I am working on channel development of this site, filmsubito.tv, as it has a lot of different contents.
Here's a list of issues I need help with:
1) Separating the two sides of the site "FILM STREAMING - NOVITÀ" and "GLI ULTIMI AGGIUNTI"
from home page, as the patron I did extracts them all together.
It also takes a lot of time to load movies, but if I use
Código: Seleccionar todo
patron = '</span>.*?<a href="(.*?)".*?><img src="(.*?)" width="145"></span><span class="vertical-align"></span></span></a>.*?<p style="font-size:14px;font-weight:bold">(.*?)</p>.*?<p style="font-size:12px;line-height:15px">(.*?)</p>'2) Cant' figure out paginador because there are two with same structure.
3) Extract videos from pages (no need to edit new servers I think, at least)
4) Extract tv shows and page them properly.
5) Paging the genres.
Mostly, I lack of time as I began a new job and need to be earlier on site, and get out later
Any help will be apreciated, here's the job I did until now:
Código: Seleccionar todo
# -*- coding: utf-8 -*-
#------------------------------------------------------------
# pelisalacarta - XBMC Plugin
# Canal para filmsubito.tv
# http://blog.tvalacarta.info/plugin-xbmc/pelisalacarta/
#------------------------------------------------------------
import urlparse
import re
import sys
from core import logger
from core import config
from core import scrapertools
from core.item import Item
from servers import servertools
__channel__ = "filmsubitotv"
__category__ = "F,A,S,D"
__type__ = "generic"
__title__ = "FilmSubito.tv"
__language__ = "IT"
sito="http://www.filmsubito.tv/"
DEBUG = config.get_setting("debug")
def isGeneric():
return True
def mainlist(item):
logger.info("pelisalacarta.filmsubitotv mainlist")
itemlist = []
itemlist.append( Item(channel=__channel__, title="[COLOR azure]Home[/COLOR]", action="peliculas", url=sito, thumbnail="http://dc584.4shared.com/img/XImgcB94/s7/13feaf0b538/saquinho_de_pipoca_01"))
itemlist.append( Item(channel=__channel__, title="[COLOR azure]Serie Anni 80[/COLOR]", action="serie80", url=sito ))
itemlist.append( Item(channel=__channel__, title="[COLOR yellow]Cerca...[/COLOR]", action="search", thumbnail="http://dc467.4shared.com/img/fEbJqOum/s7/13feaf0c8c0/Search"))
return itemlist
def serie80(item):
logger.info("pelisalacarta.filmsubitotv categorias")
itemlist = []
data = scrapertools.cache_page(item.url)
logger.info(data)
# The categories are the options for the combo
patron = '<a href="#" class="dropdown-toggle wide-nav-link" data-toggle="dropdown">Serie anni 80<b class="caret"></b></a>.*?<li class.*? ><a title="(.*?)".*?href="(.*?)">.*?</a></li>'
matches = re.compile(patron,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for scrapedtitle,scrapedurl in matches:
#scrapedurl = urlparse.urljoin(item.url,url)
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
itemlist.append( Item(channel=__channel__, action="peliculas" ,title=scrapedtitle, url=scrapedurl))
return itemlist
def peliculas(item):
logger.info("pelisalacarta.filmsubitotv peliculas")
itemlist = []
# Descarga la pagina
data = scrapertools.cache_page(item.url)
# Extrae las entradas (carpetas)
patron = '</span>.*?<a href="(.*?)".*?><img src="(.*?)".*?width="145"></span><span class="vertical-align"></span></span></a>.*?<p style="font-size:14px;font-weight:bold">(.*?)</p>.*?<p style="font-size:12px;line-height:15px">(.*?)</p>'
matches = re.compile(patron,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for scrapedurl,scrapedthumbnail,scrapedtitle,scrapedplot in matches:
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
itemlist.append( Item(channel=__channel__, action="findvideos", title=scrapedtitle, url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot, folder=True, fanart=scrapedthumbnail) )
# Extrae el paginador
patronvideos = '<li class="">.*?<a href="(.*?)">»</a>.*?</li>.*?</ul>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
scrapedurl = urlparse.urljoin(item.url,matches[0])
itemlist.append( Item(channel=__channel__, extra=item.extra, action="peliculas", title="[COLOR orange]Successivo>>[/COLOR]" , url=scrapedurl , thumbnail="http://2.bp.blogspot.com/-fE9tzwmjaeQ/UcM2apxDtjI/AAAAAAAAeeg/WKSGM2TADLM/s1600/pager+old.png", folder=True) )
return itemlist
def search(item,texto):
logger.info("[filmsubitotv.py] "+item.url+" search "+texto)
item.url = "http://www.filmsubito.tv/search.php?keywords="+texto
try:
return peliculas(item)
# Se captura la excepción, para no interrumpir al buscador global si un canal falla
except:
import sys
for line in sys.exc_info():
logger.error( "%s" % line )
return []
this is very handy
