def busqueda(item):
logger.info()
itemlist = []
host = detectar_host(item.channel)
data = httptools.downloadpage(item.url).data
# ~ logger.debug(data)
patron = '<div class="poster-media-card">(.*?)(?:<li class="search-results-item media-item">|<footer>)'
bloque = scrapertools.find_multiple_matches(data, patron)
for match in bloque:
# ~ logger.debug(match)
patron = 'href="([^"]+)" title="([^"]+)".*?src="([^"]+)".*?' \
'<p class="search-results-main-info">.*?del año (\d+).*?' \
'p class.*?>(.*?)<'
matches = scrapertools.find_multiple_matches(match, patron)
for scrapedurl, scrapedtitle, scrapedthumbnail, year, plot in matches:
scrapedtitle = scrapedtitle.capitalize()
plot = scrapertools.htmlclean(plot)
new_item = Item(channel=item.channel,
thumbnail=scrapedthumbnail,
plot=plot)
new_item.infoLabels["year"] = year
if "/serie/" in scrapedurl:
new_item.contentType = 'tvshow'
new_item.contentSerieName = scrapedtitle
new_item.action = 'temporadas'
scrapedurl += "/episodios"
elif "/pelicula/" in scrapedurl or "/adulto/" in scrapedurl:
new_item.contentType = 'movie'
new_item.contentTitle = scrapedtitle
new_item.action = 'findvideos'
# ~ filter_list = {"poster_path": limpiar_thumbnail(scrapedthumbnail)}
# ~ new_item.infoLabels['filtro'] = filter_list.items()
# parece que con filtro se detectan peor en tmdb !?
else:
logger.info('Enlace no tratado: %s' % scrapedurl)
continue
if item.search_type == 'all' or item.search_type == new_item.contentType:
new_item.fmt_sufijo = '' if item.search_type != 'all' else new_item.contentType
new_item.title = scrapedtitle
new_item.url = scrapedurl
itemlist.append(new_item)
# ~ for it in itemlist: logger.debug(it)
tmdb.set_infoLabels(itemlist)
next_page = scrapertools.find_single_match(
data, 'href="([^"]+)"[^>]+>Más resultados')
if next_page != "" and len(bloque) > 0:
next_page = urlparse.urljoin(host, next_page)
itemlist.append(
item.clone(title=">> Página siguiente",
url=next_page,
action='busqueda'))
return itemlist
