From fc5fb473dd7e9d0590dc1492b9415cdeafc5327c Mon Sep 17 00:00:00 2001 From: Kingbox <37674310+lopezvg@users.noreply.github.com> Date: Mon, 9 Apr 2018 15:51:09 +0200 Subject: [PATCH] Clones de Newpct1: mejora estabilidad en Episodios MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Evita el error de los canales cuando llega una Serie con títulos de capítulos con formatos distintos de los previstos. En este caso crea un formáto de título básico para que prosiga el programa de la forma prevista. --- plugin.video.alfa/channels/descargas2020.py | 38 +++++++++++------- plugin.video.alfa/channels/mispelisyseries.py | 40 ++++++++++++------- plugin.video.alfa/channels/torrentlocura.py | 38 +++++++++++------- plugin.video.alfa/channels/torrentrapid.py | 38 +++++++++++------- plugin.video.alfa/channels/tumejortorrent.py | 40 ++++++++++++------- plugin.video.alfa/channels/tvsinpagar.py | 40 ++++++++++++------- 6 files changed, 147 insertions(+), 87 deletions(-) diff --git a/plugin.video.alfa/channels/descargas2020.py b/plugin.video.alfa/channels/descargas2020.py index 7de30a6b..4008919a 100644 --- a/plugin.video.alfa/channels/descargas2020.py +++ b/plugin.video.alfa/channels/descargas2020.py @@ -133,7 +133,8 @@ def listado(item): for scrapedurl, scrapedtitle, scrapedthumbnail, title_alt, calidad in matches: url = scrapedurl - title = scrapedtitle + title = scrapedtitle.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") + title_alt = title_alt.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") thumbnail = scrapedthumbnail action = "findvideos" extra = "" @@ -209,10 +210,11 @@ def listado_busqueda(item): for url, thumb, title in matches: real_title = scrapertools.find_single_match(title, r'(.*?)Temporada.*?<\/strong>') #series - if real_title == "": + if not real_title: real_title = scrapertools.find_single_match(title, r'(.*?)\[.*?]') #movies real_title = scrapertools.remove_htmltags(real_title).decode('iso-8859-1').encode('utf-8') real_title = scrapertools.htmlclean(real_title) + real_title = real_title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") calidad = scrapertools.find_single_match(title, r'.*?\s*Calidad.*?]+>[\[]\s*(?P.*?)\s*[\]]<\/span>') #series if calidad == "": calidad = scrapertools.find_single_match(title, r'..*?(\[.*?.*\])') #movies @@ -220,9 +222,8 @@ def listado_busqueda(item): # fix encoding for title title = scrapertools.htmlclean(title) - title = title.replace("�", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng") title = re.sub(r'(Calidad.*?\])', '', title) - + title = title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") if real_title == "": real_title = title if calidad == "": @@ -236,18 +237,22 @@ def listado_busqueda(item): # Codigo para rescatar lo que se puede en pelisy.series.com de Series para la Videoteca. la URL apunta al capítulo y no a la Serie. Nombre de Serie frecuentemente en blanco. Se obtiene de Thumb, así como el id de la serie if ("/serie" in url or "-serie" in url) and "pelisyseries.com" in host: - calidad_mps = "series/" if "seriehd" in url: calidad_mps = "series-hd/" - if "serievo" in url: + elif "serievo" in url: calidad_mps = "series-vo/" - if "serie-vo" in url: + elif "serie-vo" in url: calidad_mps = "series-vo/" + else: + calidad_mps = "series/" - real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) - real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) + if "no_image" in thumb: + real_title_mps = title + else: + real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) + real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) - if "/0_" not in thumb: + if "/0_" not in thumb and not "no_image" in thumb: serieid = scrapertools.find_single_match(thumb, r'.*?\/\w\/(?P\d+).*?.*') if len(serieid) > 5: serieid = "" @@ -507,6 +512,11 @@ def episodios(item): "[\[]\s*(?P.*?)?\s*[\]]<\/span>" if "Especial" in info: # Capitulos Especiales pattern = ".*?[^>]+>.*?Temporada.*?\[.*?(?P\d+).*?\].*?Capitulo.*?\[\s*(?P\d+).*?\]?(?:.*?(?P\d+)?)<.+?]+>(?P.*?)?<\/span>\s*Calidad\s*]+>[\[]\s*(?P.*?)?\s*[\]]<\/span>" + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioNEW: " + pattern) + logger.debug(info) + info = '>%sTemporada %s Capitulo 0 - Español Castellano Calidad [%s]' % (item.contentTitle, season, item.infoLabels['quality']) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] @@ -540,11 +550,11 @@ def episodios(item): "(?P\d{2}))?.*?\].*?(?:\[(?P.*?)\])?" elif scrapertools.find_single_match(info, 'Cap.\d{2,3}'): pattern = ".*?Temp.*?\s(?P.*?)\s.*?Cap.(?P\d).*?(?P\d{2})(?:_(?P\d+)(?P\d{2}))?.*?\s(?P.*)?" - else: - logger.debug("patron episodio: " + pattern) + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioOLD: " + pattern) logger.debug(info) - continue - + info = '%s [%s][Cap.%s00][Español]' % (item.contentTitle, item.infoLabels['quality'], season) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] diff --git a/plugin.video.alfa/channels/mispelisyseries.py b/plugin.video.alfa/channels/mispelisyseries.py index f58462a8..7c6ae65b 100644 --- a/plugin.video.alfa/channels/mispelisyseries.py +++ b/plugin.video.alfa/channels/mispelisyseries.py @@ -10,7 +10,7 @@ from core.item import Item from platformcode import config, logger from core import tmdb -host = 'http://www.mispelisyseries.com/' +host = 'http://mispelisyseries.com/' def mainlist(item): logger.info() @@ -133,7 +133,8 @@ def listado(item): for scrapedurl, scrapedtitle, scrapedthumbnail, title_alt, calidad in matches: url = scrapedurl - title = scrapedtitle + title = scrapedtitle.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") + title_alt = title_alt.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") thumbnail = scrapedthumbnail action = "findvideos" extra = "" @@ -209,10 +210,11 @@ def listado_busqueda(item): for url, thumb, title in matches: real_title = scrapertools.find_single_match(title, r'(.*?)Temporada.*?<\/strong>') #series - if real_title == "": + if not real_title: real_title = scrapertools.find_single_match(title, r'(.*?)\[.*?]') #movies real_title = scrapertools.remove_htmltags(real_title).decode('iso-8859-1').encode('utf-8') real_title = scrapertools.htmlclean(real_title) + real_title = real_title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") calidad = scrapertools.find_single_match(title, r'.*?\s*Calidad.*?]+>[\[]\s*(?P.*?)\s*[\]]<\/span>') #series if calidad == "": calidad = scrapertools.find_single_match(title, r'..*?(\[.*?.*\])') #movies @@ -220,9 +222,8 @@ def listado_busqueda(item): # fix encoding for title title = scrapertools.htmlclean(title) - title = title.replace("�", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng") title = re.sub(r'(Calidad.*?\])', '', title) - + title = title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") if real_title == "": real_title = title if calidad == "": @@ -236,18 +237,22 @@ def listado_busqueda(item): # Codigo para rescatar lo que se puede en pelisy.series.com de Series para la Videoteca. la URL apunta al capítulo y no a la Serie. Nombre de Serie frecuentemente en blanco. Se obtiene de Thumb, así como el id de la serie if ("/serie" in url or "-serie" in url) and "pelisyseries.com" in host: - calidad_mps = "series/" if "seriehd" in url: calidad_mps = "series-hd/" - if "serievo" in url: + elif "serievo" in url: calidad_mps = "series-vo/" - if "serie-vo" in url: + elif "serie-vo" in url: calidad_mps = "series-vo/" + else: + calidad_mps = "series/" - real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) - real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) + if "no_image" in thumb: + real_title_mps = title + else: + real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) + real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) - if "/0_" not in thumb: + if "/0_" not in thumb and not "no_image" in thumb: serieid = scrapertools.find_single_match(thumb, r'.*?\/\w\/(?P\d+).*?.*') if len(serieid) > 5: serieid = "" @@ -507,6 +512,11 @@ def episodios(item): "[\[]\s*(?P.*?)?\s*[\]]<\/span>" if "Especial" in info: # Capitulos Especiales pattern = ".*?[^>]+>.*?Temporada.*?\[.*?(?P\d+).*?\].*?Capitulo.*?\[\s*(?P\d+).*?\]?(?:.*?(?P\d+)?)<.+?]+>(?P.*?)?<\/span>\s*Calidad\s*]+>[\[]\s*(?P.*?)?\s*[\]]<\/span>" + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioNEW: " + pattern) + logger.debug(info) + info = '>%sTemporada %s Capitulo 0 - Español Castellano Calidad [%s]' % (item.contentTitle, season, item.infoLabels['quality']) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] @@ -540,11 +550,11 @@ def episodios(item): "(?P\d{2}))?.*?\].*?(?:\[(?P.*?)\])?" elif scrapertools.find_single_match(info, 'Cap.\d{2,3}'): pattern = ".*?Temp.*?\s(?P.*?)\s.*?Cap.(?P\d).*?(?P\d{2})(?:_(?P\d+)(?P\d{2}))?.*?\s(?P.*)?" - else: - logger.debug("patron episodio: " + pattern) + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioOLD: " + pattern) logger.debug(info) - continue - + info = '%s [%s][Cap.%s00][Español]' % (item.contentTitle, item.infoLabels['quality'], season) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] diff --git a/plugin.video.alfa/channels/torrentlocura.py b/plugin.video.alfa/channels/torrentlocura.py index 2d3d50c6..78ebcfa8 100755 --- a/plugin.video.alfa/channels/torrentlocura.py +++ b/plugin.video.alfa/channels/torrentlocura.py @@ -133,7 +133,8 @@ def listado(item): for scrapedurl, scrapedtitle, scrapedthumbnail, title_alt, calidad in matches: url = scrapedurl - title = scrapedtitle + title = scrapedtitle.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") + title_alt = title_alt.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") thumbnail = scrapedthumbnail action = "findvideos" extra = "" @@ -209,10 +210,11 @@ def listado_busqueda(item): for url, thumb, title in matches: real_title = scrapertools.find_single_match(title, r'(.*?)Temporada.*?<\/strong>') #series - if real_title == "": + if not real_title: real_title = scrapertools.find_single_match(title, r'(.*?)\[.*?]') #movies real_title = scrapertools.remove_htmltags(real_title).decode('iso-8859-1').encode('utf-8') real_title = scrapertools.htmlclean(real_title) + real_title = real_title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") calidad = scrapertools.find_single_match(title, r'.*?\s*Calidad.*?]+>[\[]\s*(?P.*?)\s*[\]]<\/span>') #series if calidad == "": calidad = scrapertools.find_single_match(title, r'..*?(\[.*?.*\])') #movies @@ -220,9 +222,8 @@ def listado_busqueda(item): # fix encoding for title title = scrapertools.htmlclean(title) - title = title.replace("�", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng") title = re.sub(r'(Calidad.*?\])', '', title) - + title = title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") if real_title == "": real_title = title if calidad == "": @@ -236,18 +237,22 @@ def listado_busqueda(item): # Codigo para rescatar lo que se puede en pelisy.series.com de Series para la Videoteca. la URL apunta al capítulo y no a la Serie. Nombre de Serie frecuentemente en blanco. Se obtiene de Thumb, así como el id de la serie if ("/serie" in url or "-serie" in url) and "pelisyseries.com" in host: - calidad_mps = "series/" if "seriehd" in url: calidad_mps = "series-hd/" - if "serievo" in url: + elif "serievo" in url: calidad_mps = "series-vo/" - if "serie-vo" in url: + elif "serie-vo" in url: calidad_mps = "series-vo/" + else: + calidad_mps = "series/" - real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) - real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) + if "no_image" in thumb: + real_title_mps = title + else: + real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) + real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) - if "/0_" not in thumb: + if "/0_" not in thumb and not "no_image" in thumb: serieid = scrapertools.find_single_match(thumb, r'.*?\/\w\/(?P\d+).*?.*') if len(serieid) > 5: serieid = "" @@ -507,6 +512,11 @@ def episodios(item): "[\[]\s*(?P.*?)?\s*[\]]<\/span>" if "Especial" in info: # Capitulos Especiales pattern = ".*?[^>]+>.*?Temporada.*?\[.*?(?P\d+).*?\].*?Capitulo.*?\[\s*(?P\d+).*?\]?(?:.*?(?P\d+)?)<.+?]+>(?P.*?)?<\/span>\s*Calidad\s*]+>[\[]\s*(?P.*?)?\s*[\]]<\/span>" + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioNEW: " + pattern) + logger.debug(info) + info = '>%sTemporada %s Capitulo 0 - Español Castellano Calidad [%s]' % (item.contentTitle, season, item.infoLabels['quality']) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] @@ -540,11 +550,11 @@ def episodios(item): "(?P\d{2}))?.*?\].*?(?:\[(?P.*?)\])?" elif scrapertools.find_single_match(info, 'Cap.\d{2,3}'): pattern = ".*?Temp.*?\s(?P.*?)\s.*?Cap.(?P\d).*?(?P\d{2})(?:_(?P\d+)(?P\d{2}))?.*?\s(?P.*)?" - else: - logger.debug("patron episodio: " + pattern) + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioOLD: " + pattern) logger.debug(info) - continue - + info = '%s [%s][Cap.%s00][Español]' % (item.contentTitle, item.infoLabels['quality'], season) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] diff --git a/plugin.video.alfa/channels/torrentrapid.py b/plugin.video.alfa/channels/torrentrapid.py index 85caf927..17273437 100644 --- a/plugin.video.alfa/channels/torrentrapid.py +++ b/plugin.video.alfa/channels/torrentrapid.py @@ -133,7 +133,8 @@ def listado(item): for scrapedurl, scrapedtitle, scrapedthumbnail, title_alt, calidad in matches: url = scrapedurl - title = scrapedtitle + title = scrapedtitle.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") + title_alt = title_alt.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") thumbnail = scrapedthumbnail action = "findvideos" extra = "" @@ -209,10 +210,11 @@ def listado_busqueda(item): for url, thumb, title in matches: real_title = scrapertools.find_single_match(title, r'(.*?)Temporada.*?<\/strong>') #series - if real_title == "": + if not real_title: real_title = scrapertools.find_single_match(title, r'(.*?)\[.*?]') #movies real_title = scrapertools.remove_htmltags(real_title).decode('iso-8859-1').encode('utf-8') real_title = scrapertools.htmlclean(real_title) + real_title = real_title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") calidad = scrapertools.find_single_match(title, r'.*?\s*Calidad.*?]+>[\[]\s*(?P.*?)\s*[\]]<\/span>') #series if calidad == "": calidad = scrapertools.find_single_match(title, r'..*?(\[.*?.*\])') #movies @@ -220,9 +222,8 @@ def listado_busqueda(item): # fix encoding for title title = scrapertools.htmlclean(title) - title = title.replace("�", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng") title = re.sub(r'(Calidad.*?\])', '', title) - + title = title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") if real_title == "": real_title = title if calidad == "": @@ -236,18 +237,22 @@ def listado_busqueda(item): # Codigo para rescatar lo que se puede en pelisy.series.com de Series para la Videoteca. la URL apunta al capítulo y no a la Serie. Nombre de Serie frecuentemente en blanco. Se obtiene de Thumb, así como el id de la serie if ("/serie" in url or "-serie" in url) and "pelisyseries.com" in host: - calidad_mps = "series/" if "seriehd" in url: calidad_mps = "series-hd/" - if "serievo" in url: + elif "serievo" in url: calidad_mps = "series-vo/" - if "serie-vo" in url: + elif "serie-vo" in url: calidad_mps = "series-vo/" + else: + calidad_mps = "series/" - real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) - real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) + if "no_image" in thumb: + real_title_mps = title + else: + real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) + real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) - if "/0_" not in thumb: + if "/0_" not in thumb and not "no_image" in thumb: serieid = scrapertools.find_single_match(thumb, r'.*?\/\w\/(?P\d+).*?.*') if len(serieid) > 5: serieid = "" @@ -507,6 +512,11 @@ def episodios(item): "[\[]\s*(?P.*?)?\s*[\]]<\/span>" if "Especial" in info: # Capitulos Especiales pattern = ".*?[^>]+>.*?Temporada.*?\[.*?(?P\d+).*?\].*?Capitulo.*?\[\s*(?P\d+).*?\]?(?:.*?(?P\d+)?)<.+?]+>(?P.*?)?<\/span>\s*Calidad\s*]+>[\[]\s*(?P.*?)?\s*[\]]<\/span>" + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioNEW: " + pattern) + logger.debug(info) + info = '>%sTemporada %s Capitulo 0 - Español Castellano Calidad [%s]' % (item.contentTitle, season, item.infoLabels['quality']) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] @@ -540,11 +550,11 @@ def episodios(item): "(?P\d{2}))?.*?\].*?(?:\[(?P.*?)\])?" elif scrapertools.find_single_match(info, 'Cap.\d{2,3}'): pattern = ".*?Temp.*?\s(?P.*?)\s.*?Cap.(?P\d).*?(?P\d{2})(?:_(?P\d+)(?P\d{2}))?.*?\s(?P.*)?" - else: - logger.debug("patron episodio: " + pattern) + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioOLD: " + pattern) logger.debug(info) - continue - + info = '%s [%s][Cap.%s00][Español]' % (item.contentTitle, item.infoLabels['quality'], season) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] diff --git a/plugin.video.alfa/channels/tumejortorrent.py b/plugin.video.alfa/channels/tumejortorrent.py index 3ea77b12..10cf34e5 100644 --- a/plugin.video.alfa/channels/tumejortorrent.py +++ b/plugin.video.alfa/channels/tumejortorrent.py @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- import re @@ -133,7 +133,8 @@ def listado(item): for scrapedurl, scrapedtitle, scrapedthumbnail, title_alt, calidad in matches: url = scrapedurl - title = scrapedtitle + title = scrapedtitle.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") + title_alt = title_alt.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") thumbnail = scrapedthumbnail action = "findvideos" extra = "" @@ -209,10 +210,11 @@ def listado_busqueda(item): for url, thumb, title in matches: real_title = scrapertools.find_single_match(title, r'(.*?)Temporada.*?<\/strong>') #series - if real_title == "": + if not real_title: real_title = scrapertools.find_single_match(title, r'(.*?)\[.*?]') #movies real_title = scrapertools.remove_htmltags(real_title).decode('iso-8859-1').encode('utf-8') real_title = scrapertools.htmlclean(real_title) + real_title = real_title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") calidad = scrapertools.find_single_match(title, r'.*?\s*Calidad.*?]+>[\[]\s*(?P.*?)\s*[\]]<\/span>') #series if calidad == "": calidad = scrapertools.find_single_match(title, r'..*?(\[.*?.*\])') #movies @@ -220,9 +222,8 @@ def listado_busqueda(item): # fix encoding for title title = scrapertools.htmlclean(title) - title = title.replace("�", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng") title = re.sub(r'(Calidad.*?\])', '', title) - + title = title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") if real_title == "": real_title = title if calidad == "": @@ -236,18 +237,22 @@ def listado_busqueda(item): # Codigo para rescatar lo que se puede en pelisy.series.com de Series para la Videoteca. la URL apunta al capítulo y no a la Serie. Nombre de Serie frecuentemente en blanco. Se obtiene de Thumb, así como el id de la serie if ("/serie" in url or "-serie" in url) and "pelisyseries.com" in host: - calidad_mps = "series/" if "seriehd" in url: calidad_mps = "series-hd/" - if "serievo" in url: + elif "serievo" in url: calidad_mps = "series-vo/" - if "serie-vo" in url: + elif "serie-vo" in url: calidad_mps = "series-vo/" + else: + calidad_mps = "series/" - real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) - real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) + if "no_image" in thumb: + real_title_mps = title + else: + real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) + real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) - if "/0_" not in thumb: + if "/0_" not in thumb and not "no_image" in thumb: serieid = scrapertools.find_single_match(thumb, r'.*?\/\w\/(?P\d+).*?.*') if len(serieid) > 5: serieid = "" @@ -507,6 +512,11 @@ def episodios(item): "[\[]\s*(?P.*?)?\s*[\]]<\/span>" if "Especial" in info: # Capitulos Especiales pattern = ".*?[^>]+>.*?Temporada.*?\[.*?(?P\d+).*?\].*?Capitulo.*?\[\s*(?P\d+).*?\]?(?:.*?(?P\d+)?)<.+?]+>(?P.*?)?<\/span>\s*Calidad\s*]+>[\[]\s*(?P.*?)?\s*[\]]<\/span>" + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioNEW: " + pattern) + logger.debug(info) + info = '>%sTemporada %s Capitulo 0 - Español Castellano Calidad [%s]' % (item.contentTitle, season, item.infoLabels['quality']) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] @@ -540,11 +550,11 @@ def episodios(item): "(?P\d{2}))?.*?\].*?(?:\[(?P.*?)\])?" elif scrapertools.find_single_match(info, 'Cap.\d{2,3}'): pattern = ".*?Temp.*?\s(?P.*?)\s.*?Cap.(?P\d).*?(?P\d{2})(?:_(?P\d+)(?P\d{2}))?.*?\s(?P.*)?" - else: - logger.debug("patron episodio: " + pattern) + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioOLD: " + pattern) logger.debug(info) - continue - + info = '%s [%s][Cap.%s00][Español]' % (item.contentTitle, item.infoLabels['quality'], season) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] diff --git a/plugin.video.alfa/channels/tvsinpagar.py b/plugin.video.alfa/channels/tvsinpagar.py index 56898ea1..ab352ac1 100644 --- a/plugin.video.alfa/channels/tvsinpagar.py +++ b/plugin.video.alfa/channels/tvsinpagar.py @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- import re @@ -133,7 +133,8 @@ def listado(item): for scrapedurl, scrapedtitle, scrapedthumbnail, title_alt, calidad in matches: url = scrapedurl - title = scrapedtitle + title = scrapedtitle.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") + title_alt = title_alt.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "") thumbnail = scrapedthumbnail action = "findvideos" extra = "" @@ -209,10 +210,11 @@ def listado_busqueda(item): for url, thumb, title in matches: real_title = scrapertools.find_single_match(title, r'(.*?)Temporada.*?<\/strong>') #series - if real_title == "": + if not real_title: real_title = scrapertools.find_single_match(title, r'(.*?)\[.*?]') #movies real_title = scrapertools.remove_htmltags(real_title).decode('iso-8859-1').encode('utf-8') real_title = scrapertools.htmlclean(real_title) + real_title = real_title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") calidad = scrapertools.find_single_match(title, r'.*?\s*Calidad.*?]+>[\[]\s*(?P.*?)\s*[\]]<\/span>') #series if calidad == "": calidad = scrapertools.find_single_match(title, r'..*?(\[.*?.*\])') #movies @@ -220,9 +222,8 @@ def listado_busqueda(item): # fix encoding for title title = scrapertools.htmlclean(title) - title = title.replace("�", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng") title = re.sub(r'(Calidad.*?\])', '', title) - + title = title.replace("�", "ñ").replace("ñ", "ñ").replace("Temp", " Temp").replace("Esp", " Esp").replace("Ing", " Ing").replace("Eng", " Eng").replace("Calidad", "").replace("de la Serie", "") if real_title == "": real_title = title if calidad == "": @@ -236,18 +237,22 @@ def listado_busqueda(item): # Codigo para rescatar lo que se puede en pelisy.series.com de Series para la Videoteca. la URL apunta al capítulo y no a la Serie. Nombre de Serie frecuentemente en blanco. Se obtiene de Thumb, así como el id de la serie if ("/serie" in url or "-serie" in url) and "pelisyseries.com" in host: - calidad_mps = "series/" if "seriehd" in url: calidad_mps = "series-hd/" - if "serievo" in url: + elif "serievo" in url: calidad_mps = "series-vo/" - if "serie-vo" in url: + elif "serie-vo" in url: calidad_mps = "series-vo/" + else: + calidad_mps = "series/" - real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) - real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) + if "no_image" in thumb: + real_title_mps = title + else: + real_title_mps = re.sub(r'.*?\/\d+_', '', thumb) + real_title_mps = re.sub(r'\.\w+.*?', '', real_title_mps) - if "/0_" not in thumb: + if "/0_" not in thumb and not "no_image" in thumb: serieid = scrapertools.find_single_match(thumb, r'.*?\/\w\/(?P\d+).*?.*') if len(serieid) > 5: serieid = "" @@ -507,6 +512,11 @@ def episodios(item): "[\[]\s*(?P.*?)?\s*[\]]<\/span>" if "Especial" in info: # Capitulos Especiales pattern = ".*?[^>]+>.*?Temporada.*?\[.*?(?P\d+).*?\].*?Capitulo.*?\[\s*(?P\d+).*?\]?(?:.*?(?P\d+)?)<.+?]+>(?P.*?)?<\/span>\s*Calidad\s*]+>[\[]\s*(?P.*?)?\s*[\]]<\/span>" + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioNEW: " + pattern) + logger.debug(info) + info = '>%sTemporada %s Capitulo 0 - Español Castellano Calidad [%s]' % (item.contentTitle, season, item.infoLabels['quality']) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0] @@ -540,11 +550,11 @@ def episodios(item): "(?P\d{2}))?.*?\].*?(?:\[(?P.*?)\])?" elif scrapertools.find_single_match(info, 'Cap.\d{2,3}'): pattern = ".*?Temp.*?\s(?P.*?)\s.*?Cap.(?P\d).*?(?P\d{2})(?:_(?P\d+)(?P\d{2}))?.*?\s(?P.*)?" - else: - logger.debug("patron episodio: " + pattern) + + if not scrapertools.find_single_match(info, pattern): #en caso de error de formato, creo uno básico + logger.debug("patron episodioOLD: " + pattern) logger.debug(info) - continue - + info = '%s [%s][Cap.%s00][Español]' % (item.contentTitle, item.infoLabels['quality'], season) r = re.compile(pattern) match = [m.groupdict() for m in r.finditer(info)][0]