# -*- coding: utf-8 -*- import re import sys import urllib import urlparse from channelselector import get_thumb from core import httptools from core import scrapertools from core import servertools from core.item import Item from platformcode import config, logger from core import tmdb host = 'http://mispelisyseries.com/' def mainlist(item): logger.info() itemlist = [] thumb_pelis = get_thumb("channels_movie.png") thumb_pelis_hd = get_thumb("channels_movie_hd.png") thumb_series = get_thumb("channels_tvshow.png") thumb_series_hd = get_thumb("channels_tvshow_hd.png") thumb_series_az = get_thumb("channels_tvshow_az.png") thumb_docus = get_thumb("channels_documentary.png") thumb_buscar = get_thumb("search.png") thumb_settings = get_thumb("setting_0.png") itemlist.append(Item(channel=item.channel, action="submenu", title="Películas", url=host, extra="peliculas", thumbnail=thumb_pelis )) itemlist.append(Item(channel=item.channel, action="submenu", title="Series", url=host, extra="series", thumbnail=thumb_series)) itemlist.append(Item(channel=item.channel, action="submenu", title="Documentales", url=host, extra="varios", thumbnail=thumb_docus)) itemlist.append( Item(channel=item.channel, action="search", title="Buscar", url=host + "buscar", thumbnail=thumb_buscar)) itemlist.append( Item(channel=item.channel, action="", title="[COLOR yellow]Configuración de Servidores:[/COLOR]", url="", thumbnail=thumb_settings)) itemlist.append( Item(channel=item.channel, action="settingCanal", title="Servidores para Ver Online y Descargas", url="", thumbnail=thumb_settings)) return itemlist def settingCanal(item): from platformcode import platformtools return platformtools.show_channel_settings() def submenu(item): logger.info() itemlist = [] data = re.sub(r"\n|\r|\t|\s{2}|()", "", httptools.downloadpage(item.url).data) data = unicode(data, "iso-8859-1", errors="replace").encode("utf-8") data = data.replace("'", '"').replace('/series"', '/series/"') #Compatibilidad con mispelisy.series.com host_dom = host.replace("https://", "").replace("http://", "").replace("www.", "") patron = '
  • .*?(.*?)' if "pelisyseries.com" in host and item.extra == "varios": #compatibilidad con mispelisy.series.com data = ' Documentales' else: if data: data = scrapertools.get_match(data, patron) else: return itemlist patron = '<.*?href="([^"]+)".*?>([^>]+)' matches = re.compile(patron, re.DOTALL).findall(data) for scrapedurl, scrapedtitle in matches: title = scrapedtitle.strip() url = scrapedurl itemlist.append(Item(channel=item.channel, action="listado", title=title, url=url, extra=item.extra)) itemlist.append( Item(channel=item.channel, action="alfabeto", title=title + " [A-Z]", url=url, extra=item.extra)) if item.extra == "peliculas": itemlist.append(Item(channel=item.channel, action="listado", title="Películas 4K", url=host + "peliculas-hd/4kultrahd/", extra=item.extra)) itemlist.append( Item(channel=item.channel, action="alfabeto", title="Películas 4K" + " [A-Z]", url=host + "peliculas-hd/4kultrahd/", extra=item.extra)) return itemlist def alfabeto(item): logger.info() itemlist = [] data = re.sub(r"\n|\r|\t|\s{2}|()", "", httptools.downloadpage(item.url).data) data = unicode(data, "iso-8859-1", errors="replace").encode("utf-8") patron = '' if data: data = scrapertools.get_match(data, patron) else: return itemlist patron = ']+>([^>]+)' matches = re.compile(patron, re.DOTALL).findall(data) for scrapedurl, scrapedtitle in matches: title = scrapedtitle.upper() url = scrapedurl itemlist.append(Item(channel=item.channel, action="listado", title=title, url=url, extra=item.extra)) return itemlist def listado(item): logger.info() itemlist = [] clase = "pelilist" # etiqueta para localizar zona de listado de contenidos url_next_page ='' # Controlde paginación cnt_tot = 30 # Poner el num. máximo de items por página category = "" # Guarda la categoria que viene desde una busqueda global if item.category: category = item.category del item.category if item.totalItems: del item.totalItems data = re.sub(r"\n|\r|\t|\s{2}|()", "", httptools.downloadpage(item.url).data) #Establecemos los valores básicos en función del tipo de contenido if item.extra == "peliculas": item.action = "findvideos" item.contentType = "movie" pag = True #Sí hay paginación elif item.extra == "series" and not "/miniseries" in item.url: item.action = "episodios" item.contentType = "tvshow" pag = True elif item.extra == "varios" or "/miniseries" in item.url: item.action = "findvideos" item.contentType = "movie" pag = True #Selecciona el tramo de la página con el listado de contenidos patron = '' if data: fichas = scrapertools.get_match(data, patron) else: return itemlist page_extra = clase #Scrapea los datos de cada vídeo. Título alternativo se mantiene, aunque no se usa de momento patron = 'Last<\/a><\/li>') if not item.post_num: post_num = 1 else: post_num = int(item.post_num) + 1 if not total_pag: total_pag = 1 #Calcula las páginas del canal por cada página de la web total_pag = int(total_pag) * int((float(len(matches))/float(cnt_tot)) + 0.999999) # Preparamos la paginación. if not item.cnt_pag: cnt_pag = 0 else: cnt_pag = item.cnt_pag del item.cnt_pag matches_cnt = len(matches) if item.next_page != 'b': if matches_cnt > cnt_pag + cnt_tot: url_next_page = item.url matches = matches[cnt_pag:cnt_pag+cnt_tot] next_page = '' if matches_cnt <= cnt_pag + (cnt_tot * 2): if pag: next_page = 'b' modo = 'continue' else: matches = matches[cnt_pag:cnt_pag+cnt_tot] next_page = 'a' patron_next_page = 'Next<\/a>' matches_next_page = re.compile(patron_next_page, re.DOTALL).findall(data) modo = 'continue' if len(matches_next_page) > 0: url_next_page = urlparse.urljoin(item.url, matches_next_page[0]) modo = 'next' # Avanzamos el contador de líneas en una página if item.next_page: del item.next_page if modo == 'next': cnt_pag = 0 else: cnt_pag += cnt_tot #Tratamos todos los contenidos, creardo una variable local de Item for scrapedurl, scrapedtitle, scrapedthumbnail, title_alt, calidad in matches: item_local = item.clone() if item_local.tipo: del item_local.tipo if item_local.totalItems: del item_local.totalItems if item.post_num: del item.post_num item_local.title = '' item_local.context = "['buscar_trailer']" # Limpiamos títulos, Sacamos datos de calidad, audio y lenguaje title = re.sub('\r\n', '', scrapedtitle).decode('iso-8859-1').encode('utf8').strip() title_alt = re.sub('\r\n', '', title_alt).decode('iso-8859-1').encode('utf8').strip() title = title.replace("á", "a").replace("é", "e").replace("í", "i").replace("ó", "o").replace("ú", "u").replace("ü", "u").replace("�", "ñ").replace("ñ", "ñ").replace(".", " ") title_alt = title_alt.replace("á", "a").replace("é", "e").replace("í", "i").replace("ó", "o").replace("ú", "u").replace("ü", "u").replace("�", "ñ").replace("ñ", "ñ") item_local.quality = calidad title_subs = [] #Determinamos y marcamos idiomas distintos del castellano item_local.language = [] if "[vos" in title.lower() or "v.o.s" in title.lower() or "vo" in title.lower() or ".com/pelicula/" in scrapedurl or ".com/series-vo" in scrapedurl or "-vo/" in scrapedurl or "vos" in calidad.lower() or "vose" in calidad.lower() or "v.o.s" in calidad.lower() or "sub" in calidad.lower() or ".com/peliculas-vo" in item.url: item_local.language += ["VOS"] title = title.replace(" [Subs. integrados]", "").replace(" [subs. Integrados]", "").replace(" [VOSE", "").replace(" [VOS", "").replace(" (V.O.S.E)", "").replace(" VO", "").replace("Subtitulos", "") if "latino" in title.lower() or "argentina" in title.lower() or "-latino/" in scrapedurl or "latino" in calidad.lower() or "argentina" in calidad.lower(): item_local.language += ["LAT"] #Guardamos info de 3D en calidad y limpiamos if "3d" in title.lower(): if not "3d" in item_local.quality.lower(): item_local.quality = item_local.quality + " 3D" calidad3D = scrapertools.find_single_match(title, r'\s(3[d|D]\s\w+)') if calidad3D: item_local.quality = item_local.quality.replace("3D", calidad3D) title = re.sub(r'\s3[d|D]\s\w+', '', title) title = re.sub(r'\s3[d|D]', '', title) title_alt = re.sub(r'\s3[d|D]\s\w+', '', title_alt) title_alt = re.sub(r'\s3[d|D]', '', title_alt) if "imax" in title.lower(): item_local.quality = item_local.quality + " IMAX" title = title.replace(" IMAX", "").replace(" imax", "") title_alt = title_alt.replace(" IMAX", "").replace(" imax", "") if "2d" in title.lower(): title = title.replace("(2D)", "").replace("(2d)", "").replace("2D", "").replace("2d", "") title_subs += ["[2D]"] #Extraemos info adicional del título y la guardamos para después de TMDB if "temp" in title.lower() or "cap" in title.lower(): #Eliminamos Temporada, solo nos interesa la serie completa title = re.sub(r' - [t|T]emp\w+ \d+x\d+', '', title) title = re.sub(r' - [t|T]emp\w+ \d+', '', title) title = re.sub(r' - [t|T]emp\w+.*?\d+', '', title) title = re.sub(r' [t|T]emp.*?\d+x\d+', '', title) title = re.sub(r' [t|T]emp.*?\d+', '', title) title = re.sub(r' [c|C]ap.*?\d+', '', title) if "audio" in title.lower(): #Reservamos info de audio para después de TMDB title_subs += ['[%s]' % scrapertools.find_single_match(title, r'(\[[a|A]udio.*?\])')] title = re.sub(r'\[[a|A]udio.*?\]', '', title) if "[dual" in title.lower() or "multileng" in title.lower() or "multileng" in item_local.quality.lower() or (("espa" in title.lower() or "spani" in title.lower()) and "VOS" in item_local.language): item_local.language[0:0] = ["DUAL"] title = re.sub(r'\[[D|d]ual.*?\]', '', title) title = re.sub(r'\[[M|m]ultileng.*?\]', '', title) item_local.quality = re.sub(r'\[[M|m]ultileng.*?\]', '', item_local.quality) if "duolog" in title.lower(): title_subs += ["[Saga]"] title = title.replace(" Duologia", "").replace(" duologia", "").replace(" Duolog", "").replace(" duolog", "") if "trilog" in title.lower(): title_subs += ["[Saga]"] title = title.replace(" Trilogia", "").replace(" trilogia", "").replace(" Trilog", "").replace(" trilog", "") if "extendida" in title.lower(): title_subs += ["[V. Extendida]"] title = title.replace(" Version Extendida", "").replace(" (Version Extendida)", "").replace(" V. Extendida", "").replace(" VExtendida", "").replace(" V Extendida", "") if "saga" in title.lower(): title = title.replace(" Saga Completa", "").replace(" saga sompleta", "").replace(" Saga", "").replace(" saga", "") title_subs += ["[Saga]"] if "colecc" in title.lower() or "completa" in title.lower(): title = title.replace(" Coleccion", "").replace(" coleccion", "").replace(" Colecci", "").replace(" colecci", "").replace(" Completa", "").replace(" completa", "").replace(" COMPLETA", "") if scrapertools.find_single_match(title, r'(- [m|M].*?serie ?\w+)'): title = re.sub(r'- [m|M].*?serie ?\w+', '', title) title_subs += ["[Miniserie]"] #Limpiamos restos en título title = title.replace("Castellano", "").replace("castellano", "").replace("inglés", "").replace("ingles", "").replace("Inglés", "").replace("Ingles", "").replace("Espa", "").replace("Ingl", "").replace("Engl", "").replace("Calidad", "").replace("de la Serie", "") title_alt = title_alt.replace("Castellano", "").replace("castellano", "").replace("inglés", "").replace("ingles", "").replace("Inglés", "").replace("Ingles", "").replace("Espa", "").replace("Ingl", "").replace("Engl", "").replace("Calidad", "").replace("de la Serie", "") #Limpiamos cabeceras y colas del título title = re.sub(r'Descargar\s\w+\-\w+', '', title) title = re.sub(r'\(COMPLE.*?\)', '', title) title = re.sub(r'\(\d{4}\)$', '', title) title = re.sub(r'\d{4}$', '', title) title = re.sub(r' \d+x\d+', '', title) title = re.sub(r' x\d+', '', title) title = title.replace("Ver online ", "").replace("Descarga Serie HD ", "").replace("Descargar Serie HD ", "").replace("Descarga Serie ", "").replace("Descargar Serie ", "").replace("Ver en linea ", "").replace("Ver en linea", "").replace("HD ", "").replace("(Proper)", "").replace("RatDVD", "").replace("DVDRiP", "").replace("DVDRIP", "").replace("DVDR", "").replace("DVD9", "").replace("DVD", "").replace("DVB", "").replace("- ES ", "").replace("ES ", "").replace("COMPLETA", "").replace("(", "-").replace(")", "-").replace(".", " ").strip() title = title.replace("Descargar torrent ", "").replace("Descarga Gratis ", "").replace("Descargar Estreno ", "").replace("Descargar Estrenos ", "").replace("Pelicula en latino ", "").replace("Descargar Pelicula ", "").replace("Descargar Peliculas ", "").replace("Descargar peliculas ", "").replace("Descargar Todas ", "").replace("Descargar Otras ", "").replace("Descargar ", "").replace("Descarga ", "").replace("Bajar ", "").replace("HDRIP ", "").replace("HDRiP ", "").replace("HDRip ", "").replace("RIP ", "").replace("Rip", "").replace("RiP", "").replace("XviD", "").replace("AC3 5.1", "").replace("AC3", "").replace("1080p ", "").replace("720p ", "").replace("DVD-Screener ", "").replace("TS-Screener ", "").replace("Screener ", "").replace("BdRemux ", "").replace("BR ", "").replace("4KULTRA", "").replace("FULLBluRay", "").replace("FullBluRay", "").replace("BluRay", "").replace("Bonus Disc", "").replace("de Cine ", "").replace("TeleCine ", "").replace("latino", "").replace("Latino", "").replace("argentina", "").replace("Argentina", "").strip() if title.endswith("torrent gratis"): title = title[:-15] if title.endswith("gratis"): title = title[:-7] if title.endswith("torrent"): title = title[:-8] if title.endswith("en HD"): title = title[:-6] if title.endswith(" -"): title = title[:-2] if "en espa" in title: title = title[:-11] item_local.quality = item_local.quality.replace("gratis ", "") if "HDR" in title: title = title.replace(" HDR", "") if not "HDR" in item_local.quality: item_local.quality += " HDR" title = title.strip() title_alt = title_alt.strip() item_local.quality = item_local.quality.strip() if not title: #Usamos solo el title_alt en caso de que no exista el título original title = title_alt if not title: title = "SIN TITULO" #Limpieza final del título y guardado en las variables según su tipo de contenido title = scrapertools.remove_htmltags(title) item_local.title = title if item_local.contentType == "movie": item_local.contentTitle = title else: item_local.contentSerieName = title #Guardamos el resto de variables del vídeo item_local.url = scrapedurl item_local.thumbnail = scrapedthumbnail item_local.contentThumbnail = scrapedthumbnail #Guardamos el año que puede venir en la url, por si luego no hay resultados desde TMDB year = '' if item_local.contentType == "movie": year = scrapertools.find_single_match(scrapedurl, r'(\d{4})') if year >= "1900" and year <= "2040" and year != "2020": title_subs += [year] item_local.infoLabels['year'] = '-' #Guarda la variable temporal que almacena la info adicional del título a ser restaurada después de TMDB item_local.title_subs = title_subs #Agrega el item local a la lista itemlist itemlist.append(item_local.clone()) #Pasamos a TMDB la lista completa Itemlist tmdb.set_infoLabels(itemlist, True) # Pasada para maquillaje de los títulos obtenidos desde TMDB for item_local in itemlist: title = item_local.title #Restauramos la info adicional guarda en la lista title_subs, y la borramos de Item if len(item_local.title_subs) > 0: title += " " for title_subs in item_local.title_subs: if "audio" in title_subs.lower(): title = '%s [%s]' % (title, scrapertools.find_single_match(title_subs, r'[a|A]udio (.*?)')) continue if scrapertools.find_single_match(title_subs, r'(\d{4})'): if not item_local.infoLabels['year'] or item_local.infoLabels['year'] == "-": item_local.infoLabels['year'] = scrapertools.find_single_match(title_subs, r'(\d{4})') continue if not config.get_setting("unify"): #Si Titulos Inteligentes NO seleccionados: title = '%s %s' % (title, title_subs) else: title = '%s -%s-' % (title, title_subs) del item_local.title_subs # Si TMDB no ha encontrado el vídeo limpiamos el año if item_local.infoLabels['year'] == "-": item_local.infoLabels['year'] = '' item_local.infoLabels['aired'] = '' # Preparamos el título para series, con los núm. de temporadas, si las hay if item_local.contentType == "season" or item_local.contentType == "tvshow": item_local.contentTitle= '' rating = '' if item_local.infoLabels['rating'] and item_local.infoLabels['rating'] != '0.0': rating = float(item_local.infoLabels['rating']) rating = round(rating, 1) #Ahora maquillamos un poco los titulos dependiendo de si se han seleccionado títulos inteleigentes o no if not config.get_setting("unify"): #Si Titulos Inteligentes NO seleccionados: if item_local.contentType == "season" or item_local.contentType == "tvshow": title = '%s [COLOR yellow][%s][/COLOR] [%s] [COLOR limegreen][%s][/COLOR] [COLOR red]%s[/COLOR]' % (title, scrapertools.find_single_match(str(item_local.infoLabels['aired']), r'\/(\d{4})'), rating, item_local.quality, str(item_local.language)) elif item_local.contentType == "movie": title = '%s [COLOR yellow][%s][/COLOR] [%s] [COLOR limegreen][%s][/COLOR] [COLOR red]%s[/COLOR]' % (title, str(item_local.infoLabels['year']), rating, item_local.quality, str(item_local.language)) if config.get_setting("unify"): #Si Titulos Inteligentes SÍ seleccionados: title = title.replace("[", "-").replace("]", "-") title = title.replace("--", "").replace(" []", "").replace("()", "").replace("(/)", "").replace("[/]", "").strip() title = re.sub(r'\s\[COLOR \w+\]\[\[?\]?\]\[\/COLOR\]', '', title).strip() title = re.sub(r'\s\[COLOR \w+\]\[\/COLOR\]', '', title).strip() if category == "newest": #Viene de Novedades. Marquemos el título con el nombre del canal title += ' -%s-' % item_local.channel.capitalize() if item_local.contentType == "movie": item_local.contentTitle += ' -%s-' % item_local.channel.capitalize() item_local.title = title logger.debug("url: " + item_local.url + " / title: " + item_local.title + " / content title: " + item_local.contentTitle + "/" + item_local.contentSerieName + " / calidad: " + item_local.quality + " / year: " + str(item_local.infoLabels['year'])) #logger.debug(item_local) if len(itemlist) == 0: itemlist.append(Item(channel=item.channel, action="mainlist", title="No se ha podido cargar el listado")) else: if url_next_page: itemlist.append( Item(channel=item.channel, action="listado", title="[COLOR gold][B]Pagina siguiente >> [/B][/COLOR]" + str(post_num) + " de " + str(total_pag), url=url_next_page, next_page=next_page, cnt_pag=cnt_pag, post_num=post_num, pag=pag, modo=modo, extra=item.extra)) #logger.debug(url_next_page + " / " + next_page + " / " + str(matches_cnt) + " / " + str(cnt_pag)+ " / " + str(total_pag) + " / " + str(pag) + " / " + modo + " / " + item.extra) return itemlist def listado_busqueda(item): logger.info() itemlist = [] cnt_tot = 40 # Poner el num. máximo de items por página. Dejamos que la web lo controle cnt_title = 0 # Contador de líneas insertadas en Itemlist cnt_pag = 0 # Contador de líneas leídas de Matches if item.cnt_pag: cnt_pag = item.cnt_pag # Se guarda en la lista de páginas anteriores en Item del item.cnt_pag if item.totalItems: del item.totalItems if item.text_bold: del item.text_bold if item.text_color: del item.text_color #Sistema de paginado para evitar páginas vacías o semi-vacías en casos de búsquedas con series con muchos episodios title_lista = [] # Guarda la lista de series que ya están en Itemlist, para no duplicar lineas if item.title_lista: # Si viene de una pasada anterior, la lista ya estará guardada title_lista = item.title_lista # Se usa la lista de páginas anteriores en Item title_lista_alt = [] for url in title_lista: title_lista_alt += [url] #hacemos una copia no vinculada de title_lista matches = [] cnt_next = 0 total_pag = 1 post_num = 1 #Máximo num. de líneas permitidas por TMDB. Máx de 5 páginas por Itemlist para no degradar el rendimiento while cnt_title <= cnt_tot and cnt_next < 5: data = re.sub(r"\n|\r|\t|\s{2,}", "", httptools.downloadpage(item.url, post=item.post).data) cnt_next += 1 if not data: #Si la web está caída salimos sin dar error return itemlist #Obtiene la dirección de la próxima página, si la hay try: post_actual = item.post #Guardamos el post actual por si hay overflow de Itemlist y hay que hechar marcha atrás get, post, total_pag = scrapertools.find_single_match(data, '