default'] -host = config.get_setting("channel_host", __channel__) - headers = [['Referer', host]] # =========== home menu =================== - +@support.menu def mainlist(item): - """ - Creo il menu principale del canale - :param item: - :return: itemlist [] - """ - support.log() - itemlist = [] - # Menu Principale - support.menu(itemlist, 'Novità bold', 'peliculas', host) - support.menu(itemlist, 'Film per Genere', 'genres', host, args='genres') - support.menu(itemlist, 'Film per Anno submenu', 'genres', host, args='years') - support.menu(itemlist, 'Film per Qualità submenu', 'genres', host, args='quality') - support.menu(itemlist, 'Al Cinema bold', 'peliculas', host + '/film-del-cinema') - support.menu(itemlist, 'Popolari bold', 'peliculas', host + '/piu-visti.html') - support.menu(itemlist, 'Mi sento fortunato bold', 'genres', host, args='lucky') - support.menu(itemlist, 'Sub-ITA bold', 'peliculas', host + '/film-sub-ita/') - support.menu(itemlist, 'Cerca film submenu', 'search', host) + film = '' + filmSub = [ + ('Al Cinema', ['/film-del-cinema', 'peliculas']), + ('Generi', ['', 'genres', 'genres']), + ('Anni', ['', 'genres', 'years']), + ('Mi sento fortunato', ['/piu-visti.html', 'genres', 'lucky']), + ('Popolari', ['/piu-visti.html', 'peliculas', '']), + ('Qualità', ['/piu-visti.html', 'genres', 'quality']), + ('Sub-ITA', ['/sub-ita/', 'peliculas']) + ] - # per autoplay - autoplay.init(item.channel, list_servers, list_quality) - autoplay.show_option(item.channel, itemlist) - - support.channel_config(item, itemlist) - - return itemlist + return locals() # ======== def in ordine di action dal menu =========================== +@support.scrape def peliculas(item): - support.log + #import web_pdb; web_pdb.set_trace() + support.log('peliculas',item) itemlist = [] - patron = r'class="innerImage">.*?href="([^"]+)".*?src="([^"]+)"'\ - '.*?class="ml-item-title">([^<]+)</.*?class="ml-item-label"> (\d{4}) <'\ - '.*?class="ml-item-label">.*?class="ml-item-label ml-item-label-.+?"> '\ - '(.+?) </div>.*?class="ml-item-label"> (.+?) </' - listGroups = ['url', 'thumb', 'title', 'year', 'quality', 'lang'] + patron = r'class="innerImage">.*?href="(?P<url>[^"]+)".*?src="(?P<thumb>[^"]+)"'\ + '.*?class="ml-item-title">(?P<title>[^<]+)</.*?class="ml-item-label"> '\ + '(?P<year>\d{4}) <.*?class="ml-item-label"> (?P<duration>\d+) .*?'\ + 'class="ml-item-label ml-item-label-.+?"> (?P<quality>.+?) <.*?'\ + 'class="ml-item-label"> (?P<lang>.+?) </' patronNext = '<span>\d</span> <a href="([^"]+)">' - - itemlist = support.scrape(item, patron=patron, listGroups=listGroups, - headers= headers, patronNext=patronNext, - action='findvideos') - - return itemlist + + return locals() # =========== def pagina categorie ====================================== - +@support.scrape def genres(item): support.log - itemlist = [] - #data = httptools.downloadpage(item.url, headers=headers).data + action = 'peliculas' if item.args == 'genres': - bloque = r'<ul class="listSubCat" id="Film">(.*?)</ul>' + patronBlock = r'<ul class="listSubCat" id="Film">(.*?)</ul>' elif item.args == 'years': - bloque = r'<ul class="listSubCat" id="Anno">(.*?)</ul>' + patronBlock = r'<ul class="listSubCat" id="Anno">(.*?)</ul>' elif item.args == 'quality': - bloque = r'<ul class="listSubCat" id="Qualita">(.*?)</ul>' + patronBlock = r'<ul class="listSubCat" id="Qualita">(.*?)</ul>' elif item.args == 'lucky': # sono i titoli random nella pagina, cambiano 1 volta al dì - bloque = r'FILM RANDOM.*?class="listSubCat">(.*?)</ul>' + patronBlock = r'FILM RANDOM.*?class="listSubCat">(.*?)</ul>' action = 'findvideos' - - patron = r'<li><a href="([^"]+)">(.*?)<' - listGroups = ['url','title'] - itemlist = support.scrape(item, patron=patron, listGroups=listGroups, - headers= headers, patron_block = bloque, - action=action) + patron = r'<li><a href="(?P<url>[^"]+)">(?P<title>[^<]+)<' - return itemlist + return locals() # =========== def per cercare film/serietv ============= #host+/index.php?do=search&story=avatar&subaction=search @@ -133,15 +111,6 @@ def newest(categoria): return itemlist + def findvideos(item): - support.log() - - itemlist = support.server(item, headers=headers) - - # Requerido para FilterTools - # itemlist = filtertools.get_links(itemlist, item, list_language) - - # Requerido para AutoPlay - autoplay.start(itemlist, item) - - return itemlist + return support.server(item, headers=headers) diff --git a/channels/altadefinizioneclick.py b/channels/altadefinizioneclick.py index e4db4965..b1fd9aca 100644 --- a/channels/altadefinizioneclick.py +++ b/channels/altadefinizioneclick.py @@ -3,41 +3,60 @@ # Canale per altadefinizioneclick # ---------------------------------------------------------- -import re - +from specials import autoplay from core import servertools, support from core.item import Item -from platformcode import logger, config -from specials import autoplay +from platformcode import config, logger -#host = config.get_setting("channel_host", 'altadefinizioneclick') __channel__ = 'altadefinizioneclick' -host = config.get_channel_url(__channel__) -IDIOMAS = {'Italiano': 'IT'} -list_language = IDIOMAS.values() +host = config.get_channel_url(__channel__) +headers = [['Referer', host]] list_servers = ['verystream', 'openload', 'streamango', "vidoza", "thevideo", "okru", 'youtube'] list_quality = ['1080p'] -checklinks = config.get_setting('checklinks', 'altadefinizioneclick') -checklinks_number = config.get_setting('checklinks_number', 'altadefinizioneclick') - -headers = [['Referer', host]] - +@support.menu def mainlist(item): - support.log() - itemlist = [] + support.log() - support.menu(itemlist, 'Film', 'peliculas', host + "/nuove-uscite/") - support.menu(itemlist, 'Per Genere submenu', 'menu', host, args='Film') - support.menu(itemlist, 'Per Anno submenu', 'menu', host, args='Anno') - support.menu(itemlist, 'Sub-ITA', 'peliculas', host + "/sub-ita/") - support.menu(itemlist, 'Cerca...', 'search', host, 'movie') - support.aplay(item, itemlist,list_servers, list_quality) - support.channel_config(item, itemlist) + film = '' #'/nuove-uscite/' + filmSub = [ + ('Novità', ['/nuove-uscite/', 'peliculas']), + ('Al Cinema', ['/film-del-cinema', 'peliculas']), + ('Generi', ['', 'menu', 'Film']), + ('Anni', ['', 'menu', 'Anno']), + ('Qualità', ['', 'menu', 'Qualita']), + ('Sub-ITA', ['/sub-ita/', 'peliculas']) + ] - return itemlist + return locals() +@support.scrape +def menu(item): + support.log() + + action='peliculas' + patron = r'<li><a href="(?P<url>[^"]+)">(?P<title>[^<]+)</a></li>' + patronBlock= r'<ul class="listSubCat" id="'+ str(item.args) + '">(.*?)</ul>' + + return locals() + +@support.scrape +def peliculas(item): + support.log() + if item.extra == 'search': + patron = r'<a href="(?P<url>[^"]+)">\s*<div class="wrapperImage">(?:<span class="hd">(?P<quality>[^<]+)'\ + '<\/span>)?<img[^s]+src="(?P<thumb>[^"]+)"[^>]+>[^>]+>[^>]+>(?P<title>[^<]+)<[^<]+>'\ + '(?:.*?IMDB:\s(\2[^<]+)<\/div>)?' + else: + patron = r'<img width[^s]+src="(?P<thumb>[^"]+)[^>]+><\/a>.*?<a href="(?P<url>[^"]+)">(?P<title>[^(?:\]|<)]+)'\ + '(?:\[(?P<lang>[^\]]+)\])?<\/a>[^>]+>[^>]+>[^>]+>(?:\sIMDB\:\s(?P<rating>[^<]+)<)?'\ + '(?:.*?<span class="hd">(?P<quality>[^<]+)<\/span>)?\s*<a' + + # in caso di CERCA si apre la maschera di inserimento dati + patronNext = r'<a class="next page-numbers" href="([^"]+)">' + + return locals() def search(item, texto): support.log("search ", texto) @@ -77,36 +96,6 @@ def newest(categoria): return itemlist - -def menu(item): - support.log() - itemlist = support.scrape(item, '<li><a href="([^"]+)">([^<]+)</a></li>', ['url', 'title'], headers, patron_block='<ul class="listSubCat" id="'+ str(item.args) + '">(.*?)</ul>', action='peliculas') - return support.thumb(itemlist) - -def peliculas(item): - support.log() - if item.extra == 'search': - patron = r'<a href="([^"]+)">\s*<div class="wrapperImage">(?:<span class="hd">([^<]+)<\/span>)?<img[^s]+src="([^"]+)"[^>]+>[^>]+>[^>]+>([^<]+)<[^<]+>(?:.*?IMDB:\s([^<]+)<\/div>)?' - elements = ['url', 'quality', 'thumb', 'title', 'rating'] - - else: - patron = r'<img width[^s]+src="([^"]+)[^>]+><\/a>.*?<a href="([^"]+)">([^(?:\]|<)]+)(?:\[([^\]]+)\])?<\/a>[^>]+>[^>]+>[^>]+>(?:\sIMDB\:\s([^<]+)<)?(?:.*?<span class="hd">([^<]+)<\/span>)?\s*<a' - elements =['thumb', 'url', 'title','lang', 'rating', 'quality'] - itemlist = support.scrape(item, patron, elements, headers, patronNext='<a class="next page-numbers" href="([^"]+)">') - return itemlist - - def findvideos(item): - support.log() - - itemlist = support.hdpass_get_servers(item) - - if checklinks: - itemlist = servertools.check_list_links(itemlist, checklinks_number) - - # itemlist = filtertools.get_links(itemlist, item, list_language) - - autoplay.start(itemlist, item) - support.videolibrary(itemlist, item ,'color kod bold') - - return itemlist + support.log('findvideos', item) + return support.hdpass_get_servers(item) diff --git a/channels/animeleggendari.py b/channels/animeleggendari.py index d5f4fe24..aa047852 100644 --- a/channels/animeleggendari.py +++ b/channels/animeleggendari.py @@ -58,7 +58,7 @@ def search(item, texto): def last_ep(item): log('ANIME PER TUTTI') - return support.scrape(item, '<a href="([^"]+)">([^<]+)<', ['url','title'],patron_block='<ul class="mh-tab-content-posts">(.*?)<\/ul>', action='findvideos') + return support.scrape(item, '<a href="([^"]+)">([^<]+)<', ['url','title'],patronBlock='<ul class="mh-tab-content-posts">(.*?)<\/ul>', action='findvideos') def newest(categoria): log('ANIME PER TUTTI') @@ -83,7 +83,7 @@ def newest(categoria): return itemlist def genres(item): - itemlist = support.scrape(item, '<a href="([^"]+)">([^<]+)<', ['url', 'title'], action='peliculas', patron_block=r'Generi.*?<ul.*?>(.*?)<\/ul>', blacklist=['Contattaci','Privacy Policy', 'DMCA']) + itemlist = support.scrape(item, '<a href="([^"]+)">([^<]+)<', ['url', 'title'], action='peliculas', patronBlock=r'Generi.*?<ul.*?>(.*?)<\/ul>', blacklist=['Contattaci','Privacy Policy', 'DMCA']) return support.thumb(itemlist) def peliculas(item): diff --git a/channels/animeworld.py b/channels/animeworld.py index 5b0ac071..faeba1e7 100644 --- a/channels/animeworld.py +++ b/channels/animeworld.py @@ -45,10 +45,10 @@ def mainlist(item): def generi(item): log() - patron_block = r'</i>\sGeneri</a>\s*<ul class="sub">(.*?)</ul>' + patronBlock = r'</i>\sGeneri</a>\s*<ul class="sub">(.*?)</ul>' patron = r'<a href="([^"]+)"\stitle="([^"]+)">' - return support.scrape(item, patron, ['url','title'], patron_block=patron_block, action='video') + return support.scrape(item, patron, ['url','title'], patronBlock=patronBlock, action='video') # Crea Menu Filtro ====================================================== @@ -118,7 +118,7 @@ def search(item, texto): # Lista A-Z ==================================================== def alfabetico(item): - return support.scrape(item, '<a href="([^"]+)" title="([^"]+)">', ['url', 'title'], patron_block=r'<span>.*?A alla Z.<\/span>.*?<ul>(.*?)<\/ul>', action='lista_anime') + return support.scrape(item, '<a href="([^"]+)" title="([^"]+)">', ['url', 'title'], patronBlock=r'<span>.*?A alla Z.<\/span>.*?<ul>(.*?)<\/ul>', action='lista_anime') def lista_anime(item): @@ -259,9 +259,10 @@ def video(item): def episodios(item): log() itemlist = [] + patron_block = r'server active(.*?)server hidden ' patron = r'<li><a [^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+"[^=]+="[^"]+" href="([^"]+)"[^>]+>([^<]+)<' - matches = support.match(item, patron, patron_block)[0] + matches = support.match(item, patron, patronBlock)[0] for scrapedurl, scrapedtitle in matches: itemlist.append( diff --git a/channels/cineblog01.py b/channels/cineblog01.py index 0881884a..ea56d0e9 100644 --- a/channels/cineblog01.py +++ b/channels/cineblog01.py @@ -36,31 +36,24 @@ blacklist = ['BENVENUTI', 'Richieste Serie TV', 'CB01.UNO ▶ TROVA L’ 'Openload: la situazione. Benvenuto Verystream', 'Openload: lo volete ancora?'] +@support.menu def mainlist(item): findhost() + film = '' + filmSub = [ + ('HD', ['', 'menu', 'Film HD Streaming']), + ('Generi', ['', 'menu', 'Film per Genere']), + ('Anni', ['', 'menu', 'Film per Anno']) + ] + tvshow = '/serietv/' + tvshowSub = [ + ('Aggiornamenti serie tv', ['/serietv/aggiornamento-quotidiano-serie-tv/', 'last']), + ('Per Lettera', ['/serietv/', 'menu', 'Serie-Tv per Lettera']), + ('Per Genere', ['/serietv/aggiornamento-quotidiano-serie-tv/', 'menu', 'Serie-Tv per Genere']), + ('Per anno', ['/serietv/aggiornamento-quotidiano-serie-tv/', 'menu', 'Serie-Tv per Anno']) + ] - autoplay.init(item.channel, list_servers, list_quality) - - # Main options - itemlist = [] - support.menu(itemlist, 'Ultimi 100 Film Aggiornati bold', 'last', host + '/lista-film-ultimi-100-film-aggiornati/') - - support.menu(itemlist, 'Film bold', 'peliculas', host) - support.menu(itemlist, 'HD submenu', 'menu', host, args="Film HD Streaming") - support.menu(itemlist, 'Per genere submenu', 'menu', host, args="Film per Genere") - support.menu(itemlist, 'Per anno submenu', 'menu', host, args="Film per Anno") - support.menu(itemlist, 'Cerca film... submenu', 'search', host, args='film') - - support.menu(itemlist, 'Serie TV bold', 'peliculas', host + '/serietv/', contentType='tvshow') - support.menu(itemlist, 'Aggiornamenti serie tv', 'last', host + '/serietv/aggiornamento-quotidiano-serie-tv/', contentType='tvshow') - support.menu(itemlist, 'Per Lettera submenu', 'menu', host + '/serietv/', contentType='tvshow', args="Serie-Tv per Lettera") - support.menu(itemlist, 'Per Genere submenu', 'menu', host + '/serietv/', contentType='tvshow', args="Serie-Tv per Genere") - support.menu(itemlist, 'Per anno submenu', 'menu', host + '/serietv/', contentType='tvshow', args="Serie-Tv per Anno") - support.menu(itemlist, 'Cerca serie... submenu', 'search', host + '/serietv/', contentType='tvshow', args='serie') - - autoplay.show_option(item.channel, itemlist) - - return itemlist + return locals() def menu(item): @@ -110,7 +103,7 @@ def newest(categoria): item.url = host + '/lista-film-ultimi-100-film-aggiunti/' return support.scrape(item, r'<a href=([^>]+)>([^<([]+)(?:\[([A-Z]+)\])?\s\(([0-9]{4})\)<\/a>', ['url', 'title', 'quality', 'year'], - patron_block=r'Ultimi 100 film aggiunti:.*?<\/td>') + patronBlock=r'Ultimi 100 film aggiunti:.*?<\/td>') def last(item): @@ -170,21 +163,22 @@ def last(item): return itemlist +@support.scrape def peliculas(item): support.log() if item.contentType == 'movie' or '/serietv/' not in item.url: - patron = r'<div class="?card-image"?>.*?<img src="?([^" ]+)"? alt.*?<a href="?([^" >]+)(?:\/|")>([^<[(]+)(?:\[([A-Za-z0-9/-]+)])? (?:\(([0-9]{4})\))?.*?<strong>([^<>&]+).*?DURATA ([0-9]+).*?<br(?: /)?>([^<>]+)' - listGroups = ['thumb', 'url', 'title', 'quality', 'year', 'genre', 'duration', 'plot'] + patron = r'<div class="?card-image"?>.*?<img src="?(?P<thumb>[^" ]+)"? alt.*?<a href="?(?P<url>[^" >]+)(?:\/|")>(?P<title>[^<[(]+)(?:\[(?P<quality>[A-Za-z0-9/-]+)])? (?:\((?P<year>[0-9]{4})\))?.*?<strong>(?P<genre>[^<>&]+).*?DURATA (?P<duration>[0-9]+).*?<br(?: /)?>(?P<plot>[^<>]+)' action = 'findvideos' else: - patron = r'div class="card-image">.*?<img src="([^ ]+)" alt.*?<a href="([^ >]+)">([^<[(]+)<\/a>.*?<strong><span style="[^"]+">([^<>0-9(]+)\(([0-9]{4}).*?</(?:p|div)>(.*?)</div' + patron = r'div class="card-image">.*?<img src="(?P<thumb>[^ ]+)" alt.*?<a href="(?P<url>[^ >]+)">(?P<title>[^<[(]+)<\/a>.*?<strong><span style="[^"]+">(?P<genre>[^<>0-9(]+)\((?P<year>[0-9]{4}).*?</(?:p|div)>(?P<plot>.*?)</div' listGroups = ['thumb', 'url', 'title', 'genre', 'year', 'plot'] action = 'episodios' - return support.scrape(item, patron_block=[r'<div class="?sequex-page-left"?>(.*?)<aside class="?sequex-page-right"?>', - '<div class="?card-image"?>.*?(?=<div class="?card-image"?>|<div class="?rating"?>)'], - patron=patron, listGroups=listGroups, - patronNext='<a class="?page-link"? href="?([^>]+)"?><i class="fa fa-angle-right">', blacklist=blacklist, action=action) + patronBlock=[r'<div class="?sequex-page-left"?>(.*?)<aside class="?sequex-page-right"?>', + '<div class="?card-image"?>.*?(?=<div class="?card-image"?>|<div class="?rating"?>)'] + patronNext='<a class="?page-link"? href="?([^>]+)"?><i class="fa fa-angle-right">' + + return locals() def episodios(item): diff --git a/channels/cinemalibero.py b/channels/cinemalibero.py index 58634f13..811b01f4 100644 --- a/channels/cinemalibero.py +++ b/channels/cinemalibero.py @@ -64,7 +64,7 @@ def search(item, texto): def genres(item): - return support.scrape(item, patron_block=r'<div id="bordobar" class="dropdown-menu(.*?)</li>', patron=r'<a class="dropdown-item" href="([^"]+)" title="([A-z]+)"', listGroups=['url', 'title'], action='video') + return support.scrape(item, patronBlock=r'<div id="bordobar" class="dropdown-menu(.*?)</li>', patron=r'<a class="dropdown-item" href="([^"]+)" title="([A-z]+)"', listGroups=['url', 'title'], action='video') def video(item): diff --git a/channels/cinemastreaming.py b/channels/cinemastreaming.py index ae7c72ef..68b7570f 100644 --- a/channels/cinemastreaming.py +++ b/channels/cinemastreaming.py @@ -108,11 +108,11 @@ def episodios(item): def menu(item): - patron_block = r'<ul class="sub-menu">.*?</ul>' + patronBlock = r'<ul class="sub-menu">.*?</ul>' patron = r'menu-category-list"><a href="([^"]+)">([^<]+)<' list_groups = ["url", "title"] - return support.scrape(item, patron, list_groups, blacklist="Anime", action="peliculas_menu", patron_block=patron_block) + return support.scrape(item, patron, list_groups, blacklist="Anime", action="peliculas_menu", patronBlock=patronBlock) def search(item, texto): diff --git a/channels/dreamsub.py b/channels/dreamsub.py index aa57640b..dee2bfe6 100644 --- a/channels/dreamsub.py +++ b/channels/dreamsub.py @@ -68,13 +68,24 @@ def newest(categoria): def peliculas(item): +#<<<<<<< newScrape +#<<<<<<< stable +# itemlist = scrape(item, r'Lingua[^<]+<br>\s*<a href="(?:Lista episodi )?([^"]+)" title="(?:Lista episodi )?(.*?)(?: \(([0-9]+)\))?(?: Streaming)?">', ['url', 'title', 'year'], action='episodios', patron_block='<input type="submit" value="Vai!" class="blueButton">(.*?)<div class="footer">', patronNext='<li class="currentPage">[^>]+><li[^<]+<a href="([^"]+)">') +# renumber(itemlist) +# return itemlist +#======= +# itemlist = scrape(item, r'Lingua[^<]+<br>\s*<a href="(?:Lista episodi )?([^"]+)" title="(?:Lista episodi )?(.*?)(?: \(([0-9]+)\))?(?: Streaming)?">', ['url', 'title', 'year'], action='episodios', patronBlock='<input type="submit" value="Vai!" class="blueButton">(.*?)<div class="footer">', patronNext='<li class="currentPage">[^>]+><li[^<]+<a href="([^"]+)">') +# return renumber(itemlist) +#>>>>>>> newScrape +#======= itemlist = scrape(item, r'Lingua[^<]+<br>\s*<a href="(?:Lista episodi )?([^"]+)" title="(?:Lista episodi )?(.*?)(?: \(([0-9]+)\))?(?: Streaming)?">', ['url', 'title', 'year'], action='episodios', patron_block='<input type="submit" value="Vai!" class="blueButton">(.*?)<div class="footer">', patronNext='<li class="currentPage">[^>]+><li[^<]+<a href="([^"]+)">') renumber(itemlist) return itemlist +#>>>>>>> master def last(item): - return scrape(item, r'<li><a href="([^"]+)"[^>]+>([^<]+)(\d+)<br>', ['url', 'title', 'episode'], patron_block='<ul class="last" id="recentAddedEpisodesAnimeDDM">(.*?)</ul>' ) + return scrape(item, r'<li><a href="([^"]+)"[^>]+>([^<]+)(\d+)<br>', ['url', 'title', 'episode'], patronBlock='<ul class="last" id="recentAddedEpisodesAnimeDDM">(.*?)</ul>' ) def categorie(item): @@ -94,9 +105,20 @@ def categorie(item): def episodios(item): +#<<<<<<< newScrape +#<<<<<<< stable +# itemlist = scrape(item, r'<li><a href="([^"]+)"[^<]+<b>(.*?)<\/b>[^>]+>([^<]+)<\/i>', ['url','title','title2'], patron_block='<div class="seasonEp">(.*?)<div class="footer">') +# renumber(itemlist, item, 'bold') +# return itemlist +#======= +# itemlist = scrape(item, r'<li><a href="([^"]+)"[^<]+<b>(.*?)<\/b>[^>]+>([^<]+)<\/i>', ['url','title','title2'], patronBlock='<div class="seasonEp">(.*?)<div class="footer">') +# return renumber(itemlist, item, 'bold') +#>>>>>>> newScrape +#======= itemlist = scrape(item, r'<li><a href="([^"]+)"[^<]+<b>(.*?)<\/b>[^>]+>([^<]+)<\/i>', ['url','title','title2'], patron_block='<div class="seasonEp">(.*?)<div class="footer">') renumber(itemlist, item, 'bold') return itemlist +#>>>>>>> master def findvideos(item): log() diff --git a/channels/eurostreaming.json b/channels/eurostreaming.json index 3fb5ddf3..f884880f 100644 --- a/channels/eurostreaming.json +++ b/channels/eurostreaming.json @@ -4,15 +4,15 @@ "active": true, "adult": false, "language": ["ita"], - "thumbnail": "https://eurostreaming.cafe/wp-content/uploads/2017/08/logocafe.png", - "bannermenu": "https://eurostreaming.cafe/wp-content/uploads/2017/08/logocafe.png", + "thumbnail": "https://eurostreaming.pink/wp-content/uploads/2017/08/logocafe.png", + "bannermenu": "https://eurostreaming.pink/wp-content/uploads/2017/08/logocafe.png", "categories": ["tvshow","anime","vosi"], "settings": [ { "id": "channel_host", "type": "text", "label": "Host del canale", - "default": "https://eurostreaming.cafe", + "default": "https://eurostreaming.pink", "enabled": true, "visible": true }, @@ -40,6 +40,23 @@ "enabled": true, "visible": true }, + { + "id": "checklinks", + "type": "bool", + "label": "Verifica se i link esistono", + "default": false, + "enabled": true, + "visible": true + }, + { + "id": "checklinks_number", + "type": "list", + "label": "Numero di link da verificare", + "default": 1, + "enabled": true, + "visible": "eq(-1,true)", + "lvalues": [ "5", "10", "15", "20" ] + }, { "id": "filter_languages", "type": "list", diff --git a/channels/eurostreaming.py b/channels/eurostreaming.py index 817cbf45..4f5ce537 100644 --- a/channels/eurostreaming.py +++ b/channels/eurostreaming.py @@ -4,22 +4,15 @@ # by Greko # ------------------------------------------------------------ """ - Riscritto per poter usufruire del modulo support. + Riscritto per poter usufruire del decoratore support.scrape Problemi noti: - Le regex non prendono tutto... - server versystream : 'http://vcrypt.net/very/' # VeryS non decodifica il link :http://vcrypt.net/fastshield/ - alcuni server tra cui nowvideo.club non sono implementati nella cartella servers Alcune sezioni di anime-cartoni non vanno, alcune hanno solo la lista degli episodi, ma non hanno link altre cambiano la struttura - La sezione novità non fa apparire il titolo degli episodi - - In episodios è stata aggiunta la possibilità di configurare la videoteca - """ -import channelselector -from specials import autoplay, filtertools -from core import scrapertoolsV2, httptools, servertools, tmdb, support +#import channelselector +#from specials import autoplay#, filtertools +from core import scrapertoolsV2, httptools, support#, servertools, tmdb from core.item import Item from platformcode import logger, config @@ -30,8 +23,8 @@ headers = ['Referer', host] list_servers = ['verystream', 'wstream', 'speedvideo', 'flashx', 'nowvideo', 'streamango', 'deltabit', 'openload'] list_quality = ['default'] -__comprueba_enlaces__ = config.get_setting('comprueba_enlaces', 'eurostreaming') -__comprueba_enlaces_num__ = config.get_setting('comprueba_enlaces_num', 'eurostreaming') +checklinks = config.get_setting('checklinks', 'cineblog01') +checklinks_number = config.get_setting('checklinks_number', 'cineblog01') IDIOMAS = {'Italiano': 'ITA', 'Sub-ITA':'vosi'} list_language = IDIOMAS.values() @@ -48,39 +41,46 @@ def mainlist(item): support.menu(itemlist, 'Cerca...', 'search', host, contentType = 'tvshow') ## itemlist = filtertools.show_option(itemlist, item.channel, list_language, list_quality) - # richiesto per autoplay - autoplay.init(item.channel, list_servers, list_quality) - autoplay.show_option(item.channel, itemlist) - + # autoplay + support.aplay(item, itemlist, list_servers, list_quality) + # configurazione canale support.channel_config(item, itemlist) - + return itemlist +@support.scrape def serietv(item): - #import web_pdb; web_pdb.set_trace() - # lista serie tv +## import web_pdb; web_pdb.set_trace() support.log() itemlist = [] if item.args: - # il titolo degli episodi viene inglobato in episode ma non sono visibili in newest!!! - patron = r'<span class="serieTitle" style="font-size:20px">(.*?).[^–]<a href="([^"]+)"\s+target="_blank">(.*?)<\/a>' - listGroups = ['title', 'url', 'title2'] + #patron = r'<span class="serieTitle" style="font-size:20px">(.*?).[^–]<a href="([^"]+)"\s+target="_blank">(.*?)<\/a>' +## # DA SISTEMARE - problema: mette tutti gli episodi in sub-ita +## patron = r'<span class="serieTitle" style="font-size:20px">(.*?).[^–]<a href="([^"]+)"'\ +## '\s+target="_blank">(\d+x\d+) (.*?)(?:|\((.+?)\))</a>' + patron = r'<span class="serieTitle" style="font-size:20px">(.*?).[^–]<a href="([^"]+)"'\ + '\s+target="_blank">(\d+x\d+) (.*?)</a>' + listGroups = ['title', 'url', 'episode', 'title2'] patronNext = '' + + # permette di vedere episodio e titolo + titolo2 in novità + def itemHook(item): + item.show = item.episode + item.title + return item else: patron = r'<div class="post-thumb">.*?\s<img src="([^"]+)".*?><a href="([^"]+)".*?>(.*?(?:\((\d{4})\)|(\d{4}))?)<\/a><\/h2>' listGroups = ['thumb', 'url', 'title', 'year', 'year'] patronNext='a class="next page-numbers" href="?([^>"]+)">Avanti »</a>' + action='episodios' + + return locals() - itemlist = support.scrape(item, patron_block='', patron=patron, listGroups=listGroups, - patronNext=patronNext, action='episodios') - return itemlist - - +@support.scrape def episodios(item): ## import web_pdb; web_pdb.set_trace() - support.log("episodios") + support.log("episodios: %s" % item) itemlist = [] - + item.contentType = 'episode' # Carica la pagina data = httptools.downloadpage(item.url).data #======== @@ -97,46 +97,17 @@ def episodios(item): patron = r'(?:<\/span>\w+ STAGIONE\s\d+ (?:\()?(ITA|SUB ITA)(?:\))?<\/div>'\ '<div class="su-spoiler-content su-clearfix" style="display:none">|'\ '(?:\s|\Wn)?(?:<strong>)?(\d+&#.*?)(?:|–)?<a\s(.*?)<\/a><br\s\/>)' -## '(?:<\/span>\w+ STAGIONE\s\d+ (?:\()?(ITA|SUB ITA)(?:\))?'\ -## '<\/div><div class="su-spoiler-content su-clearfix" style="display:none">|'\ -## '(?:\s|\Wn)?(?:<strong>)?(\d[&#].*?)(?:–|\W)?<a\s(.*?)<\/a><br\s\/>)' -## '(?:<\/span>\w+ STAGIONE\s\d+ (?:\()?(ITA|SUB ITA)(?:\))?<\/div>'\ -## '<div class="su-spoiler-content su-clearfix" style="display:none">|'\ -## '\s(?:<strong>)?(\d[&#].*?)–<a\s(.*?)<\/a><br\s\/>)' - listGroups = ['lang', 'title', 'url'] - itemlist = support.scrape(item, data=data, patron=patron, - listGroups=listGroups, action='findvideos') - # Permette la configurazione della videoteca senza andare nel menu apposito - # così si possono Attivare/Disattivare le impostazioni direttamente dalla - # pagina delle puntate - itemlist.append( - Item(channel='setting', - action="channel_config", - title=support.typo("Configurazione Videoteca color lime"), - plot = 'Filtra per lingua utilizzando la configurazione della videoteca.\ - Escludi i video in sub attivando "Escludi streams... " e aggiungendo sub in Parole', - config='videolibrary', #item.channel, - folder=False, - thumbnail=channelselector.get_thumb('setting_0.png') - )) + listGroups = ['lang', 'title', 'url'] + action = 'findvideos' - itemlist = filtertools.get_links(itemlist, item, list_language) - return itemlist + return locals() # =========== def findvideos ============= def findvideos(item): - support.log() - itemlist =[] - - # Requerido para FilterTools -## itemlist = filtertools.get_links(itemlist, item, list_language) - - itemlist = support.server(item, item.url) -## support.videolibrary(itemlist, item) - - return itemlist + support.log('findvideos', item) + return support.server(item, item.url) # =========== def ricerca ============= def search(item, texto): @@ -174,6 +145,3 @@ def newest(categoria): return [] return itemlist - -def paginator(item): - pass diff --git a/channels/fastsubita.py b/channels/fastsubita.py index bc7e1c5e..e054e58f 100644 --- a/channels/fastsubita.py +++ b/channels/fastsubita.py @@ -208,13 +208,13 @@ def findvideos(item): itemlist = [] # data = httptools.downloadpage(item.url, headers=headers).data - patron_block = '<div class="entry-content">(.*?)<footer class="entry-footer">' - # bloque = scrapertools.find_single_match(data, patron_block) + patronBlock = '<div class="entry-content">(.*?)<footer class="entry-footer">' + # bloque = scrapertools.find_single_match(data, patronBlock) patron = r'<a href="([^"]+)">' # matches = re.compile(patron, re.DOTALL).findall(bloque) - matches, data = support.match(item, patron, patron_block, headers) + matches, data = support.match(item, patron, patronBlock, headers) for scrapedurl in matches: if 'is.gd' in scrapedurl: diff --git a/channels/guardaserieclick.py b/channels/guardaserieclick.py index e6ad4ef9..ae701c86 100644 --- a/channels/guardaserieclick.py +++ b/channels/guardaserieclick.py @@ -4,15 +4,18 @@ # Thanks to Icarus crew & Alfa addon & 4l3x87 # ------------------------------------------------------------ -import re +""" + Problemi noti: + - nella pagina categorie appaiono i risultati di tmdb in alcune voci +""" -from core import httptools, scrapertools, support -from core import tmdb +from core import scrapertoolsV2, httptools, support from core.item import Item -from core.support import log from platformcode import logger, config +from core.support import log __channel__ = 'guardaserieclick' + host = config.get_channel_url(__channel__) headers = [['Referer', host]] @@ -30,34 +33,154 @@ def mainlist(item): itemlist = [] - 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']) + support.menu(itemlist, 'Serie', 'serietv', "%s/lista-serie-tv" % host, 'tvshow', args=['news']) + support.menu(itemlist, 'Ultimi Aggiornamenti submenu', 'serietv', "%s/lista-serie-tv" % host, 'tvshow', args= ['update']) + support.menu(itemlist, 'Categorie', 'categorie', host, 'tvshow', args=['cat']) + support.menu(itemlist, 'Serie inedite Sub-ITA submenu', 'serietv', "%s/lista-serie-tv" % host, 'tvshow', args=['inedite']) + support.menu(itemlist, 'Da non perdere bold submenu', 'serietv', "%s/lista-serie-tv" % host, 'tvshow', args=['tv', 'da non perdere']) + support.menu(itemlist, 'Classiche bold submenu', 'serietv', "%s/lista-serie-tv" % host, 'tvshow', args=['tv', 'classiche']) + support.menu(itemlist, 'Disegni che si muovono sullo schermo per magia bold', 'tvserie', "%s/category/animazione/" % host, 'tvshow', args= ['anime']) + support.menu(itemlist, 'Cerca', 'search', host, 'tvshow', args=['cerca']) + + # autoplay support.aplay(item, itemlist, list_servers, list_quality) + # configurazione del canale support.channel_config(item, itemlist) return itemlist +@support.scrape +def serietv(item): +## import web_pdb; web_pdb.set_trace() + log('serietv ->\n') +##<<<<<<< HEAD +## +## action = 'episodios' +## listGroups = ['url', 'thumb', 'title'] +## patron = r'<a href="([^"]+)".*?> <img\s.*?src="([^"]+)" \/>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<\/p>' +## if 'news' in item.args: +## patronBlock = r'<div class="container container-title-serie-new container-scheda" meta-slug="new">(.*?)</div></div><div' +## elif 'inedite' in item.args: +## patronBlock = r'<div class="container container-title-serie-ined container-scheda" meta-slug="ined">(.*?)</div></div><div' +## elif 'da non perdere' in item.args: +## patronBlock = r'<div class="container container-title-serie-danonperd container-scheda" meta-slug="danonperd">(.*?)</div></div><div' +## elif 'classiche' in item.args: +## patronBlock = r'<div class="container container-title-serie-classiche container-scheda" meta-slug="classiche">(.*?)</div></div><div' +## elif 'update' in item.args: +## listGroups = ['url', 'thumb', 'episode', 'lang', 'title'] +## patron = r'rel="nofollow" href="([^"]+)"[^>]+> <img.*?src="([^"]+)"[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>(\d+.\d+) \((.+?)\).<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>' +## patronBlock = r'meta-slug="lastep">(.*?)</div></div><div' +## # permette di vedere episodio + titolo + titolo2 in novità +## def itemHook(item): +## item.show = item.episode + item.title +## return item +## return locals() +## +##@support.scrape +##def tvserie(item): +## +## action = 'episodios' +## listGroups = ['url', 'thumb', 'title'] +## patron = r'<a\shref="([^"]+)".*?>\s<img\s.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p></div>' +## patronBlock = r'<div\sclass="col-xs-\d+ col-sm-\d+-\d+">(.*?)<div\sclass="container-fluid whitebg" style="">' +## patronNext = r'<link\s.*?rel="next"\shref="([^"]+)"' +## +## return locals() +## +##@support.scrape +##def episodios(item): +## log('episodios ->\n') +## item.contentType = 'episode' +## +## action = 'findvideos' +## listGroups = ['episode', 'lang', 'title2', 'plot', 'title', 'url'] +## patron = r'class="number-episodes-on-img"> (\d+.\d+)(?:|[ ]\((.*?)\))<[^>]+>'\ +## '[^>]+>[^>]+>[^>]+>[^>]+>(.*?)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>'\ +## '(.*?)<[^>]+></div></div>.<span\s.+?meta-serie="(.*?)" meta-stag=(.*?)</span>' +## +## return locals() +## +##======= + + action = 'episodios' + listGroups = ['url', 'thumb', 'title'] + patron = r'<a href="([^"]+)".*?> <img\s.*?src="([^"]+)" \/>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<\/p>' + if 'news' in item.args: + patron_block = r'<div class="container container-title-serie-new container-scheda" meta-slug="new">(.*?)</div></div><div' + elif 'inedite' in item.args: + patron_block = r'<div class="container container-title-serie-ined container-scheda" meta-slug="ined">(.*?)</div></div><div' + elif 'da non perdere' in item.args: + patron_block = r'<div class="container container-title-serie-danonperd container-scheda" meta-slug="danonperd">(.*?)</div></div><div' + elif 'classiche' in item.args: + patron_block = r'<div class="container container-title-serie-classiche container-scheda" meta-slug="classiche">(.*?)</div></div><div' + elif 'update' in item.args: + listGroups = ['url', 'thumb', 'episode', 'lang', 'title'] + patron = r'rel="nofollow" href="([^"]+)"[^>]+> <img.*?src="([^"]+)"[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>(\d+.\d+) \((.+?)\).<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>' + patron_block = r'meta-slug="lastep">(.*?)</div></div><div' + # permette di vedere episodio + titolo + titolo2 in novità + def itemHook(item): + item.show = item.episode + item.title + return item + return locals() + +@support.scrape +def tvserie(item): + + action = 'episodios' + listGroups = ['url', 'thumb', 'title'] + patron = r'<a\shref="([^"]+)".*?>\s<img\s.*?src="([^"]+)" />[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)</p></div>' + patron_block = r'<div\sclass="col-xs-\d+ col-sm-\d+-\d+">(.*?)<div\sclass="container-fluid whitebg" style="">' + patronNext = r'<link\s.*?rel="next"\shref="([^"]+)"' + + return locals() + +@support.scrape +def episodios(item): + log('episodios ->\n') + item.contentType = 'episode' + + action = 'findvideos' + listGroups = ['episode', 'lang', 'title2', 'plot', 'title', 'url'] + patron = r'class="number-episodes-on-img"> (\d+.\d+)(?:|[ ]\((.*?)\))<[^>]+>'\ + '[^>]+>[^>]+>[^>]+>[^>]+>(.*?)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>'\ + '(.*?)<[^>]+></div></div>.<span\s.+?meta-serie="(.*?)" meta-stag=(.*?)</span>' + + return locals() + +##>>>>>>> a72130e0324ae485ae5f39d3d8f1df46c365fa5b +def findvideos(item): + log() + return support.server(item, item.url) + +@support.scrape +def categorie(item): + log + + action = 'tvserie' + listGroups = ['url', 'title'] + patron = r'<li>\s<a\shref="([^"]+)"[^>]+>([^<]+)</a></li>' + + patron_block = r'<ul\sclass="dropdown-menu category">(.*?)</ul>' + + + return locals() # ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- +## +### ---------------------------------------------------------------------------------------------------------------- def newest(categoria): log() itemlist = [] item = Item() + item.contentType= 'episode' + item.args = 'update' try: if categoria == "series": item.url = "%s/lista-serie-tv" % host - item.action = "serietvaggiornate" - itemlist = serietvaggiornate(item) + item.action = "serietv" + itemlist = serietv(item) - if itemlist[-1].action == "serietvaggiornate": + if itemlist[-1].action == "serietv": itemlist.pop() # Continua la ricerca in caso di errore @@ -69,207 +192,18 @@ def newest(categoria): return itemlist +### ================================================================================================================ +### ---------------------------------------------------------------------------------------------------------------- -# ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- def search(item, texto): log(texto) item.url = host + "/?s=" + texto + item.args = 'cerca' try: - return lista_serie(item) + return tvserie(item) # Continua la ricerca in caso di errore except: import sys for line in sys.exc_info(): logger.error("%s" % line) return [] - - -# ================================================================================================================ -# ---------------------------------------------------------------------------------------------------------------- -def cleantitle(scrapedtitle): - scrapedtitle = scrapertools.decodeHtmlentities(scrapedtitle.strip()).replace('"', "'") - return scrapedtitle.strip() - - -# ================================================================================================================ -# ---------------------------------------------------------------------------------------------------------------- - -def nuoveserie(item): - log() - itemlist = [] - - patron_block = '' - if 'inedite' in item.args: - patron_block = r'<div class="container container-title-serie-ined container-scheda" meta-slug="ined">(.*?)</div></div><div' - elif 'da non perdere' in item.args: - patron_block = r'<div class="container container-title-serie-danonperd container-scheda" meta-slug="danonperd">(.*?)</div></div><div' - elif 'classiche' in item.args: - patron_block = r'<div class="container container-title-serie-classiche container-scheda" meta-slug="classiche">(.*?)</div></div><div' - else: - patron_block = r'<div class="container container-title-serie-new container-scheda" meta-slug="new">(.*?)</div></div><div' - - patron = r'<a href="([^"]+)".*?><img\s.*?src="([^"]+)" \/>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<\/p>' - - matches = support.match(item, patron, patron_block, headers)[0] - - for scrapedurl, scrapedthumbnail, scrapedtitle in matches: - scrapedtitle = cleantitle(scrapedtitle) - - itemlist.append( - Item(channel=item.channel, - action="episodios", - contentType="tvshow", - title=scrapedtitle, - fulltitle=scrapedtitle, - url=scrapedurl, - show=scrapedtitle, - thumbnail=scrapedthumbnail, - folder=True)) - - tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True) - return itemlist - - -# ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- -def serietvaggiornate(item): - log() - itemlist = [] - - patron_block = r'<div class="container\s*container-title-serie-lastep\s*container-scheda" meta-slug="lastep">(.*?)<\/div><\/div><div' - patron = r'<a rel="nofollow"\s*href="([^"]+)"[^>]+><img.*?src="([^"]+)"[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)<[^>]+>' - - matches = support.match(item, patron, patron_block, headers)[0] - - for scrapedurl, scrapedthumbnail, scrapedep, scrapedtitle in matches: - episode = re.compile(r'^(\d+)x(\d+)', re.DOTALL).findall(scrapedep) # Prendo stagione ed episodioso - scrapedtitle = cleantitle(scrapedtitle) - - contentlanguage = "" - if 'sub-ita' in scrapedep.strip().lower(): - contentlanguage = 'Sub-ITA' - - extra = r'<span\s.*?meta-stag="%s" meta-ep="%s" meta-embed="([^"]+)"\s.*?embed2="([^"]+)?"\s.*?embed3="([^"]+)?"[^>]*>' % ( - episode[0][0], episode[0][1].lstrip("0")) - - infoLabels = {} - infoLabels['episode'] = episode[0][1].zfill(2) - infoLabels['season'] = episode[0][0] - - title = str( - "%s - %sx%s %s" % (scrapedtitle, infoLabels['season'], infoLabels['episode'], contentlanguage)).strip() - - itemlist.append( - Item(channel=item.channel, - action="findepvideos", - contentType="tvshow", - title=title, - show=scrapedtitle, - fulltitle=scrapedtitle, - url=scrapedurl, - extra=extra, - thumbnail=scrapedthumbnail, - contentLanguage=contentlanguage, - infoLabels=infoLabels, - folder=True)) - - tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True) - - return itemlist - - -# ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- -def categorie(item): - log() - 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") - - -# ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- -def lista_serie(item): - log() - itemlist = [] - - 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>' - - return support.scrape(item, patron, ['url', 'thumb', 'title'], patron_block=patron_block, patronNext=r"<link\s.*?rel='next'\shref='([^']*)'", action='episodios') - - -# ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- -def episodios(item): - log() - itemlist = [] - - patron = r'<div\sclass="[^"]+">\s([^<]+)<\/div>[^>]+>[^>]+>[^>]+>[^>]+>([^<]+)?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+><p[^>]+>([^<]+)<[^>]+>[^>]+>[^>]+>' - patron += r'[^"]+".*?serie="([^"]+)".*?stag="([0-9]*)".*?ep="([0-9]*)"\s' - patron += r'.*?embed="([^"]+)"\s.*?embed2="([^"]+)?"\s.*?embed3="([^"]+)?"?[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>\s?' - patron += r'(?:<img\sclass="[^"]+" meta-src="([^"]+)"[^>]+>|<img\sclass="[^"]+" src="" data-original="([^"]+)"[^>]+>)?' - - matches = support.match(item, patron, headers=headers)[0] - - for scrapedtitle, scrapedepisodetitle, scrapedplot, scrapedserie, scrapedseason, scrapedepisode, scrapedurl, scrapedurl2, scrapedurl3, scrapedthumbnail, scrapedthumbnail2 in matches: - scrapedtitle = cleantitle(scrapedtitle) - scrapedepisode = scrapedepisode.zfill(2) - scrapedepisodetitle = cleantitle(scrapedepisodetitle) - title = str("%sx%s %s" % (scrapedseason, scrapedepisode, scrapedepisodetitle)).strip() - if 'SUB-ITA' in scrapedtitle: - title += " "+support.typo("Sub-ITA", '_ [] color kod') - - infoLabels = {} - infoLabels['season'] = scrapedseason - infoLabels['episode'] = scrapedepisode - itemlist.append( - Item(channel=item.channel, - action="findvideos", - title=support.typo(title, 'bold'), - fulltitle=scrapedtitle, - url=scrapedurl + "\r\n" + scrapedurl2 + "\r\n" + scrapedurl3, - contentType="episode", - plot=scrapedplot, - contentSerieName=scrapedserie, - contentLanguage='Sub-ITA' if 'Sub-ITA' in title else '', - infoLabels=infoLabels, - thumbnail=scrapedthumbnail2 if scrapedthumbnail2 != '' else scrapedthumbnail, - folder=True)) - - tmdb.set_infoLabels_itemlist(itemlist, seekTmdb=True) - - support.videolibrary(itemlist, item) - - return itemlist - - -# ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- -def findepvideos(item): - log() - data = httptools.downloadpage(item.url, headers=headers, ignore_response_code=True).data - matches = scrapertools.find_multiple_matches(data, item.extra) - data = "\r\n".join(matches[0]) - item.contentType = 'movie' - return support.server(item, data=data) - - -# ================================================================================================================ - -# ---------------------------------------------------------------------------------------------------------------- -def findvideos(item): - log() - if item.contentType == 'tvshow': - data = httptools.downloadpage(item.url, headers=headers).data - matches = scrapertools.find_multiple_matches(data, item.extra) - data = "\r\n".join(matches[0]) - else: - log(item.url) - data = item.url - return support.server(item, data) diff --git a/channels/ilgeniodellostreaming.py b/channels/ilgeniodellostreaming.py index 972a7c0b..aa28bd9b 100644 --- a/channels/ilgeniodellostreaming.py +++ b/channels/ilgeniodellostreaming.py @@ -70,7 +70,7 @@ def newest(categoria): def category(item): - return support.scrape(item, r'<li.*?><a href="(.*?)"[^>]+>(.*?)<\/a>' ,['url', 'title'], action='peliculas', patron_block= r'<ul class="' + item.args + r' scrolling">(.*?)<\/ul>') + return support.scrape(item, r'<li.*?><a href="(.*?)"[^>]+>(.*?)<\/a>' ,['url', 'title'], action='peliculas', patronBlock= r'<ul class="' + item.args + r' scrolling">(.*?)<\/ul>') def search(item, texto): @@ -90,7 +90,7 @@ def search(item, texto): def peliculas_src(item): patron = r'<div class="thumbnail animation-2"><a href="([^"]+)"><img src="([^"]+)" alt="[^"]+" \/>[^>]+>([^<]+)<\/span>.*?<a href.*?>([^<]+)<\/a>[^>]+>[^>]+>(?:<span class="rating">IMDb\s*([0-9.]+)<\/span>)?.*?(?:<span class="year">([0-9]+)<\/span>)?[^>]+>[^>]+><p>(.*?)<\/p>' - return support.scrape(item, patron, ['url', 'thumb', 'type', 'title', 'lang' 'rating', 'year', 'plot'], headers, type_content_dict={'movie':['Film'], 'tvshow':['TV']}, type_action_dict={'findvideos':['Film'], 'episodios':['TV']}) + return support.scrape(item, patron, ['url', 'thumb', 'type', 'title', 'lang' 'rating', 'year', 'plot'], headers, typeContentDict={'movie':['Film'], 'tvshow':['TV']}, typeActionDict={'findvideos':['Film'], 'episodios':['TV']}) def peliculas(item): @@ -102,7 +102,7 @@ def peliculas(item): return support.scrape(item, patron, ['url', 'thumb', 'rating', 'title', 'year', 'plot'], headers, action='episodios', patronNext='<span class="current">[^<]+<[^>]+><a href="([^"]+)"') else: patron = r'<div class="thumbnail animation-2"><a href="([^"]+)"><img src="([^"]+)" alt="[^"]+" \/>[^>]+>([^<]+)<\/span>.*?<a href.*?>([^<]+)<\/a>[^>]+>[^>]+>(?:<span class="rating">IMDb\s*([0-9.]+)<\/span>)?.*?(?:<span class="year">([0-9]+)<\/span>)?[^>]+>[^>]+><p>(.*?)<\/p>' - return support.scrape(item, patron, ['url', 'thumb', 'type', 'title', 'lang' 'rating', 'year', 'plot'], headers, type_content_dict={'movie':['Film'], 'tvshow':['TV']}, type_action_dict={'findvideos':['Film'], 'episodios':['TV']}) + return support.scrape(item, patron, ['url', 'thumb', 'type', 'title', 'lang' 'rating', 'year', 'plot'], headers, typeContentDict={'movie':['Film'], 'tvshow':['TV']}, typeActionDict={'findvideos':['Film'], 'episodios':['TV']}) def newep(item): log() @@ -132,7 +132,7 @@ def newep(item): return itemlist def episodios(item): - return support.scrape(item, r'<a href="([^"]+)"><img src="([^"]+)">.*?<div class="numerando">([^<]+).*?<div class="episodiotitle">[^>]+>([^<]+)<\/a>',['url', 'thumb', 'episode', 'title'], patron_block='<div id="seasons">(.*?)<div class="sbox') + return support.scrape(item, r'<a href="([^"]+)"><img src="([^"]+)">.*?<div class="numerando">([^<]+).*?<div class="episodiotitle">[^>]+>([^<]+)<\/a>',['url', 'thumb', 'episode', 'title'], patronBlock='<div id="seasons">(.*?)<div class="sbox') def findvideos(item): log() diff --git a/channels/serietvu.py b/channels/serietvu.py index 0a9bbc2d..24b6d70d 100644 --- a/channels/serietvu.py +++ b/channels/serietvu.py @@ -150,9 +150,9 @@ def findvideos(item): def findepisodevideo(item): log() - patron_block = r'<div class="list [active]*" data-id="%s">(.*?)</div>\s*</div>' % item.extra[0][0] + patronBlock = r'<div class="list [active]*" data-id="%s">(.*?)</div>\s*</div>' % item.extra[0][0] patron = r'<a data-id="%s[^"]*" data-href="([^"]+)"(?:\sdata-original="[^"]+")?\sclass="[^"]+">' % item.extra[0][1].lstrip("0") - matches = support.match(item, patron, patron_block, headers)[0] + matches = support.match(item, patron, patronBlock, headers)[0] data = '' if len(matches) > 0: data = matches[0] @@ -169,9 +169,9 @@ def latestep(item): itemlist = [] titles = [] - patron_block = r"Ultimi episodi aggiunti.*?<h2>" + patronBlock = r"Ultimi episodi aggiunti.*?<h2>" patron = r'<a href="([^"]*)"\sdata-src="([^"]*)"\sclass="owl-lazy.*?".*?class="title">(.*?)<small>\((\d*?)x(\d*?)\s(Sub-Ita|Ita)' - matches = support.match(item, patron, patron_block, headers, host)[0] + matches = support.match(item, patron, patronBlock, headers, host)[0] for scrapedurl, scrapedimg, scrapedtitle, scrapedseason, scrapedepisode, scrapedlanguage in matches: infoLabels = {} @@ -296,8 +296,8 @@ def search(item, texto): # ---------------------------------------------------------------------------------------------------------------- def categorie(item): log() - patron_block= r'<h2>Sfoglia</h2>\s*<ul>(.*?)</ul>\s*</section>' + patronBlock= r'<h2>Sfoglia</h2>\s*<ul>(.*?)</ul>\s*</section>' patron = r'<li><a href="([^"]+)">([^<]+)</a></li>' - return support.scrape(item, patron, ['url','title'], patron_block=patron_block, action='lista_serie', blacklist=["Home Page", "Calendario Aggiornamenti"]) + return support.scrape(item, patron, ['url','title'], patronBlock=patronBlock, action='lista_serie', blacklist=["Home Page", "Calendario Aggiornamenti"]) # ================================================================================================================ diff --git a/channels/streamingaltadefinizione.py b/channels/streamingaltadefinizione.py index 0406e670..58040a99 100644 --- a/channels/streamingaltadefinizione.py +++ b/channels/streamingaltadefinizione.py @@ -41,7 +41,7 @@ def search(item, text): def generos(item): patron = '<a href="([^"#]+)">([a-zA-Z]+)' - return support.scrape(item, patron, ['url', 'title'], patron_block='<a href="#">Genere</a><ul class="sub-menu">.*?</ul>', action='peliculas') + return support.scrape(item, patron, ['url', 'title'], patronBlock='<a href="#">Genere</a><ul class="sub-menu">.*?</ul>', action='peliculas') def peliculas(item): diff --git a/channels/streamking.json b/channels/streamking.json deleted file mode 100644 index df0eba59..00000000 --- a/channels/streamking.json +++ /dev/null @@ -1,10 +0,0 @@ -{ - "id": "streamking", - "name": "Stream King", - "language": ["ita"], - "active": true, - "adult": false, - "thumbnail": "http://streamking.cc/assets/img/logon.png", - "banner": "", - "categories": ["sport"] -} \ No newline at end of file diff --git a/channels/streamking.py b/channels/streamking.py deleted file mode 100644 index 729ad9d9..00000000 --- a/channels/streamking.py +++ /dev/null @@ -1,58 +0,0 @@ -# -*- coding: utf-8 -*- -# ------------------------------------------------------------ -# Canale per Stream King **** TEST **** -# Alhaziel -# ------------------------------------------------------------ - -import re -import urllib - -from core import scrapertools, httptools -from core.item import Item -from platformcode import logger -from platformcode import config - -__channel__ = "streamking" -host = config.get_channel_url(__channel__) - -headers = [['Referer', host]] - -def mainlist(item): - logger.info("[streamking] canali") - itemlist = [] - - data = httptools.downloadpage(host, headers=headers).data.replace('\n','') - patron = '<div class="tv-block">.*?<a href="([^"]+)".*?src="([^"]+)".*?title="([^"]+)"' - matches = re.compile(patron, re.DOTALL).findall(data) - - for scrapedurl, scrapedthumbnail, scrapedtitle in matches: - url = host + scrapedurl - thumb = host + scrapedthumbnail - scrapedtitle = scrapertools.decodeHtmlentities(scrapedtitle) - itemlist.append( - Item(channel=item.channel, - action="findvideos", - contentTitle=scrapedtitle, - title=scrapedtitle, - fulltitle=scrapedtitle, - url=url, - thumbnail=thumb)) - - return itemlist - -def findvideos(item): - logger.info("[streamking] findvideos") - itemlist = [] - - data = httptools.downloadpage(item.url, headers=headers).data.replace('\n','') - iframe = scrapertools.find_single_match(data, '<iframe src="([^"]+)"') - data = httptools.downloadpage(iframe, headers=headers).data - m3u8 = scrapertools.find_single_match(data, "file: '([^']+)'") - - itemlist.append( - Item(channel=item.channel, - action="play", - title=item.title + 'Play', - url=m3u8 + '|' + urllib.urlencode(dict(headers)) - )) - return itemlist \ No newline at end of file diff --git a/channels/tantifilm.py b/channels/tantifilm.py index 0a285bc5..b59fb2b4 100644 --- a/channels/tantifilm.py +++ b/channels/tantifilm.py @@ -123,7 +123,7 @@ def search_peliculas(item): def category(item): blacklist = ['Serie TV Altadefinizione', 'HD AltaDefinizione', 'Al Cinema', 'Serie TV', 'Miniserie', 'Programmi Tv', 'Live', 'Trailers', 'Serie TV Aggiornate', 'Aggiornamenti', 'Featured'] - itemlist = support.scrape(item, '<li><a href="([^"]+)"><span></span>([^<]+)</a></li>', ['url', 'title'], headers, blacklist, patron_block='<ul class="table-list">(.*?)</ul>', action='peliculas') + itemlist = support.scrape(item, '<li><a href="([^"]+)"><span></span>([^<]+)</a></li>', ['url', 'title'], headers, blacklist, patronBlock='<ul class="table-list">(.*?)</ul>', action='peliculas') return support.thumb(itemlist) @@ -132,7 +132,7 @@ def peliculas(item): action = 'findvideos' if item.extra == 'movie' else 'episodios' if item.args == 'movie': patron= r'<div class="mediaWrap mediaWrapAlt">[^<]+<a href="([^"]+)" title="Permalink to\s([^"]+) \(([^<]+)\).*?"[^>]+>[^<]+<img[^s]+src="([^"]+)"[^>]+>[^<]+<\/a>.*?<p>\s*([a-zA-Z-0-9]+)\s*<\/p>' - itemlist = support.scrape(item, patron, ['url', 'title', 'year', 'thumb', 'quality'], headers, action=action, patron_block='<div id="main_col">(.*?)main_col', patronNext='<a class="nextpostslink" rel="next" href="([^"]+)">') + itemlist = support.scrape(item, patron, ['url', 'title', 'year', 'thumb', 'quality'], headers, action=action, patronBlock='<div id="main_col">(.*?)main_col', patronNext='<a class="nextpostslink" rel="next" href="([^"]+)">') else: patron = r'<div class="media3">[^>]+><a href="([^"]+)"><img[^s]+src="([^"]+)"[^>]+><\/a><[^>]+><a[^<]+><p>([^<]+) \(([^\)]+)[^<]+<\/p>.*?<p>\s*([a-zA-Z-0-9]+)\s*<\/p>' itemlist = support.scrape(item, patron, ['url', 'thumb', 'title', 'year', 'quality'], headers, action=action, patronNext='<a class="nextpostslink" rel="next" href="([^"]+)">') diff --git a/channels/vedohd.py b/channels/vedohd.py index bb536728..fc5c4856 100644 --- a/channels/vedohd.py +++ b/channels/vedohd.py @@ -100,13 +100,13 @@ def findvideos(item): def generos(item): findhost() patron = '<a href="([^"#]+)">([a-zA-Z]+)' - return support.scrape(item, patron, ['url', 'title'], patron_block='<a href="#">Genere</a><ul class="sub-menu">.*?</ul>', action='peliculas') + return support.scrape(item, patron, ['url', 'title'], patronBlock='<a href="#">Genere</a><ul class="sub-menu">.*?</ul>', action='peliculas') def year(item): findhost() patron = r'<a href="([^"#]+)">(\d+)' - return support.scrape(item, patron, ['url', 'title'], patron_block='<a href="#">Anno</a><ul class="sub-menu">.*?</ul>', action='peliculas') + return support.scrape(item, patron, ['url', 'title'], patronBlock='<a href="#">Anno</a><ul class="sub-menu">.*?</ul>', action='peliculas') def play(item): diff --git a/core/scrapertoolsV2.py b/core/scrapertoolsV2.py index 9fa26d28..a8e5b163 100644 --- a/core/scrapertoolsV2.py +++ b/core/scrapertoolsV2.py @@ -32,6 +32,11 @@ def find_multiple_matches(text, pattern): return re.findall(pattern, text, re.DOTALL) +def find_multiple_matches_groups(text, pattern): + r = re.compile(pattern) + return [m.groupdict() for m in r.finditer(text)] + + # 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})(;?)") diff --git a/core/support.py b/core/support.py index ee2326d8..21313ff4 100644 --- a/core/support.py +++ b/core/support.py @@ -92,172 +92,202 @@ def url_decode(url_enc): def color(text, color): return "[COLOR " + color + "]" + text + "[/COLOR]" - -def scrape(item, patron = '', listGroups = [], headers="", blacklist="", data="", patron_block="", - patronNext="", action="findvideos", addVideolibrary = True, type_content_dict={}, type_action_dict={}): +def scrape(func): + # args is a dict containing the foolowing keys: # 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 + # headers: 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), + # patronBlock: 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 + # addVideolibrary: if "add to videolibrary" should appear # 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'], + # return support.scrape(item, itemlist, patron, ['thumb', 'quality', 'url', 'title', '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={} + # IMPORTANT 'type' is a special key, to work need typeContentDict={} and typeActionDict={} - itemlist = [] + def wrapper(*args): + 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) + args = func(*args) - block = data + item = args['item'] - if patron_block: - if type(patron_block) == str: - patron_block = [patron_block] + action = args['action'] if 'action' in args else 'findvideos' + anime = args['anime'] if 'anime' in args else '' + addVideolibrary = args['addVideolibrary'] if 'addVideolibrary' in args else True + blacklist = args['blacklist'] if 'blacklist' in args else '' + data = args['data'] if 'data' in args else '' + headers = args['headers'] if 'headers' in args else '' + patron = args['patron'] if 'patron' in args else '' + patronNext = args['patronNext'] if 'patronNext' in args else '' + patronBlock = args['patronBlock'] if 'patronBlock' in args else '' + typeActionDict = args['type_action_dict'] if 'type_action_dict' in args else {} + typeContentDict = args['type_content_dict'] if 'type_content_dict' in args else {} - 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) + 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) - 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))) + block = data - 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 patronBlock: + if type(patronBlock) == str: + patronBlock = [patronBlock] - 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'] == '': #altrimenti nei canali dei film mi aggiunge sub-ita a tutti i film successivi - lang = '' # o in alternativa lang = 'ITA' - 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) + for n, regex in enumerate(patronBlock): + blocks = scrapertoolsV2.find_multiple_matches(block, regex) + block = "" + for b in blocks: + block += "\n" + str(b) + log('BLOCK ', n, '=', block) else: - for it in itemlist: - it.infoLabels = item.infoLabels + block = data + if patron: + matches = scrapertoolsV2.find_multiple_matches_groups(block, patron) + log('MATCHES =', matches) - if patronNext: - nextPage(itemlist, item, data, patronNext, 2) + 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: + listGroups = match.keys() + match = match.values() - if addVideolibrary and (item.infoLabels["title"] or item.fulltitle): - item.fulltitle = item.infoLabels["title"] - videolibrary(itemlist, item) + if len(listGroups) > len(match): # to fix a bug + match = list(match) + match.extend([''] * (len(listGroups) - len(match))) - return itemlist + 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('"',"'")).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 title is set, probably this is a list of episodes or video sources + if item.infoLabels["title"] or item.fulltitle: + 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 typeContentDict: + for name, variants in typeContentDict.items(): + if scraped['type'] in variants: + item.contentType = name + if typeActionDict: + for name, variants in typeActionDict.items(): + if scraped['type'] in variants: + action = name + + if scraped["title"] not in blacklist: + it = Item( + channel=item.channel, + action=action, + contentType=item.contentType, + title=longtitle, + fulltitle=title, + show=title, + 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)]) + + if 'itemHook' in args: + it = args['itemHook'](it) + itemlist.append(it) + checkHost(item, itemlist) +## if (item.contentType == "episode" and (action != "findvideos" and action != "play")) \ +## or (item.contentType == "movie" and action != "play"): + 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 'itemlistHook' in args: + itemlist = args['itemlistHook'](itemlist) + + if patronNext: + nextPage(itemlist, item, data, patronNext, 2) + + if anime: + from specials import autorenumber + autorenumber.renumber(itemlist) + + if addVideolibrary and (item.infoLabels["title"] or item.fulltitle): + item.fulltitle = item.infoLabels["title"] + videolibrary(itemlist, item) + + if 'fullItemlistHook' in args: + itemlist = args['fullItemlistHook'](itemlist) + + return itemlist + + return wrapper def checkHost(item, itemlist): @@ -398,13 +428,9 @@ def swzz_get_url(item): return data -def menu(itemlist, title='', action='', url='', contentType='movie', args=[]): +def menuItem(itemlist, filename, title='', action='', url='', contentType='movie', args=[]): # Function to simplify menu creation - frame = inspect.stack()[1] - filename = frame[0].f_code.co_filename - filename = os.path.basename(filename).replace('.py','') - # Call typo function title = typo(title) @@ -428,6 +454,51 @@ def menu(itemlist, title='', action='', url='', contentType='movie', args=[]): return itemlist +def menu(func): + def wrapper(*args): + args = func(*args) + + item = args['item'] + host = func.__globals__['host'] + list_servers = func.__globals__['list_servers'] + list_quality = func.__globals__['list_quality'] + filename = func.__module__.split('.')[1] + + listUrls = ['film', 'filmSub', 'tvshow', 'tvshowSub'] + dictUrl = {} + for name in listUrls: + dictUrl[name] = args[name] if name in args else None + autoplay.init(item.channel, list_servers, list_quality) + + # Main options + itemlist = [] + if dictUrl['film'] is not None: + menuItem(itemlist, filename, 'Film bold', 'peliculas', host + dictUrl['film']) + ### modificato by greko ######## + for sub, var in dictUrl['filmSub']: + menuItem(itemlist, filename, sub + ' submenu', var[1], + host + var[0], + args=var[2] if len(var)>2 else '') + + menuItem(itemlist, filename, 'Cerca submenu bold', 'search', host, args='film') + + if dictUrl['tvshow'] is not None: + menuItem(itemlist, filename, 'Serie TV bold', 'peliculas', host + dictUrl['tvshow'], contentType='tvshow') + + for sub, var in dictUrl['tvshowSub']: + menuItem(itemlist, filename, sub + ' submenu', var[1], + host + var[0], contentType='tvshow', + args=var[2] if len(var)>2 else '') + + menuItem(itemlist, filename, 'Cerca submenu bold', 'search', host, args='serie') + ### fine by greko ######## + autoplay.show_option(item.channel, itemlist) + + return itemlist + + return wrapper + + def typo(string, typography=''): kod_color = '0xFF65B3DA' #'0xFF0081C2' @@ -480,7 +551,7 @@ def typo(string, typography=''): return string -def match(item, patron='', patron_block='', headers='', url=''): +def match(item, patron='', patronBlock='', headers='', url=''): matches = [] url = url if url else item.url data = httptools.downloadpage(url, headers=headers, ignore_response_code=True).data.replace("'", '"') @@ -488,8 +559,8 @@ def match(item, patron='', patron_block='', headers='', url=''): data = re.sub(r'>\s\s*<', '><', data) log('DATA= ', data) - if patron_block: - block = scrapertoolsV2.find_single_match(data, patron_block) + if patronBlock: + block = scrapertoolsV2.find_single_match(data, patronBlock) log('BLOCK= ',block) else: block = data @@ -546,7 +617,8 @@ def nextPage(itemlist, item, data='', patron='', function_level=1, next_page='', log('NEXT= ', next_page) itemlist.append( Item(channel=item.channel, - action=inspect.stack()[function_level][3], + #action=inspect.stack()[function_level][3], + action = item.action, contentType=item.contentType, title=typo(config.get_localized_string(30992), 'color kod bold'), url=next_page, @@ -648,5 +720,4 @@ def channel_config(item, itemlist): config=item.channel, folder=False, thumbnail=get_thumb('setting_0.png')) - ) - + ) \ No newline at end of file diff --git a/custom_code.json b/custom_code.json new file mode 100644 index 00000000..7e7fd8fc --- /dev/null +++ b/custom_code.json @@ -0,0 +1,3 @@ +{ + "addon_version": "0.4" +} \ No newline at end of file diff --git a/servers/decrypters/zcrypt.py b/servers/decrypters/zcrypt.py index 50e2cb82..0333a6ac 100644 --- a/servers/decrypters/zcrypt.py +++ b/servers/decrypters/zcrypt.py @@ -72,7 +72,7 @@ def get_video_url(page_url, premium=False, user="", password="", video_password= else: logger.info(" url duplicada=" + url) - patron = r"""(https?://(?:www\.)?(?:threadsphere\.bid|adf\.ly|q\.gs|j\.gs|u\.bb|ay\.gy|linkbucks\.com|any\.gs|cash4links\.co|cash4files\.co|dyo\.gs|filesonthe\.net|goneviral\.com|megaline\.co|miniurls\.co|qqc\.co|seriousdeals\.net|theseblogs\.com|theseforums\.com|tinylinks\.co|tubeviral\.com|ultrafiles\.net|urlbeat\.net|whackyvidz\.com|yyv\.co|adfoc\.us|lnx\.lu|sh\.st|href\.li|anonymz\.com|shrink-service\.it|rapidcrypt\.net|ecleneue\.com)/[^"']+)""" + patron = r"""(https?://(?:www\.)?(?:threadsphere\.bid|adf\.ly|q\.gs|j\.gs|u\.bb|ay\.gy|linkbucks\.com|any\.gs|cash4links\.co|cash4files\.co|dyo\.gs|filesonthe\.net|goneviral\.com|megaline\.co|miniurls\.co|qqc\.co|seriousdeals\.net|theseblogs\.com|theseforums\.com|tinylinks\.co|tubeviral\.com|ultrafiles\.net|urlbeat\.net|whackyvidz\.com|yyv\.co|adfoc\.us|lnx\.lu|sh\.st|href\.li|anonymz\.com|shrink-service\.it|rapidcrypt\.net|ecleneue\.com)/[^"']+)"""#|bit\.ly)/[^"']+)""" logger.info(" find_videos #" + patron + "#") matches = re.compile(patron).findall(page_url) diff --git a/specials/check.py b/specials/check.py new file mode 100644 index 00000000..49a79d7e --- /dev/null +++ b/specials/check.py @@ -0,0 +1,175 @@ +# -*- coding: utf-8 -*- +# -*- Scritto per KOD -*- +# versione: 0.1 + +##import sys +##import os +##import json +##import xbmc +##import xbmcaddon, xbmcgui +import kdicc +## +##from core import channeltools, scrapertools +##from platformcode import logger, config, platformtools +##from core.item import Item + + +""" + Abbinato allo script kdicc permette di modificare gli url del file channels_active.json ( poi channels.json ): + 1. riscrivere l'url in caso di redirect + 2. + a. disattivare il canale in caso di problemi al sito + b. riattivare il canale quando l'url viene raggiunto nuovamente + + quando far partire il check? + 1. all'inizio per controllare i file nel channels_not_active (pochi) + 2. durante l'apertura del canale + 3. nelle varie ricerche globali + + Problematiche: + + 1. i redirect sono gestiti in locale + 2. se il canale viene disattivato bisogna scrivere nel json: + a. del canale per disattivarlo + b. inserire il canale nel channels_not_active +""" + +class CheckHost(object): + + def __init__(self): + pass + + def http_code(): + pass + +def checkHost(item, itemlist): + # nel caso non ci siano risultati puo essere che l'utente abbia cambiato manualmente l'host, pertanto lo riporta + # al valore di default (fixa anche il problema del cambio di host da parte nostra) + if len(itemlist) == 0: + # trovo il valore di default + + defHost = None + for s in channeltools.get_channel_json(item.channel)['settings']: + if s['id'] == 'channel_host': + defHost = s['default'] + break + # lo confronto con quello attuale + if config.get_setting('channel_host', item.channel) != defHost: + config.set_setting('channel_host', defHost, item.channel) + +## +##def host_check(itemlist, item=None): +## """ +## se item == None allora siamo nello start() +## +## :param itemlist: +## :param item: +## :return: +## """ +## #import web_pdb; web_pdb.set_trace() +## logger.info("host_check item, itemlist : %s %s " % (item, itemlist)) +## +## if not item: +## logger.info("%s %s " % (item, itemlist)) +## check_host(itemlist = '', item=None) +## else: +## pass +## +## +##def check_host(itemlist, item=None): +## #import web_pdb; web_pdb.set_trace() +## if not item: +## logger.info("ITEM : %s " % (item)) +## channel_path = os.path.join(config.get_runtime_path(), "") +## file = 'channel_not_active.json' +## # leggo dal file channel_not_active +## with open(channel_path+file, 'r') as json_file: +## data = '' +## try: +## data = json.load(json_file) +## logger.info("Json data : %s " % (data)) +## except: +## logger.info("Json except : %s " % (data)) +## if len(data) !=0: +## logger.info("IF len(data) : %s " % len(data)) +## for canale in data: +## url_org = str(data[canale]) +## +## +## # X debug, da togliere +## else: +## logger.info("ELSE len(data) : %s " % len(data)) +## +## else: +## logger.info() +## +## channel_path = os.path.join(config.get_runtime_path(), "") +## file = 'channels.json' +## #logger.info("canale Json data : %s " % canale) +## new_domain = [] +## error_domain = [] +## nonraggiungibile_domain = [] +## code_error = [] +## with open(channel_path+file, 'r') as json_file: +## data = json.load(json_file) +## logger.info("Json data : %s " % (data))#, data['settings'])) +## +## for canale in data: +## url_org = str(data[canale]) +## try: +## res = requests.get(url_org) +## url = str(res.url) +## logger.info("Canale : %s " % canale) +## logger.info("R = %s" % res.status_code) +## logger.info("siamo qui data[canale]: %s " % url_org) # contiene l'url nuovo se c'è link +## logger.info("siamo qui res.url: %s " % url) # contiene l'url nuovo se c'è link +## +## if url.endswith('/') == True: +## url = url[:-1] +## +## logger.info("url_org -> %s" % url_org) +## logger.info("url -> %s" % url) +## logger.info("################") +## +## if url_org != url: +## new_domain.append((canale, url_org, url)) +## if res.status_code == 200: +## pass +## elif res.status_code == 301: +## code_error.append(res.status_code) +## elif str(res.status_code).startswith('5'): +## code_error.append(res.status_code) +## logger.info("res.code 5XX: %s " % res.status_code) +## ## elif res.status_code == +## ## if res.code == 503: +## ## # disabilitare il canale +## ## logger.info("res.code non è 200: %s " % res.code) +## ## error_domain.append((canale, data[canale])) +## ## if res.code == 200 and 'link' in res.headers: +## ## logger.info("res.code è 200 and 'link': %s " % res.code) +## ## host_red = res.headers['link'] +## ## pat = r'<([a-zA-Z0-9-\.\/:]+)/wp-json/>;' +## ## host_red = scrapertools.find_single_match(host_red, pat) +## ## logger.info("host_red: %s " % host_red) +## ## # confronto i 2 link, se non sono uguali c'è un redirect +## ## if host_red != data[canale]: +## ## logger.info("host_red host_link: %s - %s " % (host_red, data[canale])) +## ## new_domain.append((canale, host_red)) +## ## logger.info("data modificato link: %s " % canale) +## ## +## ## logger.info("fuori dagli if': %s " % res.code) +## except requests.RequestException as e: +## """ +## Il sito risulta non raggiungibile per qualche motivo +## quindi verrà disabilitato +## """ +## logger.info("DICT: %s " % dict(error=e.message)) +## logger.info("Canale : %s " % canale) +## logger.info("siti non raggiungibili: %s %s" % (url_org, res.status_code)) +## logger.info("################") +## nonraggiungibile_domain.append((canale, url_org)) +## +## logger.info("new_domain: %s " % new_domain) +## logger.info("code_error: %s " % code_error) +## logger.info("error_domain: %s " % error_domain) +## logger.info("nonraggiungibile_domain: %s " % nonraggiungibile_domain)