def listmirrors(item):
logger.info("[yotix.py] listmirrors")
title = item.title
url = item.url
thumbnail = item.thumbnail
plot = item.plot
itemlist = []
# Descarga la página de detalle
data = scrapertools.cachePage(url)
#logger.info(data)
# Extrae el argumento
patronvideos = '<div class="texto-sinopsis">(.*?)<div'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
plot = scrapertools.htmlclean(matches[0].strip())
# Extrae los enlaces si el video está en la misma página
patron = 'so.addParam\(\'flashvars\',\'.*?file\=([^\&]+)\&'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
url = matches[0]
newurl = findnewlocation(url)
if newurl!="":
url = newurl
itemlist.append( Item(channel=CHANNELNAME, action="play" , title=title , url=url, thumbnail=thumbnail, plot=plot, server="Directo", folder=False))
# Extrae los enlaces a los vídeos (Megavídeo)
patronvideos = '<a.*?href="(http://yotix.tv/flash/[^"]+)"[^>]*>(.*?)</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Añade al listado de XBMC
scrapedtitle = scrapertools.htmlclean(match[1].replace("–","-")).strip()
scrapedurl = match[0]
itemlist.append( Item(channel=CHANNELNAME, action="play" , title=title , url=url, thumbnail=thumbnail, plot=plot, server="Megavideo", folder=False))
# Extrae los enlaces a los vídeos (Directo)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/sitio/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/media/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/video/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/ver/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/rt/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/anime/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/gb/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/online/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
buscamirrors(itemlist,'<a.*?href="(http://yotix.tv/4s/[^"]+)"[^>]*>(.*?)</a>',data,thumbnail,plot)
return itemlist
def episodios(params,url,category):
xbmc.output("[boing.py] videolist")
# El título es el de la serie
title = urllib.unquote_plus( params.get("title") )
# Descarga la página
data = scrapertools.cachePage("http://www.boing.es/videos/FFFFFF.xml")
#xbmc.output(data)
'''
<video id="ben10af_ep2_01" series="ben10af" extras="" novedad="0">
<titulo>Episodio 2 (parte 1)</titulo>
<imagen>/videos/1clips/ben10af/ep/ep.jpg</imagen>
<url>http://ht.cdn.turner.com/tbseurope/big/toones/protected_auth/b10af/Ben10_Ep02_Sg01.flv</url>
<stats>http://www.boing.es/videos/stats/episodios_ben10af.html</stats>
<descripcion><![CDATA[<a href='/microsites/ben10alienforce/index.jsp' target='_self'><font color='#FF0000'>Pincha</font></a> para visitar la página de Ben 10 Alien Force<br/>Episodios solamente disponibles en España]]></descripcion>
</video>
'''
# Extrae las entradas (videos, el parámetro url es el id de la serie)
patronvideos = '<video id="[^"]+" series="'+url+'"[^>]+>[^<]+'
patronvideos += '<titulo>([^<]+)</titulo>[^<]+'
patronvideos += '<imagen>([^<]+)</imagen>[^<]+'
patronvideos += '<url>([^<]+)</url>[^<]+'
patronvideos += '<stats>[^<]+</stats>[^<]+'
patronvideos += '<descripcion>(.*?)</descripcion>[^<]+'
patronvideos += '</video>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Titulo
try:
scrapedtitle = unicode( match[0], "utf-8" ).encode("iso-8859-1")
except:
scrapedtitle = match[0]
scrapedurl = urlparse.urljoin(url,match[2])
scrapedthumbnail = urlparse.urljoin(url,match[1])
try:
scrapedplot = scrapertools.htmlclean(unicode( match[3], "utf-8" ).encode("iso-8859-1"))
except:
scrapedplot = scrapertools.htmlclean(match[3])
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
xbmctools.addnewvideo( CHANNELCODE , "play" , category , "Directo" , title + " - " + scrapedtitle , scrapedurl , scrapedthumbnail , scrapedplot )
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_LABEL )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def listmirrors(params,url,category):
logger.info("[yotix.py] listmirrors")
title = urllib.unquote_plus( params.get("title") )
thumbnail = urllib.unquote_plus( params.get("thumbnail") )
plot = urllib.unquote_plus( params.get("plot") )
# Descarga la página de detalle
data = scrapertools.cachePage(url)
#logger.info(data)
# Extrae el argumento
patronvideos = '<div class="texto-sinopsis">(.*?)<div'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
plot = scrapertools.htmlclean(matches[0].strip())
# Extrae los enlaces si el video está en la misma página
patron = 'so.addParam\(\'flashvars\',\'.*?file\=([^\&]+)\&'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
url = matches[0]
xbmctools.addnewvideo( CHANNELNAME , "play2" , category , "Directo" , title , url , thumbnail , plot )
# Extrae los enlaces a los vídeos (Megavídeo)
patronvideos = '<a.*?href="(http://yotix.tv/flash/[^"]+)"[^>]*>(.*?)</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Añade al listado de XBMC
scrapedtitle = scrapertools.htmlclean(match[1].replace("–","-")).strip()
scrapedurl = match[0]
xbmctools.addnewvideo( CHANNELNAME , "play" , category , "Megavideo" , scrapedtitle , scrapedurl , thumbnail , plot )
# Extrae los enlaces a los vídeos (Directo)
extraevideos('<a.*?href="(http://yotix.tv/sitio/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
extraevideos('<a.*?href="(http://yotix.tv/media/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
extraevideos('<a.*?href="(http://yotix.tv/video/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
extraevideos('<a.*?href="(http://yotix.tv/ver/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
extraevideos('<a.*?href="(http://yotix.tv/rt/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
extraevideos('<a.*?href="(http://yotix.tv/anime/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
extraevideos('<a.*?href="(http://yotix.tv/gb/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
extraevideos('<a.*?href="(http://yotix.tv/online/[^"]+)"[^>]*>(.*?)</a>',data,category,thumbnail,plot)
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def novedades(params,url,category):
xbmc.output("[boing.py] videolist")
# Descarga la página
data = scrapertools.cachePage(url)
#xbmc.output(data)
'''
<video id="naruto_promo" extras="naruto" novedad="1" promo="">
<titulo>Naruto en Boing FDF</titulo>
<imagen>/videos/extras/naruto/thumb.jpg</imagen>
<url>http://ht.cdn.turner.com/tbseurope/big/toones/naruto/PromoNaruto.flv</url>
<stats>http://www.boing.es/videos/stats/clips.html</stats>
<descripcion><![CDATA[<a href='/microsites/naruto/index.jsp' target='_self'><font color='#FF0000'>Pincha</font></a> para visitar la página de Naruto para Juegos y Descargas]]></descripcion>
</video>
'''
# Extrae las entradas (videos, el parámetro url es el id de la serie)
patronvideos = '<video id="[^"]+" extras="([^"]+)"[^>]+>[^<]+'
patronvideos += '<titulo>([^<]+)</titulo>[^<]+'
patronvideos += '<imagen>([^<]+)</imagen>[^<]+'
patronvideos += '<url>([^<]+)</url>[^<]+'
patronvideos += '<stats>[^<]+</stats>[^<]+'
patronvideos += '<descripcion>(.*?)</descripcion>[^<]+'
patronvideos += '</video>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Titulo
try:
scrapedtitle = match[0] + " - " + unicode( match[1], "utf-8" ).encode("iso-8859-1")
except:
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(url,match[3])
scrapedthumbnail = urlparse.urljoin(url,match[2])
try:
scrapedplot = scrapertools.htmlclean(unicode( match[4], "utf-8" ).encode("iso-8859-1"))
except:
scrapedplot = scrapertools.htmlclean(match[4])
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
xbmctools.addnewvideo( CHANNELCODE , "play" , category , "Directo" , scrapedtitle , scrapedurl , scrapedthumbnail , scrapedplot )
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_LABEL )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def detail(params, url, category):
logger.info("[dibujosanimadosgratis.py] detail")
# Recupera los parámetros
title = urllib.unquote_plus(params.get("title"))
thumbnail = urllib.unquote_plus(params.get("thumbnail"))
plot = urllib.unquote_plus(params.get("plot"))
# Descarga la página de detalle
'''
<div class="post">
<h2 class="postTitle"><a href="http://dibujosanimadosgratis.net/ranma/ranma-%c2%bd-episodio-142-33-audio-latino-dvdrip-hq.html">Ranma ½ Episodio 142 3/3 Audio Latino DVDRip HQ</a></h2>
<div class="postMeta">
<span class="date">May.08, 2010</span> en
<span class="filed"><a href="http://dibujosanimadosgratis.net/category/ranma" title="Ver todas las entradas en Ranma" rel="category tag">Ranma</a></span>
</div>
<div class="postContent"><p> <img src="http://i4.ytimg.com/vi/3k4YsDCdfoA/default.jpg" align="right" border="0" width="120" height="90" vspace="4" hspace="4" />
</p>
<p> Author: <a href="http://youtube.com/profile?user=AlucardReturn08">AlucardReturn08</a><br/> Keywords: <br/> Added: May 8, 2010<br/> </p>
<p><object width="425" height="350"><param name="movie" value="http://www.youtube.com/v/3k4YsDCdfoA"></param><param name="wmode" value="transparent"></param><embed src="http://www.youtube.com/v/3k4YsDCdfoA" type="application/x-shockwave-flash" wmode="transparent" width="425" height="350"></embed></object></p>
</div>
'''
data = scrapertools.cachePage(url)
patron = '<div class="post">(.*?<div class="postMeta">.*?<div class="postContent">.*?)</div>'
matches = re.compile(patron, re.DOTALL).findall(data)
if len(matches) > 0:
data = matches[0]
logger.info(data)
# Plot
scrapedplot = scrapertools.htmlclean(data)
scrapedplot = scrapedplot.replace("\n", " ")
scrapedplot = scrapedplot.replace("\r", " ")
# Thumbnail
patron = '<img src="([^"]+)"'
matches = re.compile(patron, re.DOTALL).findall(data)
scrapedthumbnail = ""
if len(matches) > 0:
scrapedthumbnail = matches[0]
# ------------------------------------------------------------------------------------
# Busca los enlaces a los videos conocidos en el iframe
# ------------------------------------------------------------------------------------
listavideos = servertools.findvideos(data)
for video in listavideos:
videotitle = video[0]
url = video[1]
server = video[2]
xbmctools.addnewvideo(CHANNELNAME, "play", category, server,
title.strip() + " - " + videotitle, url,
scrapedthumbnail, scrapedplot)
# ------------------------------------------------------------------------------------
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
xbmcplugin.addSortMethod(handle=pluginhandle,
sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def episodelist(item):
logger.info("[seriespepito.py] list")
# Descarga la página
data = scrapertools.cachePage(item.url)
#logger.info(data)
# Extrae el argumento
patron = '<div class="contenido" id="noticia">.*?<span[^>]+>(.*?)</div>'
matches = re.compile(patron, re.DOTALL).findall(data)
if len(matches) > 0:
scrapedplot = matches[0]
scrapedplot = scrapertools.htmlclean(scrapedplot).strip()
# Unas series están en utf-8, otras en iso-8859-1. Esta doble conversión funciona :)
try:
intermedia = unicode(scrapedplot, "utf-8",
errors="replace").encode("iso-8859-1")
intermedia = unicode(intermedia, "iso-8859-1",
errors="replace").encode("utf-8")
#print item.title+" encoding 1"
scrapedplot = intermedia
except:
#print item.title+" encoding 2"
scrapedplot = unicode(scrapedplot, "iso-8859-1",
errors="replace").encode("utf-8")
item.plot = scrapedplot
else:
scrapedplot = ""
# Extrae los capítulos
patron = "<li class='li_capitulo'><a class='capitulo1' href='([^']+)' title='[^']+'>([^<]+)</a> <img src='([^']+)'[^>]+></li>"
matches = re.compile(patron, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
itemlist = []
for match in matches:
scrapedtitle = match[1] + " [" + match[2][49:-4] + "]"
scrapedurl = match[0]
scrapedthumbnail = item.thumbnail
#scrapedplot = ""
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
# Ajusta el encoding a UTF-8
scrapedtitle = unicode(scrapedtitle, "iso-8859-1",
errors="replace").encode("utf-8")
itemlist.append(
Item(channel=CHANNELNAME,
action="findvideos",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot,
show=item.show))
return itemlist
def estrenos(params, url, category):
logger.info("[mcanime.py] estrenos")
# Descarga la página
data = scrapertools.cachePage(url)
# logger.info(data)
# Extrae las entradas (carpetas)
"""
<dl id="addRow9203" class="min row1">
<dd class="thumb">
<img src="/images/anime/th_9203.jpg" width="75" height="100" alt="" />
</dd>
<dt><a href="/enciclopedia/anime/cobra_the_animation_rokunin_no_yuushi/9203">Cobra The Animation: Rokunin no Yuushi</a> <i>(Serie)</i></dt>
<dd>Cobra es un conocido pirata espacial, pero decide cambiar su cara y borrar todas sus memorias. El ahora es un hombre normal, con un trabajo normal y una vida aburrida, pero comienza a recordar su verdadera identidad y sus aventuras comienzan de nuevo. <a href="/enciclopedia/anime/cobra_the_animation_rokunin_no_yuushi/9203">leer más.</a></dd>
<dd class="small mgn"><a href="/descarga_directa/anime/cobra_the_animation_rokunin_no_yuushi/9203" class="srch_dd">Descargar <img width="14" height="14" src="/images/dds/download_icon.gif" alt="[DD]" /></a></dd> </dl>
"""
patron = '<dl id="[^"]+" class="min row.">(.*?)</dl>'
matches = re.compile(patron, re.DOTALL).findall(data)
for match in matches:
data = match
patron = '<dd class="thumb">[^<]+'
patron += '<img src="([^"]+)"[^>]+>[^<]+'
patron += "</dd>[^<]+"
patron += '<dt><a href="[^"]+">([^<]+)</a>\s*<i>([^<]+)</i>\s*</dt>[^<]+'
matches2 = re.compile(patron, re.DOTALL).findall(data)
if len(matches2) > 0:
scrapedtitle = matches2[0][1].strip() + " " + matches2[0][2].strip()
scrapedthumbnail = urlparse.urljoin(url, matches2[0][0])
scrapedplot = ""
scrapedurl = ""
if DEBUG:
logger.info(
"title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]"
)
patron = '</dt>(.*?)<dd class="small mgn"><a href="([^"]+)"'
matches2 = re.compile(patron, re.DOTALL).findall(data)
if len(matches2) > 0:
try:
scrapedplot = unicode(matches2[0][0].strip(), "utf-8").encode("iso-8859-1")
except:
scrapedplot = matches2[0][0].strip()
scrapedplot = scrapertools.htmlclean(scrapedplot)
scrapedplot = scrapedplot.replace("\n", " ")
scrapedplot = scrapedplot.replace("\r", " ")
scrapedplot = scrapedplot.replace("\r\n", " ")
scrapedurl = urlparse.urljoin(url, matches2[0][1])
# Añade al listado de XBMC
xbmctools.addnewfolder(
CHANNELNAME, "ddseriedetail", category, scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
# Propiedades
xbmcplugin.setPluginCategory(handle=int(sys.argv[1]), category=category)
xbmcplugin.addSortMethod(handle=int(sys.argv[1]), sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=int(sys.argv[1]), succeeded=True)
def ddpostdetail(params,url,category):
logger.info("[mcanime.py] ddpostdetail")
title = urllib.unquote_plus( params.get("title") )
thumbnail = urllib.unquote_plus( params.get("thumbnail") )
plot = unicode( xbmc.getInfoLabel( "ListItem.Plot" ), "utf-8" )
# Descarga la p·gina
data = scrapertools.cachePage(url)
#logger.info(data)
# Foto de la serie de la enciclopedia
patron = '<img src="([^"]+)" width="300".*?class="title_pic" />'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
thumbnail = matches[0]
# Argumento - texto del post
patron = '<div id="download_detail">(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
plot = scrapertools.htmlclean(matches[0])
plot = plot.replace("\r\n"," ")
plot = plot.replace("\r"," ")
plot = plot.replace("\n"," ")
plot = plot.strip()
# ------------------------------------------------------------------------------------
# Busca los enlaces a los videos
# ------------------------------------------------------------------------------------
listavideos = servertools.findvideos(data)
i = 1
for video in listavideos:
try:
fulltitle = unicode( title.strip() + " (%d) " + video[0], "utf-8" ).encode("iso-8859-1")
except:
fulltitle = title.strip() + " (%d) " + video[0]
fulltitle = fulltitle % i
i = i + 1
videourl = video[1]
server = video[2]
#logger.info("videotitle="+urllib.quote_plus( videotitle ))
#logger.info("plot="+urllib.quote_plus( plot ))
#plot = ""
#logger.info("title="+urllib.quote_plus( title ))
xbmctools.addnewvideo( CHANNELNAME , "play" , category , server , fulltitle , videourl , thumbnail , plot )
# ------------------------------------------------------------------------------------
# ------------------------------------------------------------------------------------
# AÒade la opciÛn "AÒadir todos los vÌdeos a la lista de descarga"
# ------------------------------------------------------------------------------------
xbmctools.addnewvideo( CHANNELNAME , "addalltodownloadlist" , title , "" , "(AÒadir todos los vÌdeos a la lista de descarga)" , url , thumbnail , plot )
# Cierra el directorio
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def ddseriedetail(params,url,category):
logger.info("[mcanime.py] ddseriedetail")
title = urllib.unquote_plus( params.get("title") )
thumbnail = urllib.unquote_plus( params.get("thumbnail") )
plot = urllib.unquote_plus( params.get("plot") )
# Descarga la p·gina
data = scrapertools.cachePage(url)
# Foto de la serie de la enciclopedia
patron = '<img src="([^"]+)" width="300".*?class="title_pic" />'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
thumbnail = matches[0]
logger.info("[mcanime.py] thumbnail="+thumbnail)
# Argumento
patron = '<h6>Sinopsis.*?</h6>(.*?)<h6>'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
plot = matches[0]
plot = plot.replace("\n"," ")
plot = plot.replace("\r"," ")
plot = plot.replace("\r\n"," ")
plot = plot.strip()
plot = scrapertools.htmlclean(matches[0])
logger.info("[mcanime.py] plot="+plot)
# Aportaciones de los usuarios
patron = '<h6 class="m">Por los Usuarios</h6>[^<]+'
patron += '<div id="user_actions">(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
data = matches[0]
#logger.info("[mcanime.py] data="+data)
patron = '<ul class="dd_row">[^<]+'
patron += '<li class="dd_type"><img[^>]+></li>[^<]+'
patron += '<li class="dd_update"> <img[^>]+>([^<]+)</li>[^<]+'
patron += '<li class="dd_title">[^<]+'
patron += '<h5><a href="([^"]+)">([^<]+)</a></h5>'
matches = re.compile(patron,re.DOTALL).findall(data)
for match in matches:
# Atributos
scrapedtitle = match[2].strip()+" ("+match[0].strip()+")"
scrapedurl = urlparse.urljoin(url,match[1])
scrapedthumbnail = thumbnail
scrapedplot = plot
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# AÒade al listado de XBMC
xbmctools.addnewfolder( CHANNELNAME , "ddpostdetail" , category , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
# Cierra el directorio
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def home(params, url, category):
logger.info("[mcanime.py] listvideos")
# Descarga la página
data = scrapertools.cachePage(url)
# logger.info(data)
# Extrae las entradas (carpetas)
patronvideos = '<div class="release" style="background-image.url\(\'([^\']+)\'\)\;">[^<]+'
patronvideos += '<h4>([^<]+)<a href="([^"]+)">([^<]+)</a> <span class="date">([^<]+)</span></h4>[^<]+'
patronvideos += '<div class="rimg"><img src="([^"]+)"[^>]+></div>[^<]+'
patronvideos += '<div class="rtext">(.*?)</div>[^<]+'
patronvideos += '<div class="rfinfo">(.*?)</div>[^<]+'
patronvideos += '<div class="rflinks">(.*?)</div>[^<]+'
patronvideos += '<div class="rinfo">(.*?)</div>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
if match[0].endswith("anime.gif"):
scrapedtitle = match[3].strip() + " " + match[1].strip() + " (" + match[4] + ")"
scrapedurl = urlparse.urljoin(url, match[2])
scrapedthumbnail = urlparse.urljoin(url, match[5])
scrapedplot = scrapertools.htmlclean(match[6])
scrapedextra = match[8]
if DEBUG:
logger.info(
"title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]"
)
# Añade al listado de XBMC
xbmctools.addnewfolderextra(
CHANNELNAME,
"homedetail",
category,
scrapedtitle,
scrapedurl,
scrapedthumbnail,
scrapedplot,
scrapedextra,
)
# Extrae la marca de siguiente página
patronvideos = '<span class="next"><a href="([^"]+)">Anteriores</a>...</span>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches) > 0:
scrapedtitle = "Página siguiente"
scrapedurl = urlparse.urljoin(url, matches[0])
scrapedthumbnail = ""
scrapedplot = ""
xbmctools.addnewfolder(CHANNELNAME, "home", category, scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot)
# Propiedades
xbmcplugin.setPluginCategory(handle=int(sys.argv[1]), category=category)
xbmcplugin.addSortMethod(handle=int(sys.argv[1]), sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=int(sys.argv[1]), succeeded=True)
def novedades(item):
logger.info("[documentalesatonline.py] novedades")
# Descarga la página
data = scrapertools.cachePage(item.url)
#logger.info(data)
# Extrae las entradas (carpetas)
patronvideos = "<div class='post hentry'>.*?"
patronvideos += "<h3 class='post-title entry-title'>[^<]+"
patronvideos += "<a href='([^']+)'>([^<]+)</a>.*?"
patronvideos += '<img.*?src="([^"]+)"[^>]+>(.*?)<div'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
itemlist = []
for match in matches:
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(item.url, match[0])
scrapedthumbnail = match[2]
scrapedplot = scrapertools.htmlclean(match[3])
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
itemlist.append(
Item(channel=CHANNELNAME,
action="findvideos",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot))
# Página siguiente
patronvideos = "<a class='blog-pager-older-link' href='([^']+)' id='Blog1_blog-pager-older-link' title='Entradas antiguas'>Entradas antiguas</a>"
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = "Página siguiente"
scrapedurl = urlparse.urljoin(item.url, match)
scrapedthumbnail = ""
scrapedplot = ""
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
itemlist.append(
Item(channel=CHANNELNAME,
action="novedades",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot))
return itemlist
def detail(params,url,category):
logger.info("[dibujosanimadosgratis.py] detail")
# Recupera los parámetros
title = urllib.unquote_plus( params.get("title") )
thumbnail = urllib.unquote_plus( params.get("thumbnail") )
plot = urllib.unquote_plus( params.get("plot") )
# Descarga la página de detalle
'''
<div class="post">
<h2 class="postTitle"><a href="http://dibujosanimadosgratis.net/ranma/ranma-%c2%bd-episodio-142-33-audio-latino-dvdrip-hq.html">Ranma ½ Episodio 142 3/3 Audio Latino DVDRip HQ</a></h2>
<div class="postMeta">
<span class="date">May.08, 2010</span> en
<span class="filed"><a href="http://dibujosanimadosgratis.net/category/ranma" title="Ver todas las entradas en Ranma" rel="category tag">Ranma</a></span>
</div>
<div class="postContent"><p> <img src="http://i4.ytimg.com/vi/3k4YsDCdfoA/default.jpg" align="right" border="0" width="120" height="90" vspace="4" hspace="4" />
</p>
<p> Author: <a href="http://youtube.com/profile?user=AlucardReturn08">AlucardReturn08</a><br/> Keywords: <br/> Added: May 8, 2010<br/> </p>
<p><object width="425" height="350"><param name="movie" value="http://www.youtube.com/v/3k4YsDCdfoA"></param><param name="wmode" value="transparent"></param><embed src="http://www.youtube.com/v/3k4YsDCdfoA" type="application/x-shockwave-flash" wmode="transparent" width="425" height="350"></embed></object></p>
</div>
'''
data = scrapertools.cachePage(url)
patron = '<div class="post">(.*?<div class="postMeta">.*?<div class="postContent">.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
data = matches[0]
logger.info(data)
# Plot
scrapedplot = scrapertools.htmlclean(data)
scrapedplot = scrapedplot.replace("\n"," ")
scrapedplot = scrapedplot.replace("\r"," ")
# Thumbnail
patron = '<img src="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(data)
scrapedthumbnail = ""
if len(matches)>0:
scrapedthumbnail = matches[0]
# ------------------------------------------------------------------------------------
# Busca los enlaces a los videos conocidos en el iframe
# ------------------------------------------------------------------------------------
listavideos = servertools.findvideos(data)
for video in listavideos:
videotitle = video[0]
url = video[1]
server = video[2]
xbmctools.addnewvideo( CHANNELNAME , "play" , category , server , title.strip() + " - " + videotitle , url , scrapedthumbnail , scrapedplot )
# ------------------------------------------------------------------------------------
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def novedades(params,url,category):
logger.info("[documentalesatonline.py] novedades")
# Descarga la página
data = scrapertools.cachePage(url)
#logger.info(data)
# Extrae las entradas (carpetas)
patronvideos = "<div class='post hentry'>.*?"
patronvideos += "<h3 class='post-title entry-title'>[^<]+"
patronvideos += "<a href='([^']+)'>([^<]+)</a>.*?"
patronvideos += '<img.*?src="([^"]+)"[^>]+>(.*?)<div'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(url,match[0])
scrapedthumbnail = match[2]
scrapedplot = scrapertools.htmlclean(match[3])
# Depuracion
if (DEBUG):
logger.info("scrapedtitle="+scrapedtitle)
logger.info("scrapedurl="+scrapedurl)
logger.info("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELNAME , "detail" , category , scrapedtitle , scrapedurl , scrapedthumbnail , scrapedplot)
# Página siguiente
patronvideos = "<a class='blog-pager-older-link' href='([^']+)' id='Blog1_blog-pager-older-link' title='Entradas antiguas'>Entradas antiguas</a>"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = "Página siguiente"
scrapedurl = urlparse.urljoin(url,match)
scrapedthumbnail = ""
scrapedplot = ""
# Depuracion
if (DEBUG):
logger.info("scrapedtitle="+scrapedtitle)
logger.info("scrapedurl="+scrapedurl)
logger.info("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELNAME , "novedades" , category , scrapedtitle , scrapedurl , scrapedthumbnail , scrapedplot)
if config.getSetting("singlechannel")=="true":
xbmctools.addSingleChannelOptions(params,url,category)
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def buscamirrors(itemlist,patronvideos,data,thumbnail,plot):
logger.info("patron="+patronvideos)
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = scrapertools.htmlclean(match[1].replace("–","-")).strip()
scrapedurl = match[0]
itemlist.append( Item(channel=CHANNELNAME, action="findvideos" , title=scrapedtitle , url=scrapedurl, thumbnail=thumbnail, plot=plot))
def extraevideos(patronvideos,data,category,thumbnail,plot):
logger.info("patron="+patronvideos)
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = scrapertools.htmlclean(match[1].replace("–","-")).strip()
scrapedurl = match[0]
xbmctools.addnewvideo( CHANNELNAME , "play" , category , "Directo" , scrapedtitle , scrapedurl , thumbnail , plot )
def novedades(item):
logger.info("[xhamster.py] novedades")
# Descarga la página
data = scrapertools.cachePage(item.url)
#logger.info(data)
# Extrae las entradas
# seccion novedades
'''
<a href="/movies/496069/the_cheerleader.html" class="hRotator">
<img src="http://st5.xhamster.com/t/069/2_496069.jpg" height="120" width="160">
<img class="hSprite" src="http://static.xhamster.com/images/spacer.gif" sprite="http://st5.xhamster.com/t/069/s_496069.jpg" id="496069" onmouseover="hRotator.start2(this);" height="120" width="160">
</a>
<div class="moduleFeaturedTitle">
<a href="/movies/496069/the_cheerleader.html">The Cheerleader</a>
</div>
<div class="moduleFeaturedDetails">Runtime: 35m51s<br><span style="color: Green;">
'''
#patronvideos = '<p style="text-align: center;">.*?'
patronvideos = '<a href="(/movies/[^"]+.html)"[^>]*?>[^<]*?'
patronvideos += '<img src=\'([^\']+.xhamster.com[^\']+)\'[^>]+>[^<]*?'
patronvideos += '<img[^<]*?>[^<]*?</a>[^<]*?'
patronvideos += '<div[^<]*?>[^<]*?'
patronvideos += '<a href="/movies/[^"]+.html"[^>]*?>([^<]+)</a>[^<]*?'
patronvideos += '</div[^<]*?>[^<]*?'
patronvideos += '<div[^<]*?>Runtime: ([^<]+)<'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[2] + " [" + match[3] + "]"
scrapedurl = urlparse.urljoin(item.url,match[0])
scrapedthumbnail = match[1].replace(" ", "%20")
scrapedplot = scrapertools.htmlclean(match[2].strip())
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
itemlist.append( Item(channel=CHANNELNAME, action="findvideos", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=True) )
# Extrae el paginador
#<A HREF="/new/2.html">Next</A><
patronvideos = '<a href="(\/new\/[^\.]+\.html)"[^>]*?>Next[^<]*?<\/a>'
matches = re.compile(patronvideos,re.DOTALL | re.IGNORECASE).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
scrapedurl = urlparse.urljoin(item.url,matches[0])
logger.info("[xhamster.py] " + scrapedurl)
itemlist.append( Item(channel=CHANNELNAME, action="novedades", title="!Página siguiente" , url=scrapedurl , folder=True) )
return itemlist
def home(params, url, category):
logger.info("[mcanime.py] listvideos")
# Descarga la p·gina
data = scrapertools.cachePage(url)
#logger.info(data)
# Extrae las entradas (carpetas)
patronvideos = '<div class="release" style="background-image.url\(\'([^\']+)\'\)\;">[^<]+'
patronvideos += '<h4>([^<]+)<a href="([^"]+)">([^<]+)</a> <span class="date">([^<]+)</span></h4>[^<]+'
patronvideos += '<div class="rimg"><img src="([^"]+)"[^>]+></div>[^<]+'
patronvideos += '<div class="rtext">(.*?)</div>[^<]+'
patronvideos += '<div class="rfinfo">(.*?)</div>[^<]+'
patronvideos += '<div class="rflinks">(.*?)</div>[^<]+'
patronvideos += '<div class="rinfo">(.*?)</div>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
if match[0].endswith("anime.gif"):
scrapedtitle = match[3].strip() + " " + match[1].strip(
) + " (" + match[4] + ")"
scrapedurl = urlparse.urljoin(url, match[2])
scrapedthumbnail = urlparse.urljoin(url, match[5])
scrapedplot = scrapertools.htmlclean(match[6])
scrapedextra = match[8]
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" +
scrapedurl + "], thumbnail=[" + scrapedthumbnail +
"]")
# AÒade al listado de XBMC
xbmctools.addnewfolderextra(CHANNELNAME, "homedetail", category,
scrapedtitle, scrapedurl,
scrapedthumbnail, scrapedplot,
scrapedextra)
# Extrae la marca de siguiente p·gina
patronvideos = '<span class="next"><a href="([^"]+)">Anteriores</a>...</span>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches) > 0:
scrapedtitle = "P·gina siguiente"
scrapedurl = urlparse.urljoin(url, matches[0])
scrapedthumbnail = ""
scrapedplot = ""
xbmctools.addnewfolder(CHANNELNAME, "home", category, scrapedtitle,
scrapedurl, scrapedthumbnail, scrapedplot)
# Propiedades
xbmcplugin.setPluginCategory(handle=int(sys.argv[1]), category=category)
xbmcplugin.addSortMethod(handle=int(sys.argv[1]),
sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=int(sys.argv[1]), succeeded=True)
def getnovedades(params,url,category):
logger.info("[tubehentai.py] getnovedades")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
#logger.info(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
# seccion novedades
'''
<a href="http://www.tubehentai.com/videos/1167/teen-f**k-in-hospital.html" target="_self">
<img src="http://media.tubehentai.com/thumbs/4cbb3700dbdd91.avi/4cbb3700dbdd91.avi-3.jpg" alt="Teen F**k in Hospital" name="4cbb3700dbdd91.avi" id="4cbb3700dbdd91.avi" onmouseover='startm("4cbb3700dbdd91.avi","http://media.tubehentai.com/thumbs/4cbb3700dbdd91.avi/4cbb3700dbdd91.avi-",".jpg");' onmouseout='endm("4cbb3700dbdd91.avi"); this.src="http://media.tubehentai.com/thumbs/4cbb3700dbdd91.avi/4cbb3700dbdd91.avi-3.jpg";' height="164" width="218" border="0">
</a>
'''
#patronvideos = '<p style="text-align: center;">.*?'
patronvideos = '<a href="(http://www.tubehentai.com/videos/[^"]+)"[^>]*?>[^<]*?'
patronvideos += '<img src="(http://media.tubehentai.com/thumbs/[^"]+)" alt="([^"]+)"[^>]+>[^<]*?</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[2]
scrapedurl = match[0]
scrapedthumbnail = match[1].replace(" ", "%20")
scrapedplot = scrapertools.htmlclean(match[2].strip())
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
itemlist.append( Item(channel=CHANNELNAME, action="play", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=False) )
# ------------------------------------------------------
# Extrae el paginador
# ------------------------------------------------------
#<a href="page2.html" class="next">Next »</a>
patronvideos = '<a href=\'(page[^\.]+\.html)\'[^>]*?>Next[^<]*?<\/a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
scrapedurl = urlparse.urljoin(url,"/" + matches[0])
logger.info("[tubehentai.py] " + scrapedurl)
itemlist.append( Item(channel=CHANNELNAME, action="novedades", title="!Página siguiente" , url=scrapedurl , folder=True) )
return itemlist
def temporadas(item):
logger.info("[cinetube.py] temporadas")
itemlist = []
# Descarga la página
data = scrapertools.cachePage(item.url)
# Busca el argumento
patronvideos = '<div class="ficha_des des_move">(.*?)</div>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if len(matches) > 0:
data = matches[0]
scrapedplot = scrapertools.htmlclean(matches[0])
logger.info("plot actualizado en detalle")
else:
logger.info("plot no actualizado en detalle")
# Busca las temporadas
patronvideos = '<li><h2><a href="([^"]+)">([^<]+)<'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = match[1].strip()
scrapedurl = urlparse.urljoin(item.url, match[0])
scrapedthumbnail = item.thumbnail
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
itemlist.append(
Item(channel=CHANNELNAME,
action="episodios",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot))
# Una trampa, si la serie enlaza no con la temporada sino con la lista de episodios, se resuelve aquí
if len(itemlist) == 0:
itemlist = episodios(item)
# Si la serie lleva directamente a la página de detalle de un episodio (suele pasar en novedades) se detecta aquí
if len(itemlist) == 0:
itemlist.extend(findvideos(item))
return itemlist
def episodelist(item):
logger.info("[seriespepito.py] list")
# Descarga la página
data = scrapertools.cachePage(item.url)
#logger.info(data)
# Extrae el argumento
patron = '<div class="contenido" id="noticia">.*?<span[^>]+>(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
scrapedplot = matches[0]
scrapedplot = scrapertools.htmlclean(scrapedplot).strip()
# Unas series están en utf-8, otras en iso-8859-1. Esta doble conversión funciona :)
try:
intermedia = unicode( scrapedplot, "utf-8" , errors="replace" ).encode("iso-8859-1")
intermedia = unicode( intermedia, "iso-8859-1" , errors="replace" ).encode("utf-8")
#print item.title+" encoding 1"
scrapedplot = intermedia
except:
#print item.title+" encoding 2"
scrapedplot = unicode( scrapedplot, "iso-8859-1" , errors="replace" ).encode("utf-8")
item.plot = scrapedplot
else:
scrapedplot = ""
# Extrae los capítulos
patron = "<li class='li_capitulo'><a class='capitulo1' href='([^']+)' title='[^']+'>([^<]+)</a> <img src='([^']+)'[^>]+></li>"
matches = re.compile(patron,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
itemlist = []
for match in matches:
scrapedtitle = match[1] + " ["+match[2][49:-4]+"]"
scrapedurl = match[0]
scrapedthumbnail = item.thumbnail
#scrapedplot = ""
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Ajusta el encoding a UTF-8
scrapedtitle = unicode( scrapedtitle, "iso-8859-1" , errors="replace" ).encode("utf-8")
itemlist.append( Item(channel=CHANNELNAME, action="findvideos" , title=scrapedtitle , url=scrapedurl, thumbnail=scrapedthumbnail, plot=scrapedplot, show=item.show))
return itemlist
def getcapitulos(params,url,category):
logger.info("[anifenix.py] getcapitulos")
title = urllib.unquote_plus( params.get("title") )
thumbnail = urllib.unquote_plus( params.get("thumbnail") )
plot = urllib.unquote_plus( params.get("plot") )
# ------------------------------------------------------------------------------------
# Descarga la página
# ------------------------------------------------------------------------------------
data = scrapertools.cachePage(url)
#logger.info(data)
# ------------------------------------------------------------------------------------
# Busca el argumento
# ------------------------------------------------------------------------------------
patronvideos = '<div class="ficha_des">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matches)>0:
plot = scrapertools.htmlclean(matches[0])
logger.info("plot actualizado en detalle");
else:
logger.info("plot no actualizado en detalle");
# ------------------------------------------------------------------------------------
# Busca los enlaces a los mirrors, o a los capítulos de las series...
# ------------------------------------------------------------------------------------
'''
<a href="video-hentai-2349.html"><strong>Episodio 01(sub Ingles) sorry..</strong></a>
'''
patronvideos = '<a href="(video-hentai[^"]+)"><strong>([^<]+)</strong></a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(url,match[0])
scrapedthumbnail = thumbnail
scrapedplot = plot
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
itemlist.append( Item(channel=CHANNELNAME, action="detail", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=True) )
return itemlist
def getnovedades(params,url,category):
logger.info("[myhentaitube.py] getnovedades")
# Descarga la pagina
data = scrapertools.cachePage(url)
#logger.info(data)
# Extrae las entradas
# seccion novedades
'''
<a href="/index.php?option=com_content&view=article&id=29:ai-shimai-hentai-movie-anime-&catid=1:movies&Itemid=2">
<img src="/images/stories/ai_shimai_dvd copy.gif" border="0" />
</a>
'''
#patronvideos = '<p style="text-align: center;">.*?'
patronvideos = '<a href="(/index.php[^"]+view=article[^"]+id=[^:]([^"]+)catid=1+[^"]+)">[^<]*?'
patronvideos += '<img src="([^"]+)".*?</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(url,match[0])
scrapedthumbnail = urlparse.urljoin(url,match[2]).replace(" ", "%20")
scrapedplot = scrapertools.htmlclean(match[1].strip())
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
itemlist.append( Item(channel=CHANNELNAME, action="capitulos", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=True) )
# Extrae el paginador
patronvideos = '<a href="(\/index.php\?pageNum[^"]+)">[^<]+</a></span>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
scrapedurl = urlparse.urljoin(url,matches[0])
itemlist.append( Item(channel=CHANNELNAME, action="novedades", title="!P�gina siguiente" , url=scrapedurl , folder=True) )
return itemlist
def getcapitulos(params,url,category):
logger.info("[myhentaitube.py] getcapitulos")
title = urllib.unquote_plus( params.get("title") )
thumbnail = urllib.unquote_plus( params.get("thumbnail") )
plot = urllib.unquote_plus( params.get("plot") )
# Descarga la pagina
data = scrapertools.cachePage(url)
#logger.info(data)
# Busca el argumento
patronvideos = '<div class="ficha_des">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matches)>0:
plot = scrapertools.htmlclean(matches[0])
logger.info("plot actualizado en detalle");
else:
logger.info("plot no actualizado en detalle");
# Busca los enlaces a los mirrors, o a los capitulos de las series...
'''
<h3 style="text-align: center;">
<a href="/index.php?option=com_content&view=article&id=8&Itemid=2">CAPITULO 1
</a></h3>
'''
patronvideos = '<a href="(/index.php[^"]+view=article[^"]+id=[^"]+)">([^<]+)<'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(url,match[0])
scrapedthumbnail = thumbnail
scrapedplot = plot
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
itemlist.append( Item(channel=CHANNELNAME, action="play", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=False) )
return itemlist
def novedades(item):
logger.info("[documentalesatonline.py] novedades")
# Descarga la página
data = scrapertools.cachePage(item.url)
#logger.info(data)
# Extrae las entradas (carpetas)
patronvideos = "<div class='post hentry'>.*?"
patronvideos += "<h3 class='post-title entry-title'>[^<]+"
patronvideos += "<a href='([^']+)'>([^<]+)</a>.*?"
patronvideos += '<img.*?src="([^"]+)"[^>]+>(.*?)<div'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
itemlist = []
for match in matches:
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(item.url,match[0])
scrapedthumbnail = match[2]
scrapedplot = scrapertools.htmlclean(match[3])
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
itemlist.append( Item(channel=CHANNELNAME, action="findvideos" , title=scrapedtitle , url=scrapedurl, thumbnail=scrapedthumbnail, plot=scrapedplot))
# Página siguiente
patronvideos = "<a class='blog-pager-older-link' href='([^']+)' id='Blog1_blog-pager-older-link' title='Entradas antiguas'>Entradas antiguas</a>"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = "Página siguiente"
scrapedurl = urlparse.urljoin(item.url,match)
scrapedthumbnail = ""
scrapedplot = ""
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
itemlist.append( Item(channel=CHANNELNAME, action="novedades" , title=scrapedtitle , url=scrapedurl, thumbnail=scrapedthumbnail, plot=scrapedplot))
return itemlist
def temporadas(item):
logger.info("[cinetube.py] temporadas")
itemlist = []
# Descarga la página
data = scrapertools.cachePage(item.url)
# Busca el argumento
patronvideos = '<div class="ficha_des des_move">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matches)>0:
data = matches[0]
scrapedplot = scrapertools.htmlclean(matches[0])
logger.info("plot actualizado en detalle");
else:
logger.info("plot no actualizado en detalle");
# Busca las temporadas
patronvideos = '<li><h2><a href="([^"]+)">([^<]+)<'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = match[1].strip()
scrapedurl = urlparse.urljoin(item.url,match[0])
scrapedthumbnail = item.thumbnail
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
itemlist.append( Item(channel=CHANNELNAME, action="episodios", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail, plot=scrapedplot) )
# Una trampa, si la serie enlaza no con la temporada sino con la lista de episodios, se resuelve aquí
if len(itemlist)==0:
itemlist = episodios(item)
# Si la serie lleva directamente a la página de detalle de un episodio (suele pasar en novedades) se detecta aquí
if len(itemlist)==0:
itemlist.extend(findvideos(item))
return itemlist
def findvideos(item):
logger.info("[cinetube.py] findvideos")
url = item.url
title = item.title
thumbnail = item.thumbnail
plot = item.plot
# ------------------------------------------------------------------------------------
# Descarga la pagina
# ------------------------------------------------------------------------------------
data = scrapertools.cachePage(url)
# logger.info(data)
# ------------------------------------------------------------------------------------
# Busca el argumento
# ------------------------------------------------------------------------------------
patronvideos = '<div class="ficha_des">(.*?)</div>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if len(matches) > 0:
plot = scrapertools.htmlclean(matches[0])
logger.info("plot actualizado en detalle")
else:
logger.info("plot no actualizado en detalle")
# ------------------------------------------------------------------------------------
# Busca el thumbnail
# ------------------------------------------------------------------------------------
patronvideos = '<div class="ficha_img pelicula_img">[^<]+'
patronvideos += '<img src="([^"]+)"'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if len(matches) > 0:
thumbnail = matches[0]
logger.info("thumb actualizado en detalle")
else:
logger.info("thumb no actualizado en detalle")
# ------------------------------------------------------------------------------------
# Busca los enlaces a los mirrors, o a los capitulos de las series...
# ------------------------------------------------------------------------------------
# url = "http://www.cinetube.es/inc/mostrar_contenido.php?sec=pelis_ficha&zona=online&id=video-4637"
# patronvideos = '<div class="ver_des_peli iframe2">[^<]+'
# patronvideos += '<ul class="tabs-nav" id="([^"]+)">'
# matches = re.compile(patronvideos,re.DOTALL).findall(data)
# data = scrapertools.cachePage("http://www.cinetube.es/inc/mostrar_contenido.php?sec=pelis_ficha&zona=online&id="+matches[0])
"""
<div id="ficha_ver_peli">
<div class="v_online">
<h2>Ver online <span>El destino de Nunik</span></h2>
<div class="opstions_pelicula_list">
<div class="tit_opts" style="cursor:pointer;" onclick="location.href='http://www.cinetube.es/peliculas/drama/el-destino-de-nunik_espanol-dvd-rip-megavideo-6026.html'">
<p>Mirror 1: Megavideo</p>
<p><span>CALIDAD: DVD-RIP | IDIOMA: ESPAÑOL</span></p>
<p class="v_ico"><img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="Megavideo" /></p>
</div>
<div class="tit_opts" style="cursor:pointer;" onclick="location.href='http://www.cinetube.es/peliculas/drama/el-destino-de-nunik_espanol-dvd-rip-megavideo-6027.html'">
<p>Mirror 2: Megavideo</p>
<p><span>CALIDAD: DVD-RIP | IDIOMA: ESPAÑOL</span></p>
<p class="v_ico"><img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="Megavideo" /></p>
</div>
</div>
</div>
</div>
"""
"""
<div class="v_online">
<h2>Ver online <span>Cantajuego 6</span></h2>
<div class="opstions_pelicula_list"><div class="tit_opts"><a href="/peliculas/animacion-e-infantil/cantajuego-6_espanol-dvd-rip-megavideo-73371.html">
<p>Mirror 1: Megavideo</p>
<p><span>CALIDAD: DVD-RIP | IDIOMA: ESPAÑOL</span></p>
<p class="v_ico"><img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="Megavideo" /></p>
</a></div> </div>
</div>
</div><br/><div id="ficha_desc_peli">
<div class="v_online">
<h2 class="ico_fuego">Descargar <span>Cantajuego 6</span></h2>
<div class="opstions_pelicula_list"><div class="tit_opts"><a href="/peliculas/animacion-e-infantil/descargar-cantajuego-6_espanol-dvd-rip-megaupload-73372.html" target="_blank">
<p>Mirror 1: Megaupload </p>
<p><span>CALIDAD: DVD-RIP | IDIOMA: ESPAÑOL </span></p>
<p class="v_ico"><img src="http://caratulas.cinetube.es/img/cont/megaupload.png" alt="Megaupload" /></p>
</a></div>
</div>
</div>
</div>
"""
# patronvideos = '<div class="tit_opts"><a href="([^"]+)">[^<]+'
patronvideos = '<div class="tit_opts"><a href="([^"]+)".*?>[^<]+'
patronvideos += "<p>([^<]+)</p>[^<]+"
patronvideos += "<p><span>([^<]+)</span>"
matches = re.compile(patronvideos, re.DOTALL).findall(data)
itemlist = []
for match in matches:
logger.info("Encontrado iframe mirrors " + match[0])
# Lee el iframe
mirror = urlparse.urljoin(url, match[0].replace(" ", "%20"))
req = urllib2.Request(mirror)
req.add_header(
"User-Agent", "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3"
)
response = urllib2.urlopen(req)
data = response.read()
response.close()
listavideos = servertools.findvideos(data)
for video in listavideos:
scrapedtitle = title.strip() + " " + match[1] + " " + match[2] + " " + video[0]
scrapedurl = video[1]
server = video[2]
itemlist.append(
Item(
channel=CHANNELNAME,
action="play",
title=scrapedtitle,
url=scrapedurl,
thumbnail=item.thumbnail,
plot=item.plot,
server=server,
folder=False,
)
)
return itemlist
def getnovedades(params,url,category):
logger.info("[anifenix.py] getnovedades")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
#logger.info(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
# seccion novedades
'''
<!--DWLayoutTable-->
<tr>
<td width="220" height="301" valign="top"><table width="100%" border="0" cellpadding="0" cellspacing="0">
<!--DWLayoutTable-->
<tr>
<td height="214" colspan="2" valign="top"><a href="descripcion.php?ns=Another lady innocent"><img src="../Administracion/Noticias/archivos/33bd660(cab).jpg" alt="" width="214" height="212" border="0" /></a></td>
<td width="6" rowspan="2" valign="top"><!--DWLayoutEmptyCell--> </td>
</tr>
<tr>
<td width="107" height="87" valign="top"><img src="../Administracion/Noticias/archivos/th_51143_2_123_237lo(cab_sub_1).jpg" width="106" height="87" alt="" /></td>
<td width="107" align="right" valign="top"><a href="descripcion.php?ns=Another lady innocent"><img src="../Administracion/Noticias/archivos/th_51147_4_123_414lo(cab_sub_2).jpg" alt="" width="106" height="87" border="0" /></a></td>
</tr>
</table> </td>
<td width="334" valign="top"><p align="center"><span class="Estilo57" style="margin:0px"><a href="serie-hentai-online-Another lady innocent.html">Serie hentai Online: Another lady innocent</a></span></p>
'''
patronvideos = '<!--DWLayoutTable-->.*?<!--DWLayoutTable-->.*?<img src="([^"]+)".*?'
patronvideos += '<span class="Estilo57"[^>]+><a href="([^"]+)">([^<]+)</a></span>.*?'
patronvideos += '<p class="Estilo59">(.*?)</p>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[2]
scrapedurl = urlparse.urljoin(url,match[1])
scrapedthumbnail = urlparse.urljoin(url,match[0][2:])
scrapedplot = scrapertools.htmlclean(match[3].strip())
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
itemlist.append( Item(channel=CHANNELNAME, action="capitulos", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=True) )
# ------------------------------------------------------
# Extrae el paginador
# ------------------------------------------------------
patronvideos = '<a href="(\/index.php\?pageNum[^"]+)">[^<]+</a></span>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
scrapedurl = urlparse.urljoin(url,matches[0])
itemlist.append( Item(channel=CHANNELNAME, action="novedades", title="!Página siguiente" , url=scrapedurl , folder=True) )
return itemlist
def series(item):
logger.info("[cinetube.py] series")
itemlist = []
# Descarga la página
data = scrapertools.cachePage(item.url)
logger.info("Pagina de %d caracteres" % len(data))
# Extrae las entradas
'''
<li>
<a href="/series/en-tierra-de-lobos/temporada-1/capitulo-12/"><img src="http://caratulas.cinetube.es/series/8912.jpg" alt="peli" /></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/espanol.png" alt="espanol" /> <img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="megavideo.png" /> <img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> <p><span class="rosa"></span></p></div>
<p class="tit_ficha"><a class="tit_ficha" title="Ver serie Tierra de lobos" href="/series/en-tierra-de-lobos/temporada-1/capitulo-12/">Tierra de lobos </a></p>
<p class="tem_fich">1a Temporada - Cap 12</p>
</li>
'''
'''
<li>
<a href="/series/gabriel-un-amor-inmortal/"><img src="http://caratulas.cinetube.es/series/7952.jpg" alt="peli" /></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/latino.png" alt="" /><img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div>
<p class="tit_ficha">Gabriel, un amor inmortal </p>
</li>
'''
'''
<li>
<a href="/series-anime/star-driver-kagayaki-no-takuto/temporada-1/capitulo-13/"><img src="http://caratulas.cinetube.es/seriesa/9009.jpg" alt="peli" /></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/sub.png" alt="sub" /> <img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="megavideo.png" /> <img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> <p><span class="rosa"></span></p></div>
<p class="tit_ficha"><a class="tit_ficha" title="Ver serie Star Driver Kagayaki no Takuto" href="/series-anime/star-driver-kagayaki-no-takuto/temporada-1/capitulo-13/">Star Driver Kagayaki no Takuto </a></p>
<p class="tem_fich">1a Temporada - Cap 13</p>
</li>
'''
patronvideos = '<li>[^<]+'
patronvideos += '<a href="([^"]+)"><img src="([^"]+)"[^>]*></a>[^<]+'
patronvideos += '<div class="icos_lg">(.*?)</div>[^<]+'
patronvideos += '<p class="tit_ficha">(.*?)</p>[^<]+'
patronvideos += '(?:<p class="tem_fich">([^<]+)</p>)?'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[3].strip()
if len(match)>=5:
scrapedtitle = scrapedtitle+" "+match[4]
matchesconectores = re.compile('<img.*?alt="([^"]*)"',re.DOTALL).findall(match[2])
conectores = ""
for matchconector in matchesconectores:
logger.info("matchconector="+matchconector)
if matchconector=="":
matchconector = "megavideo"
conectores = conectores + matchconector + "/"
if len(matchesconectores)>0:
scrapedtitle = scrapedtitle + " (" + conectores[:-1] + ")"
scrapedtitle = scrapedtitle.replace("megavideo/megavideo","megavideo")
scrapedtitle = scrapedtitle.replace("megavideo/megavideo","megavideo")
scrapedtitle = scrapedtitle.replace("megavideo/megavideo","megavideo")
scrapedtitle = scrapedtitle.replace("descarga directa","DD")
scrapedtitle = scrapertools.htmlclean(scrapedtitle)
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedplot = ""
scrapedurl = urlparse.urljoin(item.url,match[0])
scrapedthumbnail = match[1]
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
itemlist.append( Item(channel=CHANNELNAME, action="temporadas", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=True) )
# Paginador
#<li class="navs"><a class="pag_next" href="/peliculas-todas/2.html"></a></li>
patronvideos = '<li class="navs"><a class="pag_next" href="([^"]+)"></a></li>'
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=CHANNELNAME, action="series", title="!Página siguiente" , url=scrapedurl , folder=True) )
return itemlist
def findvideos(item):
logger.info("[cinetube.py] findvideos")
url = item.url
title = item.title
thumbnail = item.thumbnail
plot = item.plot
# Descarga la pagina
data = scrapertools.cachePage(url)
#logger.info(data)
# Busca el argumento
patronvideos = '<div class="ficha_des">(.*?)</div>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if len(matches) > 0:
plot = scrapertools.htmlclean(matches[0])
logger.info("plot actualizado en detalle")
else:
logger.info("plot no actualizado en detalle")
# Busca el thumbnail
patronvideos = '<div class="ficha_img pelicula_img">[^<]+'
patronvideos += '<img src="([^"]+)"'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if len(matches) > 0:
thumbnail = matches[0]
logger.info("thumb actualizado en detalle")
else:
logger.info("thumb no actualizado en detalle")
# Busca los enlaces a los mirrors, o a los capitulos de las series...
'''
FORMATO EN SERIES
<div class="tit_opts"><a href="/series/hawai-five/temporada-1/capitulo-13/212498.html">
<p>Opción 1: Ver online en Megavideo <span class="bold"></span></p>
<p><span>IDIOMA: SUB</span></p>
<p class="v_ico"><img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="Megavideo" /></p>
'''
patronvideos = '<div class="tit_opts"><a href="([^"]+)"[^>]*>[^<]+'
patronvideos += '<p>(.*?)</p>[^<]+'
patronvideos += '<p><span>(.*?)</span>'
'''
patronvideos = '<div class="tit_opts"><a href="([^"]+)".*?>[^<]+'
patronvideos += '<p>([^<]+)</p>[^<]+'
patronvideos += '<p><span>(.*?)</span>'
'''
matches = re.compile(patronvideos, re.DOTALL).findall(data)
itemlist = []
for match in matches:
logger.info("Encontrado iframe mirrors " + match[0])
# Lee el iframe
mirror = urlparse.urljoin(url, match[0].replace(" ", "%20"))
req = urllib2.Request(mirror)
req.add_header(
'User-Agent',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3'
)
response = urllib2.urlopen(req)
data = response.read()
response.close()
listavideos = servertools.findvideos(data)
for video in listavideos:
scrapedtitle = title.strip(
) + " " + match[1] + " " + match[2] + " " + video[0]
scrapedtitle = scrapertools.htmlclean(scrapedtitle)
scrapedurl = video[1]
server = video[2]
itemlist.append(
Item(channel=CHANNELNAME,
action="play",
title=scrapedtitle,
url=scrapedurl,
thumbnail=item.thumbnail,
plot=item.plot,
server=server,
folder=False))
return itemlist
def novedades(item):
logger.info("[xhamster.py] novedades")
# Descarga la página
data = scrapertools.cachePage(item.url)
#logger.info(data)
# Extrae las entradas
# seccion novedades
'''
<a href="/movies/496069/the_cheerleader.html" class="hRotator">
<img src="http://st5.xhamster.com/t/069/2_496069.jpg" height="120" width="160">
<img class="hSprite" src="http://static.xhamster.com/images/spacer.gif" sprite="http://st5.xhamster.com/t/069/s_496069.jpg" id="496069" onmouseover="hRotator.start2(this);" height="120" width="160">
</a>
<div class="moduleFeaturedTitle">
<a href="/movies/496069/the_cheerleader.html">The Cheerleader</a>
</div>
<div class="moduleFeaturedDetails">Runtime: 35m51s<br><span style="color: Green;">
'''
#patronvideos = '<p style="text-align: center;">.*?'
patronvideos = '<a href="(/movies/[^"]+.html)"[^>]*?>[^<]*?'
patronvideos += '<img src=\'([^\']+.xhamster.com[^\']+)\'[^>]+>[^<]*?'
patronvideos += '<img[^<]*?>[^<]*?</a>[^<]*?'
patronvideos += '<div[^<]*?>[^<]*?'
patronvideos += '<a href="/movies/[^"]+.html"[^>]*?>([^<]+)</a>[^<]*?'
patronvideos += '</div[^<]*?>[^<]*?'
patronvideos += '<div[^<]*?>Runtime: ([^<]+)<'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[2] + " [" + match[3] + "]"
scrapedurl = urlparse.urljoin(item.url, match[0])
scrapedthumbnail = match[1].replace(" ", "%20")
scrapedplot = scrapertools.htmlclean(match[2].strip())
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
itemlist.append(
Item(channel=CHANNELNAME,
action="findvideos",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot,
folder=True))
# Extrae el paginador
#<A HREF="/new/2.html">Next</A><
patronvideos = '<a href="(\/new\/[^\.]+\.html)"[^>]*?>Next[^<]*?<\/a>'
matches = re.compile(patronvideos, re.DOTALL | re.IGNORECASE).findall(data)
scrapertools.printMatches(matches)
if len(matches) > 0:
scrapedurl = urlparse.urljoin(item.url, matches[0])
logger.info("[xhamster.py] " + scrapedurl)
itemlist.append(
Item(channel=CHANNELNAME,
action="novedades",
title="!Página siguiente",
url=scrapedurl,
folder=True))
return itemlist
def list(params,url,category):
xbmc.output("[newcineonline.py] list")
# Descarga la página
data = scrapertools.cachePage(url)
#xbmc.output(data)
# Extrae las entradas (carpetas)
patronvideos = '<div id="post-info-mid">[^<]+<div class="post-title"><a href="([^"]+)">([^<]+)</a></div>'
patronvideos += '.*?<td class="post-story">.*?<tbody>.*?<img src="([^"]+)"[^>]+>(.*?)</tbody>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[1]
# URL
scrapedurl = urlparse.urljoin(url,match[0])
# Thumbnail
scrapedthumbnail = urlparse.urljoin(url,match[2])
# procesa el resto
scrapeddescription = match[3]
scrapeddescription = scrapertools.htmlclean(scrapeddescription)
scrapeddescription = scrapeddescription.replace("<!--colorstart:#589BB9-->","")
scrapeddescription = scrapeddescription.replace("<!--colorend-->","")
scrapeddescription = scrapeddescription.replace("<!--/colorend-->","")
scrapeddescription = scrapeddescription.replace("<!--/colorstart-->","")
scrapeddescription = scrapeddescription.strip()
# Depuracion
if (DEBUG):
xbmc.output("scrapedtitle="+scrapedtitle)
xbmc.output("scrapedurl="+scrapedurl)
xbmc.output("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
#addfolder( scrapedtitle , scrapedurl , "detail" )
xbmctools.addnewfolder( CHANNELNAME , "detail" , CHANNELNAME , scrapedtitle , scrapedurl , scrapedthumbnail , scrapeddescription )
# ------------------------------------------------------------------------------------
# Busca los enlaces a los mirrors, o a los capítulos de las series...
# ------------------------------------------------------------------------------------
xbmc.output("Busca el enlace de página siguiente...")
try:
# La siguiente página
patronvideos = '<a href\="([^"]+)"><span class\="navigation"[^>]+>Sigu'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
url = matches[0]
addfolder("!Siguiente",url,"list")
except:
xbmc.output("No encuentro la pagina...")
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=int( sys.argv[ 1 ] ), category=category )
# Disable sorting...
xbmcplugin.addSortMethod( handle=int( sys.argv[ 1 ] ), sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory( handle=int( sys.argv[ 1 ] ), succeeded=True )
def series(item):
logger.info("[cinetube.py] series")
itemlist = []
# Descarga la página
data = scrapertools.cachePage(item.url)
logger.info("Pagina de %d caracteres" % len(data))
# Extrae las entradas
'''
<li>
<a href="/series/en-tierra-de-lobos/temporada-1/capitulo-12/"><img src="http://caratulas.cinetube.es/series/8912.jpg" alt="peli" /></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/espanol.png" alt="espanol" /> <img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="megavideo.png" /> <img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> <p><span class="rosa"></span></p></div>
<p class="tit_ficha"><a class="tit_ficha" title="Ver serie Tierra de lobos" href="/series/en-tierra-de-lobos/temporada-1/capitulo-12/">Tierra de lobos </a></p>
<p class="tem_fich">1a Temporada - Cap 12</p>
</li>
'''
'''
<li>
<a href="/series/gabriel-un-amor-inmortal/"><img src="http://caratulas.cinetube.es/series/7952.jpg" alt="peli" /></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/latino.png" alt="" /><img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div>
<p class="tit_ficha">Gabriel, un amor inmortal </p>
</li>
'''
'''
<li>
<a href="/series-anime/star-driver-kagayaki-no-takuto/temporada-1/capitulo-13/"><img src="http://caratulas.cinetube.es/seriesa/9009.jpg" alt="peli" /></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/sub.png" alt="sub" /> <img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="megavideo.png" /> <img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> <p><span class="rosa"></span></p></div>
<p class="tit_ficha"><a class="tit_ficha" title="Ver serie Star Driver Kagayaki no Takuto" href="/series-anime/star-driver-kagayaki-no-takuto/temporada-1/capitulo-13/">Star Driver Kagayaki no Takuto </a></p>
<p class="tem_fich">1a Temporada - Cap 13</p>
</li>
'''
patronvideos = '<li>[^<]+'
patronvideos += '<a href="([^"]+)"><img src="([^"]+)"[^>]*></a>[^<]+'
patronvideos += '<div class="icos_lg">(.*?)</div>[^<]+'
patronvideos += '<p class="tit_ficha">(.*?)</p>[^<]+'
patronvideos += '(?:<p class="tem_fich">([^<]+)</p>)?'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[3].strip()
if len(match) >= 5:
scrapedtitle = scrapedtitle + " " + match[4]
matchesconectores = re.compile('<img.*?alt="([^"]*)"',
re.DOTALL).findall(match[2])
conectores = ""
for matchconector in matchesconectores:
logger.info("matchconector=" + matchconector)
if matchconector == "":
matchconector = "megavideo"
conectores = conectores + matchconector + "/"
if len(matchesconectores) > 0:
scrapedtitle = scrapedtitle + " (" + conectores[:-1] + ")"
scrapedtitle = scrapedtitle.replace("megavideo/megavideo", "megavideo")
scrapedtitle = scrapedtitle.replace("megavideo/megavideo", "megavideo")
scrapedtitle = scrapedtitle.replace("megavideo/megavideo", "megavideo")
scrapedtitle = scrapedtitle.replace("descarga directa", "DD")
scrapedtitle = scrapertools.htmlclean(scrapedtitle)
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedplot = ""
scrapedurl = urlparse.urljoin(item.url, match[0])
scrapedthumbnail = match[1]
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
itemlist.append(
Item(channel=CHANNELNAME,
action="temporadas",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot,
folder=True))
# Paginador
#<li class="navs"><a class="pag_next" href="/peliculas-todas/2.html"></a></li>
patronvideos = '<li class="navs"><a class="pag_next" href="([^"]+)"></a></li>'
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=CHANNELNAME,
action="series",
title="!Página siguiente",
url=scrapedurl,
folder=True))
return itemlist
def ddpostdetail(params, url, category):
logger.info("[mcanime.py] ddpostdetail")
title = urllib.unquote_plus(params.get("title"))
thumbnail = urllib.unquote_plus(params.get("thumbnail"))
plot = unicode(xbmc.getInfoLabel("ListItem.Plot"), "utf-8")
# Descarga la p·gina
data = scrapertools.cachePage(url)
#logger.info(data)
# Foto de la serie de la enciclopedia
patron = '<img src="([^"]+)" width="300".*?class="title_pic" />'
matches = re.compile(patron, re.DOTALL).findall(data)
if len(matches) > 0:
thumbnail = matches[0]
# Argumento - texto del post
patron = '<div id="download_detail">(.*?)</div>'
matches = re.compile(patron, re.DOTALL).findall(data)
if len(matches) > 0:
plot = scrapertools.htmlclean(matches[0])
plot = plot.replace("\r\n", " ")
plot = plot.replace("\r", " ")
plot = plot.replace("\n", " ")
plot = plot.strip()
# ------------------------------------------------------------------------------------
# Busca los enlaces a los videos
# ------------------------------------------------------------------------------------
listavideos = servertools.findvideos(data)
i = 1
for video in listavideos:
try:
fulltitle = unicode(title.strip() + " (%d) " + video[0],
"utf-8").encode("iso-8859-1")
except:
fulltitle = title.strip() + " (%d) " + video[0]
fulltitle = fulltitle % i
i = i + 1
videourl = video[1]
server = video[2]
#logger.info("videotitle="+urllib.quote_plus( videotitle ))
#logger.info("plot="+urllib.quote_plus( plot ))
#plot = ""
#logger.info("title="+urllib.quote_plus( title ))
xbmctools.addnewvideo(CHANNELNAME, "play", category, server, fulltitle,
videourl, thumbnail, plot)
# ------------------------------------------------------------------------------------
# ------------------------------------------------------------------------------------
# AÒade la opciÛn "AÒadir todos los vÌdeos a la lista de descarga"
# ------------------------------------------------------------------------------------
xbmctools.addnewvideo(
CHANNELNAME, "addalltodownloadlist", title, "",
"(AÒadir todos los vÌdeos a la lista de descarga)", url, thumbnail,
plot)
# Cierra el directorio
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
xbmcplugin.addSortMethod(handle=pluginhandle,
sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def ddseriedetail(params, url, category):
logger.info("[mcanime.py] ddseriedetail")
title = urllib.unquote_plus(params.get("title"))
thumbnail = urllib.unquote_plus(params.get("thumbnail"))
plot = urllib.unquote_plus(params.get("plot"))
# Descarga la p·gina
data = scrapertools.cachePage(url)
# Foto de la serie de la enciclopedia
patron = '<img src="([^"]+)" width="300".*?class="title_pic" />'
matches = re.compile(patron, re.DOTALL).findall(data)
if len(matches) > 0:
thumbnail = matches[0]
logger.info("[mcanime.py] thumbnail=" + thumbnail)
# Argumento
patron = '<h6>Sinopsis.*?</h6>(.*?)<h6>'
matches = re.compile(patron, re.DOTALL).findall(data)
if len(matches) > 0:
plot = matches[0]
plot = plot.replace("\n", " ")
plot = plot.replace("\r", " ")
plot = plot.replace("\r\n", " ")
plot = plot.strip()
plot = scrapertools.htmlclean(matches[0])
logger.info("[mcanime.py] plot=" + plot)
# Aportaciones de los usuarios
patron = '<h6 class="m">Por los Usuarios</h6>[^<]+'
patron += '<div id="user_actions">(.*?)</div>'
matches = re.compile(patron, re.DOTALL).findall(data)
if len(matches) > 0:
data = matches[0]
#logger.info("[mcanime.py] data="+data)
patron = '<ul class="dd_row">[^<]+'
patron += '<li class="dd_type"><img[^>]+></li>[^<]+'
patron += '<li class="dd_update"> <img[^>]+>([^<]+)</li>[^<]+'
patron += '<li class="dd_title">[^<]+'
patron += '<h5><a href="([^"]+)">([^<]+)</a></h5>'
matches = re.compile(patron, re.DOTALL).findall(data)
for match in matches:
# Atributos
scrapedtitle = match[2].strip() + " (" + match[0].strip() + ")"
scrapedurl = urlparse.urljoin(url, match[1])
scrapedthumbnail = thumbnail
scrapedplot = plot
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" +
scrapedurl + "], thumbnail=[" + scrapedthumbnail +
"]")
# AÒade al listado de XBMC
xbmctools.addnewfolder(CHANNELNAME, "ddpostdetail", category,
scrapedtitle, scrapedurl, scrapedthumbnail,
scrapedplot)
# Cierra el directorio
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
xbmcplugin.addSortMethod(handle=pluginhandle,
sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def list(params, url, category):
logger.info("[newcineonline.py] list")
# Descarga la página
data = scrapertools.cachePage(url)
#logger.info(data)
# Extrae las entradas (carpetas)
patronvideos = '<div id="post-info-mid">[^<]+<div class="post-title"><a href="([^"]+)">([^<]+)</a></div>'
patronvideos += '.*?<td class="post-story">.*?<tbody>.*?<img src="([^"]+)"[^>]+>(.*?)</tbody>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[1]
# URL
scrapedurl = urlparse.urljoin(url, match[0])
# Thumbnail
scrapedthumbnail = urlparse.urljoin(url, match[2])
# procesa el resto
scrapeddescription = match[3]
scrapeddescription = scrapertools.htmlclean(scrapeddescription)
scrapeddescription = scrapeddescription.replace(
"<!--colorstart:#589BB9-->", "")
scrapeddescription = scrapeddescription.replace("<!--colorend-->", "")
scrapeddescription = scrapeddescription.replace("<!--/colorend-->", "")
scrapeddescription = scrapeddescription.replace(
"<!--/colorstart-->", "")
scrapeddescription = scrapeddescription.strip()
# Depuracion
if (DEBUG):
logger.info("scrapedtitle=" + scrapedtitle)
logger.info("scrapedurl=" + scrapedurl)
logger.info("scrapedthumbnail=" + scrapedthumbnail)
# Añade al listado de XBMC
#addfolder( scrapedtitle , scrapedurl , "detail" )
xbmctools.addnewfolder(CHANNELNAME, "detail", CHANNELNAME,
scrapedtitle, scrapedurl, scrapedthumbnail,
scrapeddescription)
# ------------------------------------------------------------------------------------
# Busca los enlaces a los mirrors, o a los capítulos de las series...
# ------------------------------------------------------------------------------------
logger.info("Busca el enlace de página siguiente...")
try:
# La siguiente página
patronvideos = '<a href\="([^"]+)"><span class\="navigation"[^>]+>Sigu'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
url = matches[0]
addfolder("!Siguiente", url, "list")
except:
logger.info("No encuentro la pagina...")
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=int(sys.argv[1]), category=category)
# Disable sorting...
xbmcplugin.addSortMethod(handle=int(sys.argv[1]),
sortMethod=xbmcplugin.SORT_METHOD_NONE)
# End of directory...
xbmcplugin.endOfDirectory(handle=int(sys.argv[1]), succeeded=True)
def findvideos(data):
logger.info("[servertools.py] findvideos")
encontrados = set()
devuelve = []
#Megavideo con partes para cinetube
logger.info ("0) Megavideo con partes para cinetube")
patronvideos = 'id.+?http://www.megavideo.com..v.(.+?)".+?(parte\d+)'
#id="http://www.megavideo.com/?v=CN7DWZ8S"><a href="#parte1">Parte 1 de 2</a></li>
matches = re.compile(patronvideos).findall(data)
for match in matches:
titulo = "[Megavideo " + match[1] + "]"
url = match[0]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("1) Megavideo con titulo...")
patronvideos = '<div align="center">([^<]+)<.*?<param name="movie" value="http://www.megavideo.com/v/([A-Z0-9a-z]{8})[^"]+"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[0].strip()
if titulo == "":
titulo = "[Megavideo]"
url = match[1]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("1b) Megavideo con titulo...")
patronvideos = '<a href\="http\:\/\/www.megavideo.com/\?v\=([A-Z0-9a-z]{8})".*?>([^<]+)</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[1].strip()
if titulo == "":
titulo = "[Megavideo]"
url = match[0]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("1c) Megavideo sin titulo...")
#http://www.megavideo.com/?v=OYGXMZBM
patronvideos = 'http\:\/\/www.megavideo.com/\?v\=([A-Z0-9a-z]{8})"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
titulo = ""
if titulo == "":
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("1d) Megavideo sin titulo...")
#http://www.megavideo.com/?v=OYGXMZBM
patronvideos = 'http\:\/\/www.megavideo.com/\?v\=([A-Z0-9a-z]{8})'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
titulo = ""
if titulo == "":
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megaupload con título
logger.info("1k1) Megaupload...")
patronvideos = '<a.*?href="http://www.megaupload.com/\?d=([A-Z0-9a-z]{8})".*?>(.*?)</a>'
matches = re.compile(patronvideos).findall(data)
for match in matches:
titulo = scrapertools.htmlclean(match[1].strip())+" - [Megaupload]"
url = match[0]
if url not in encontrados:
logger.info(" titulo="+titulo)
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megaupload' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#2/12/2010 Megaupload
logger.info("1k) Megaupload...")
patronvideos = 'http\://www.megaupload.com/(?:es/)?\?.*?d\=([A-Z0-9a-z]{8})(?:[^>]*>([^<]+)</a>)?'
matches = re.compile(patronvideos).findall(data)
for match in matches:
if match[1]<>"":
titulo = match[1].strip()+" - [Megaupload]"
else:
titulo = "[Megaupload]"
url = match[0]
if url not in encontrados:
logger.info(" titulo="+titulo)
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megaupload' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos sin título
logger.info("2) Megavideo sin titulo...")
patronvideos = '<param name="movie" value="http://wwwstatic.megavideo.com/mv_player.swf\?v=([^"]+)">'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Vreel - Vídeos con título
logger.info( "3) Vreel con título...")
patronvideos = '<div align="center"><b>([^<]+)</b>.*?<a href\="(http://beta.vreel.net[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[0].strip()
if titulo == "":
titulo = "[Vreel]"
url = match[1]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Vreel' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Vreel - Vídeos con título
logger.info("4) Vreel con titulo...")
patronvideos = '<div align="center">([^<]+)<.*?<a href\="(http://beta.vreel.net[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[0].strip()
if titulo == "":
titulo = "[Vreel]"
url = match[1]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Vreel' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# STAGEVU
logger.info("7) Stagevu sin título...")
patronvideos = '"(http://stagevu.com[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Stagevu]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# TU.TV
logger.info("8) Tu.tv sin título...")
patronvideos = '<param name="movie" value="(http://tu.tv[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[tu.tv]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'tu.tv' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# TU.TV
logger.info("9) Tu.tv sin título...")
#<param name="movie" value="http://www.tu.tv/tutvweb.swf?kpt=aHR0cDovL3d3dy50dS50di92aWRlb3Njb2RpL24vYS9uYXppcy11bi1hdmlzby1kZS1sYS1oaXN0b3JpYS0xLTYtbGEtbC5mbHY=&xtp=669149_VIDEO"
patronvideos = '<param name="movie" value="(http://www.tu.tv[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[tu.tv]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'tu.tv' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("9b) Tu.tv sin título...")
#<embed src="http://tu.tv/tutvweb.swf?kpt=aHR0cDovL3d3dy50dS50di92aW
patronvideos = '<embed src="(http://tu.tv/[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[tu.tv]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'tu.tv' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos sin título
logger.info("10 ) Megavideo sin titulo...")
patronvideos = '"http://www.megavideo.com/v/([A-Z0-9a-z]{8})[^"]+"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos sin título
logger.info("11) Megavideo sin titulo...")
patronvideos = '"http://www.megavideo.com/v/([A-Z0-9a-z]{8})[^"]+"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# STAGEVU
'''
logger.info("12) Stagevu...")
patronvideos = '(http://stagevu.com[^<]+)<'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "Ver el vídeo en Stagevu"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
'''
# Vreel - Vídeos sin título
logger.info("13) Vreel sin titulo...")
patronvideos = '(http://beta.vreel.net[^<]+)<'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Vreel]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Vreel' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("14) Megavideo con titulo...")
patronvideos = '<a href="http://www.megavideo.com/\?v\=([^"]+)".*?>(.*?)</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[1].strip()
if titulo == "":
titulo = "[Megavideo]"
url = match[0]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("14b) Megavideo con titulo...")
patronvideos = '<param name="movie" value=".*?v\=([A-Z0-9]{8})" />'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Stagevu...")
patronvideos = '"http://stagevu.com.*?uid\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Stagevu]"
url = "http://stagevu.com/video/"+match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Stagevu...")
patronvideos = "'http://stagevu.com.*?uid\=([^']+)'"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Stagevu]"
url = "http://stagevu.com/video/"+match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Megavideo... formato d=XXXXXXX")
patronvideos = 'http://www.megavideo.com/.*?\&d\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Megavideo... formato watchanimeon")
patronvideos = 'src="http://wwwstatic.megavideo.com/mv_player.swf.*?\&v\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Megaupload... formato megavideo con d=XXXXXXX")
patronvideos = 'http://www.megavideo.com/\?d\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megaupload' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Movshare...")
patronvideos = '"(http://www.movshare.net/video/[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Movshare]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'movshare' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Movshare...")
patronvideos = "'(http://www.movshare.net/embed/[^']+)'"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Movshare]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'movshare' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Veoh...")
patronvideos = '"http://www.veoh.com/.*?permalinkId=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Veoh]"
if match.count("&")>0:
primera = match.find("&")
url = match[:primera]
else:
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'veoh' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Directo - myspace")
patronvideos = 'flashvars="file=(http://[^\.]+.myspacecdn[^\&]+)&'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Directo - myspace")
patronvideos = '(http://[^\.]+\.myspacecdn.*?\.flv)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Directo - ning")
patronvideos = '(http://api.ning.com.*?\.flv)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Videoweed...")
patronvideos = '(http://www.videoweed.com/file/*?\.flv)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Videoweed]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'videoweed' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) YouTube...")
patronvideos = '"http://www.youtube.com/v/([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[YouTube]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'youtube' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#http://video.ak.facebook.com/cfs-ak-ash2/33066/239/133241463372257_27745.mp4
logger.info("0) Facebook...")
patronvideos = '(http://video.ak.facebook.com/.*?\.mp4)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Facebook]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'facebook' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#http://www.4shared.com/embed/392975628/ff297d3f
logger.info("0) 4shared...")
patronvideos = '"(http://www.4shared.com.*?)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[4shared]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , '4shared' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#http://www.4shared.com/embed/392975628/ff297d3f
logger.info("0) 4shared...")
patronvideos = "'(http://www.4shared.com.*?)'"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[4shared]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , '4shared' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#file=http://es.video.netlogstatic.com//v/oo/004/398/4398830.flv&
#http://es.video.netlogstatic.com//v/oo/004/398/4398830.flv
logger.info("0) netlogicstat...")
patronvideos = "file\=(http\:\/\/es.video.netlogstatic[^\&]+)\&"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
return devuelve
def estrenos(params, url, category):
logger.info("[mcanime.py] estrenos")
# Descarga la p·gina
data = scrapertools.cachePage(url)
#logger.info(data)
# Extrae las entradas (carpetas)
'''
<dl id="addRow9203" class="min row1">
<dd class="thumb">
<img src="/images/anime/th_9203.jpg" width="75" height="100" alt="" />
</dd>
<dt><a href="/enciclopedia/anime/cobra_the_animation_rokunin_no_yuushi/9203">Cobra The Animation: Rokunin no Yuushi</a> <i>(Serie)</i></dt>
<dd>Cobra es un conocido pirata espacial, pero decide cambiar su cara y borrar todas sus memorias. El ahora es un hombre normal, con un trabajo normal y una vida aburrida, pero comienza a recordar su verdadera identidad y sus aventuras comienzan de nuevo. <a href="/enciclopedia/anime/cobra_the_animation_rokunin_no_yuushi/9203">leer m·s.</a></dd>
<dd class="small mgn"><a href="/descarga_directa/anime/cobra_the_animation_rokunin_no_yuushi/9203" class="srch_dd">Descargar <img width="14" height="14" src="/images/dds/download_icon.gif" alt="[DD]" /></a></dd> </dl>
'''
patron = '<dl id="[^"]+" class="min row.">(.*?)</dl>'
matches = re.compile(patron, re.DOTALL).findall(data)
for match in matches:
data = match
patron = '<dd class="thumb">[^<]+'
patron += '<img src="([^"]+)"[^>]+>[^<]+'
patron += '</dd>[^<]+'
patron += '<dt><a href="[^"]+">([^<]+)</a>\s*<i>([^<]+)</i>\s*</dt>[^<]+'
matches2 = re.compile(patron, re.DOTALL).findall(data)
if len(matches2) > 0:
scrapedtitle = matches2[0][1].strip() + " " + matches2[0][2].strip(
)
scrapedthumbnail = urlparse.urljoin(url, matches2[0][0])
scrapedplot = ""
scrapedurl = ""
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" +
scrapedurl + "], thumbnail=[" + scrapedthumbnail +
"]")
patron = '</dt>(.*?)<dd class="small mgn"><a href="([^"]+)"'
matches2 = re.compile(patron, re.DOTALL).findall(data)
if len(matches2) > 0:
try:
scrapedplot = unicode(matches2[0][0].strip(),
"utf-8").encode("iso-8859-1")
except:
scrapedplot = matches2[0][0].strip()
scrapedplot = scrapertools.htmlclean(scrapedplot)
scrapedplot = scrapedplot.replace("\n", " ")
scrapedplot = scrapedplot.replace("\r", " ")
scrapedplot = scrapedplot.replace("\r\n", " ")
scrapedurl = urlparse.urljoin(url, matches2[0][1])
# AÒade al listado de XBMC
xbmctools.addnewfolder(CHANNELNAME, "ddseriedetail", category,
scrapedtitle, scrapedurl, scrapedthumbnail,
scrapedplot)
# Propiedades
xbmcplugin.setPluginCategory(handle=int(sys.argv[1]), category=category)
xbmcplugin.addSortMethod(handle=int(sys.argv[1]),
sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=int(sys.argv[1]), succeeded=True)
def findvideos(item):
logger.info("[cinetube.py] findvideos")
url = item.url
title = item.title
thumbnail = item.thumbnail
plot = item.plot
# Descarga la pagina
data = scrapertools.cachePage(url)
#logger.info(data)
# Busca el argumento
patronvideos = '<div class="ficha_des">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matches)>0:
plot = scrapertools.htmlclean(matches[0])
logger.info("plot actualizado en detalle");
else:
logger.info("plot no actualizado en detalle");
# Busca el thumbnail
patronvideos = '<div class="ficha_img pelicula_img">[^<]+'
patronvideos += '<img src="([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matches)>0:
thumbnail = matches[0]
logger.info("thumb actualizado en detalle");
else:
logger.info("thumb no actualizado en detalle");
# Busca los enlaces a los mirrors, o a los capitulos de las series...
'''
FORMATO EN SERIES
<div class="tit_opts"><a href="/series/hawai-five/temporada-1/capitulo-13/212498.html">
<p>Opción 1: Ver online en Megavideo <span class="bold"></span></p>
<p><span>IDIOMA: SUB</span></p>
<p class="v_ico"><img src="http://caratulas.cinetube.es/img/cont/megavideo.png" alt="Megavideo" /></p>
'''
patronvideos = '<div class="tit_opts"><a href="([^"]+)"[^>]*>[^<]+'
patronvideos += '<p>(.*?)</p>[^<]+'
patronvideos += '<p><span>(.*?)</span>'
'''
patronvideos = '<div class="tit_opts"><a href="([^"]+)".*?>[^<]+'
patronvideos += '<p>([^<]+)</p>[^<]+'
patronvideos += '<p><span>(.*?)</span>'
'''
matches = re.compile(patronvideos,re.DOTALL).findall(data)
itemlist = []
for match in matches:
logger.info("Encontrado iframe mirrors "+match[0])
# Lee el iframe
mirror = urlparse.urljoin(url,match[0].replace(" ","%20"))
req = urllib2.Request(mirror)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3')
response = urllib2.urlopen(req)
data=response.read()
response.close()
listavideos = servertools.findvideos(data)
for video in listavideos:
scrapedtitle = title.strip() + " " + match[1] + " " + match[2] + " " + video[0]
scrapedtitle = scrapertools.htmlclean(scrapedtitle)
scrapedurl = video[1]
server = video[2]
itemlist.append( Item(channel=CHANNELNAME, action="play" , title=scrapedtitle , url=scrapedurl, thumbnail=item.thumbnail, plot=item.plot, server=server, folder=False))
return itemlist
def generico(params,url,category):
xbmc.output("[rtveprogramas.py] generico")
# El parametro allowblanks permite que haya vídeos sin título
allowblanktitles = False
if category=="allowblanktitles":
allowblanktitles = True
category = CHANNELNAME
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
#xbmc.output(data)
# --------------------------------------------------------
# Extrae las categorias (carpetas)
# --------------------------------------------------------
patron = '<div class="news[^"]+">(.*?</div>)'
bloques = re.compile(patron,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(bloques)
for bloque in bloques:
'''
##############################################################################################################
<span class="imgL"><a href="/mediateca/videos/20100225/aguila-roja-cap21/705225.shtml" title=""><img src="/imagenes/jpg/1267703487420.jpg" alt="" title=""/></a></span>
<h3 class="M ">
<a href="/mediateca/videos/20100225/aguila-roja-cap21/705225.shtml" title="Capítulo 21">Capítulo 21</a>
</h3>
<div class="chapeaux">Emitido el 25/02/10</div>
##############################################################################################################
<span class="imgL"><a href="/mediateca/videos/20100218/aguila-roja-cap20/698541.shtml" title="Capítulo 20"><img src="/imagenes/capitulo-20/1267703445964.jpg" alt="Capítulo 20" title="Capítulo 20"/></a></span>
<h3 class="M ">
<a href="/mediateca/videos/20100218/aguila-roja-cap20/698541.shtml" title="Capítulo 20">Capítulo 20</a>
</h3>
<div class="chapeaux">Emitido el 18/02/10</div>
##############################################################################################################
'''
scrapedtitle = ""
scrapedurl = ""
scrapedthumbnail = ""
scrapedplot = ""
# Enlace a la página y título
patron = '<a href="([^"]+)"[^>]+>([^<]+)<'
matches = re.compile(patron,re.DOTALL).findall(bloque)
if DEBUG: scrapertools.printMatches(matches)
if len(matches)>0:
scrapedurl = urlparse.urljoin(url, matches[0][0])
scrapedtitle = scrapertools.entityunescape(matches[0][1])
# Si no tiene titulo busca el primer enlace que haya
if scrapedurl=="":
# Enlace a la página y título
patron = '<a href="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(bloque)
if DEBUG: scrapertools.printMatches(matches)
if len(matches)>0:
scrapedurl = urlparse.urljoin(url, matches[0])
# Thumbnail
patron = '<img src="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(bloque)
if DEBUG: scrapertools.printMatches(matches)
if len(matches)>0:
scrapedthumbnail = urlparse.urljoin(url, matches[0])
# Argumento
patron = '<div class="chapeaux">(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(bloque)
if DEBUG: scrapertools.printMatches(matches)
if len(matches)>0:
scrapedplot = scrapertools.htmlclean(matches[0])
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
if allowblanktitles:
titulos = scrapedurl.split("/")
scrapedtitle = titulos[ len(titulos)-2 ]
# Añade al listado de XBMC
if scrapedtitle<>"" and scrapedurl<>"":
xbmctools.addnewvideo( "rtve" , "play" , category , "Directo" , scrapedtitle , scrapedurl , scrapedthumbnail , scrapedplot )
# Cierra el directorio
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def listmirrors(params,url,category):
logger.info("[gratisdocumentales.py] detail")
title = urllib.unquote_plus( params.get("title") )
thumbnail = urllib.unquote_plus( params.get("thumbnail") )
#plot = unicode( xbmc.getInfoLabel( "ListItem.Plot" ), "utf-8" )
plot = urllib.unquote_plus( params.get("plot") )
# ------------------------------------------------------------------------------------
# Descarga la página
# ------------------------------------------------------------------------------------
data = scrapertools.cachePage(url)
#logger.info(data)
# ------------------------------------------------------------------------------------
# Busca el argumento
# ------------------------------------------------------------------------------------
patronvideos = '<div class="ficha_des">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matches)>0:
plot = scrapertools.htmlclean(matches[0])
# ------------------------------------------------------------------------------------
# Busca el thumbnail
# ------------------------------------------------------------------------------------
patronvideos = '<div class="ficha_img pelicula_img">[^<]+'
patronvideos += '<img src="([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matches)>0:
thumbnail = matches[0]
# ------------------------------------------------------------------------------------
# Busca los enlaces a los mirrors, o a los capítulos de las series...
# ------------------------------------------------------------------------------------
# url = "http://www.gratisdocumentales.es/inc/mostrar_contenido.php?sec=pelis_ficha&zona=online&id=video-4637"
patronvideos = '<div class="ver_des_peli iframe2">[^<]+'
patronvideos += '<ul class="tabs-nav" id="([^"]+)">'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
'''
<div id="ficha_ver_peli">
<div class="v_online">
<h2>Ver online <span>El destino de Nunik</span></h2>
<div class="opstions_pelicula_list">
<div class="tit_opts" style="cursor:pointer;" onclick="location.href='http://www.gratisdocumentales.es/peliculas/drama/el-destino-de-nunik_espanol-dvd-rip-megavideo-6026.html'">
<p>Mirror 1: Megavideo</p>
<p><span>CALIDAD: DVD-RIP | IDIOMA: ESPAÑOL</span></p>
<p class="v_ico"><img src="http://caratulas.gratisdocumentales.es/img/cont/megavideo.png" alt="Megavideo" /></p>
</div>
<div class="tit_opts" style="cursor:pointer;" onclick="location.href='http://www.gratisdocumentales.es/peliculas/drama/el-destino-de-nunik_espanol-dvd-rip-megavideo-6027.html'">
<p>Mirror 2: Megavideo</p>
<p><span>CALIDAD: DVD-RIP | IDIOMA: ESPAÑOL</span></p>
<p class="v_ico"><img src="http://caratulas.gratisdocumentales.es/img/cont/megavideo.png" alt="Megavideo" /></p>
</div>
</div>
</div>
</div>
'''
data = scrapertools.cachePage("http://www.gratisdocumentales.es/inc/mostrar_contenido.php?sec=pelis_ficha&zona=online&id="+matches[0])
patronvideos = '<div class="tit_opts" style="cursor:pointer;" onclick="location.href=\'([^\']+)\'">[^<]+'
patronvideos += '<p>([^<]+)</p>[^<]+'
patronvideos += '<p><span>([^<]+)</span>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
logger.info("Encontrado iframe mirrors "+match[0])
# Lee el iframe
mirror = urlparse.urljoin(url,match[0].replace(" ","%20"))
req = urllib2.Request(mirror)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3')
response = urllib2.urlopen(req)
data=response.read()
response.close()
listavideos = servertools.findvideos(data)
for video in listavideos:
videotitle = video[0]
scrapedurl = video[1]
server = video[2]
xbmctools.addnewvideo( CHANNELNAME , "play" , category , server , title.strip()+" "+match[1]+" "+match[2]+" "+videotitle , scrapedurl , thumbnail , plot )
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=int( sys.argv[ 1 ] ), category=category )
xbmcplugin.addSortMethod( handle=int( sys.argv[ 1 ] ), sortMethod=xbmcplugin.SORT_METHOD_NONE )
xbmcplugin.endOfDirectory( handle=int( sys.argv[ 1 ] ), succeeded=True )
def findvideos(data):
logger.info("[servertools.py] findvideos")
encontrados = set()
devuelve = []
#Megavideo con partes para cinetube
logger.info ("0) Megavideo con partes para cinetube")
patronvideos = 'id.+?http://www.megavideo.com..v.(.+?)".+?(parte\d+)'
#id="http://www.megavideo.com/?v=CN7DWZ8S"><a href="#parte1">Parte 1 de 2</a></li>
matches = re.compile(patronvideos).findall(data)
for match in matches:
titulo = "[Megavideo " + match[1] + "]"
url = match[0]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("1) Megavideo con titulo...")
patronvideos = '<div align="center">([^<]+)<.*?<param name="movie" value="http://www.megavideo.com/v/([A-Z0-9a-z]{8})[^"]+"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[0].strip()
if titulo == "":
titulo = "[Megavideo]"
url = match[1]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("1b) Megavideo con titulo...")
patronvideos = '<a href\="http\:\/\/www.megavideo.com/\?v\=([A-Z0-9a-z]{8})".*?>([^<]+)</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[1].strip()
if titulo == "":
titulo = "[Megavideo]"
url = match[0]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("1c) Megavideo sin titulo...")
#http://www.megavideo.com/?v=OYGXMZBM
patronvideos = 'http\:\/\/www.megavideo.com/\?v\=([A-Z0-9a-z]{8})"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
titulo = ""
if titulo == "":
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("1d) Megavideo sin titulo...")
#http://www.megavideo.com/?v=OYGXMZBM
patronvideos = 'http\:\/\/www.megavideo.com/\?v\=([A-Z0-9a-z]{8})'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
titulo = ""
if titulo == "":
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megaupload con título
logger.info("1k1) Megaupload...")
patronvideos = '<a.*?href="http://www.megaupload.com/\?d=([A-Z0-9a-z]{8})".*?>(.*?)</a>'
matches = re.compile(patronvideos).findall(data)
for match in matches:
titulo = scrapertools.htmlclean(match[1].strip())+" - [Megaupload]"
url = match[0]
if url not in encontrados:
logger.info(" titulo="+titulo)
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megaupload' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#2/12/2010 Megaupload
logger.info("1k) Megaupload...")
patronvideos = 'http\://www.megaupload.com/(?:es/)?\?.*?d\=([A-Z0-9a-z]{8})(?:[^>]*>([^<]+)</a>)?'
matches = re.compile(patronvideos).findall(data)
for match in matches:
if match[1]<>"":
titulo = match[1].strip()+" - [Megaupload]"
else:
titulo = "[Megaupload]"
url = match[0]
if url not in encontrados:
logger.info(" titulo="+titulo)
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megaupload' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos sin título
logger.info("2) Megavideo sin titulo...")
patronvideos = '<param name="movie" value="http://wwwstatic.megavideo.com/mv_player.swf\?v=([^"]+)">'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Vreel - Vídeos con título
logger.info( "3) Vreel con título...")
patronvideos = '<div align="center"><b>([^<]+)</b>.*?<a href\="(http://beta.vreel.net[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[0].strip()
if titulo == "":
titulo = "[Vreel]"
url = match[1]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Vreel' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Vreel - Vídeos con título
logger.info("4) Vreel con titulo...")
patronvideos = '<div align="center">([^<]+)<.*?<a href\="(http://beta.vreel.net[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[0].strip()
if titulo == "":
titulo = "[Vreel]"
url = match[1]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Vreel' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# STAGEVU
logger.info("7) Stagevu sin título...")
patronvideos = '"(http://stagevu.com[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Stagevu]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# TU.TV
logger.info("8) Tu.tv sin título...")
patronvideos = '<param name="movie" value="(http://tu.tv[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[tu.tv]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'tu.tv' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# TU.TV
logger.info("9) Tu.tv sin título...")
#<param name="movie" value="http://www.tu.tv/tutvweb.swf?kpt=aHR0cDovL3d3dy50dS50di92aWRlb3Njb2RpL24vYS9uYXppcy11bi1hdmlzby1kZS1sYS1oaXN0b3JpYS0xLTYtbGEtbC5mbHY=&xtp=669149_VIDEO"
patronvideos = '<param name="movie" value="(http://www.tu.tv[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[tu.tv]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'tu.tv' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("9b) Tu.tv sin título...")
#<embed src="http://tu.tv/tutvweb.swf?kpt=aHR0cDovL3d3dy50dS50di92aW
patronvideos = '<embed src="(http://tu.tv/[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[tu.tv]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'tu.tv' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos sin título
logger.info("10 ) Megavideo sin titulo...")
patronvideos = '"http://www.megavideo.com/v/([A-Z0-9a-z]{8})[^"]+"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos sin título
logger.info("11) Megavideo sin titulo...")
patronvideos = '"http://www.megavideo.com/v/([A-Z0-9a-z]{8})[^"]+"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# STAGEVU
'''
logger.info("12) Stagevu...")
patronvideos = '(http://stagevu.com[^<]+)<'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "Ver el vídeo en Stagevu"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
'''
# Vreel - Vídeos sin título
logger.info("13) Vreel sin titulo...")
patronvideos = '(http://beta.vreel.net[^<]+)<'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Vreel]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Vreel' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("14) Megavideo con titulo...")
patronvideos = '<a href="http://www.megavideo.com/\?v\=([^"]+)".*?>(.*?)</a>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = match[1].strip()
if titulo == "":
titulo = "[Megavideo]"
url = match[0]
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
# Megavideo - Vídeos con título
logger.info("14b) Megavideo con titulo...")
patronvideos = '<param name="movie" value=".*?v\=([A-Z0-9]{8})" />'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Stagevu...")
patronvideos = '"http://stagevu.com.*?uid\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Stagevu]"
url = "http://stagevu.com/video/"+match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Stagevu...")
patronvideos = "'http://stagevu.com.*?uid\=([^']+)'"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Stagevu]"
url = "http://stagevu.com/video/"+match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Stagevu' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Megavideo... formato d=XXXXXXX")
patronvideos = 'http://www.megavideo.com/.*?\&d\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Megavideo... formato watchanimeon")
patronvideos = 'src="http://wwwstatic.megavideo.com/mv_player.swf.*?\&v\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megavideo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Megaupload... formato megavideo con d=XXXXXXX")
patronvideos = 'http://www.megavideo.com/\?d\=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Megavideo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Megaupload' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Movshare...")
patronvideos = '"(http://www.movshare.net/video/[^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Movshare]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'movshare' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Movshare...")
patronvideos = "'(http://www.movshare.net/embed/[^']+)'"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Movshare]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'movshare' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Veoh...")
patronvideos = '"http://www.veoh.com/.*?permalinkId=([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Veoh]"
if match.count("&")>0:
primera = match.find("&")
url = match[:primera]
else:
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'veoh' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Directo - myspace")
patronvideos = 'flashvars="file=(http://[^\.]+.myspacecdn[^\&]+)&'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Directo - myspace")
patronvideos = '(http://[^\.]+\.myspacecdn.*?\.flv)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Directo - ning")
patronvideos = '(http://api.ning.com.*?\.flv)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) Videoweed...")
patronvideos = '(http://www.videoweed.com/file/*?\.flv)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Videoweed]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'videoweed' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) YouTube...")
patronvideos = '"http://www.youtube.com/v/([^"]+)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[YouTube]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'youtube' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#http://video.ak.facebook.com/cfs-ak-ash2/33066/239/133241463372257_27745.mp4
logger.info("0) Facebook...")
patronvideos = '(http://video.ak.facebook.com/.*?\.mp4)'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Facebook]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'facebook' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#http://www.4shared.com/embed/392975628/ff297d3f
logger.info("0) 4shared...")
patronvideos = '"(http://www.4shared.com.*?)"'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[4shared]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , '4shared' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#http://www.4shared.com/embed/392975628/ff297d3f
logger.info("0) 4shared...")
patronvideos = "'(http://www.4shared.com.*?)'"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[4shared]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , '4shared' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
#file=http://es.video.netlogstatic.com//v/oo/004/398/4398830.flv&
#http://es.video.netlogstatic.com//v/oo/004/398/4398830.flv
logger.info("0) netlogicstat...")
patronvideos = "file\=(http\:\/\/es.video.netlogstatic[^\&]+)\&"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[Directo]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'Directo' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("videobb...")
patronvideos = "(http\:\/\/videobb.com\/video\/[a-zA-Z0-9]+)"
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[videobb]"
url = match
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'videobb' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
logger.info("0) megaporn...")
patronvideos = 'http\:\/\/www.mega(?:(?:p**n)|(?:rotic)?)?\.com/(?:(?:e/)?|\?(?:s=.+?&(?:amp;)?)?(?:(?:v\=)|)?)?([A-Z0-9]{8})'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
for match in matches:
titulo = "[megaporn]"
url = match
print url
if url not in encontrados:
logger.info(" url="+url)
devuelve.append( [ titulo , url , 'megaporn' ] )
encontrados.add(url)
else:
logger.info(" url duplicada="+url)
return devuelve
