def videolist(params, url, category):
xbmc.output("[rtvv.py] videolist")
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
# xbmc.output(data)
# --------------------------------------------------------
# Extrae los videos
# --------------------------------------------------------
patron = '<div class="texto">.*?<a href="([^"]+)">([^<]+)(.*?)</div>.*?<img src="([^"]+)"'
matches = re.compile(patron, re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = scrapertools.entityunescape(match[1])
# TODO: Sacar la fecha de la descripcion
patronfechas = "<p>Emissió: ([^<]+)<"
matchesfechas = re.compile(patronfechas, re.DOTALL).findall(match[2])
if len(matchesfechas) > 0:
scrapedtitle = scrapedtitle + " (" + matchesfechas[0] + ")"
scrapedurl = "http://www.rtvv.es/alacarta/secciones.asp" + match[0].replace("&", "&")
scrapedthumbnail = urlparse.urljoin(url, match[3]).replace(" ", "%20")
scrapedplot = "%s" % match[2]
scrapedplot = scrapedplot.strip()
scrapedplot = scrapedplot.replace("</a>", "")
scrapedplot = scrapedplot.replace("</p>", "")
scrapedplot = scrapedplot.replace("<p>", "")
scrapedplot = scrapertools.entityunescape(scrapedplot)
if DEBUG:
xbmc.output("title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
# addvideo( scrapedtitle , scrapedurl , category )
xbmctools.addnewvideo(
CHANNELCODE, "play", CHANNELNAME, "", scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
# Disable sorting...
# xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def novedades(params,url,category):
logger.info("[capitancinema.py] novedades")
# Descarga la página
data = scrapertools.cachePage(url)
# Extrae las entradas (carpetas)
patronvideos = '<td width="23\%"><a href="([^"]+)"[^>]+><img style="[^"]+" src="([^"]+)" border="0" alt="([^"]+)"[^>]+></a></td>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Atributos
scrapedtitle = match[2]
scrapedtitle = scrapedtitle.replace(""","")
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedurl = urlparse.urljoin(url,match[0])
scrapedthumbnail = urlparse.urljoin(url,match[1])
scrapedplot = ""
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELNAME , "mirrors" , category , scrapedtitle , scrapedurl , 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 mainlist(item):
logger.info("[totlol.py] mainlist")
# Descarga la página
data = scrapertools.cachePage("http://www.totlol.com/videos")
#logger.info(data)
patron = '<select class="subnavbarform" name="vdolanguage"[^>]+>(.*?)</select>'
matches = re.compile(patron,re.DOTALL).findall(data)
#if DEBUG: scrapertools.printMatches(matches)
data = matches[0]
patron = "<option.*?value=([^>]+)>(.*?)</option>"
matches = re.compile(patron,re.DOTALL).findall(data)
'''
<select class="subnavbarform" name="vdolanguage" onchange="location.href = this[this.selectedIndex].value;">
<option selected="selected" value="http://www.totlol.com/videos?&flang=all&orderby=df&u=&c=&search_id=&catid=0">- All Languages -</option>
<option value='http://www.totlol.com/videos?&flang=zz&u=&c=&search_id='>- No Language -</option><option value='http://www.totlol.com/videos?&flang=ar&u=&c=&search_id='>Arabic</option><option value='http://www.totlol.com/videos?&flang=nl&u=&c=&search_id='>Dutch</option><option value='http://www.totlol.com/videos?&flang=en&u=&c=&search_id='>English</option><option value='http://www.totlol.com/videos?&flang=fr&u=&c=&search_id='>French</option><option value='http://www.totlol.com/videos?&flang=de&u=&c=&search_id='>German</option><option value='http://www.totlol.com/videos?&flang=el&u=&c=&search_id='>Greek</option><option value='http://www.totlol.com/videos?&flang=he&u=&c=&search_id='>Hebrew</option><option value='http://www.totlol.com/videos?&flang=it&u=&c=&search_id='>Italian</option><option value='http://www.totlol.com/videos?&flang=ja&u=&c=&search_id='>Japanese</option><option value='http://www.totlol.com/videos?&flang=pt&u=&c=&search_id='>Portuguese</option><option value='http://www.totlol.com/videos?&flang=es&u=&c=&search_id='>Spanish</option>
</select>
'''
itemlist = []
for match in matches:
scrapedtitle = match[1]
scrapedurl = scrapertools.entityunescape(match[0][1:-1])
scrapedthumbnail = ""
scrapedplot = ""
#if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado
itemlist.append( Item(channel=CHANNELNAME, title=scrapedtitle , action="categoria" , url=scrapedurl, thumbnail=scrapedthumbnail, plot=scrapedplot , folder=True) )
return itemlist
def novedades(item):
logger.info("[capitancinema.py] novedades")
# Descarga la página
data = scrapertools.cachePage(item.url)
# Extrae las entradas (carpetas)
patronvideos = '<td width="23\%"><a href="([^"]+)"[^>]+><img style="[^"]+" src="([^"]+)" border="0" alt="([^"]+)"[^>]+></a></td>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
itemlist = []
for match in matches:
# Atributos
scrapedtitle = match[2]
scrapedtitle = scrapedtitle.replace(""", "")
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedurl = urlparse.urljoin(item.url, match[0])
scrapedthumbnail = urlparse.urljoin(item.url, match[1])
scrapedplot = ""
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
itemlist.append(
Item(channel=CHANNELNAME,
action="mirrors",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot,
folder=True))
return itemlist
def novedades(item):
logger.info("[capitancinema.py] novedades")
# Descarga la página
data = scrapertools.cachePage(item.url)
# Extrae las entradas (carpetas)
patronvideos = '<td width="23\%"><a href="([^"]+)"[^>]+><img style="[^"]+" src="([^"]+)" border="0" alt="([^"]+)"[^>]+></a></td>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
itemlist=[]
for match in matches:
# Atributos
scrapedtitle = match[2]
scrapedtitle = scrapedtitle.replace(""","")
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedurl = urlparse.urljoin(item.url,match[0])
scrapedthumbnail = urlparse.urljoin(item.url,match[1])
scrapedplot = ""
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
itemlist.append( Item(channel=CHANNELNAME, action="mirrors", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=True) )
return itemlist
def listtemporadacaratula(item):
logger.info("[cinetube.py] listtemporadacaratula")
itemlist = []
# Descarga la página
data = scrapertools.cachePage(item.url)
# 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>
"""
patronvideos = "<li>[^<]+"
patronvideos += '<a href="([^"]+)"><img src="([^"]+)"[^>]+></a>[^>]+'
patronvideos += '<div class="icos_lg">(.*?)</div>.*?'
patronvideos += '<p class="tit_ficha"><a[^>]+>([^<]+)</a></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() + " - " + match[4].strip()
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 = 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="findvideos",
title=scrapedtitle,
url=scrapedurl,
thumbnail=scrapedthumbnail,
plot=scrapedplot,
folder=True,
)
)
return itemlist
def videolist(params, url, category):
xbmc.output("[clantv.py] videolist")
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage2(
url,
[
["Referer", "http://www.rtve.es/infantil/videos-juegos/#/videos/edebits/todos/"],
[
"User-Agent",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; SLCC1; .NET CLR 2.0.50727; .NET CLR 3.0.04506; InfoPath.2)",
],
],
)
xbmc.output(data)
# --------------------------------------------------------
# Extrae los capítulos
# --------------------------------------------------------
patron = '<video id="[^"]+" thumbnail="([^"]+)" url="([^"]+)" publication_date="([^T]+)T[^>]+>[^<]+<title>([^<]+)</title>[^<]+<sinopsis([^<]+)<'
matches = re.compile(patron, re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
try:
scrapedtitle = unicode(match[3], "utf-8").encode("iso-8859-1")
except:
scrapedtitle = match[3]
scrapedtitle = scrapedtitle + " (" + match[2] + ")"
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedurl = urlparse.urljoin(url, match[1])
scrapedthumbnail = urlparse.urljoin(url, match[0])
scrapedplot = match[4]
# Depuracion
if DEBUG:
xbmc.output("scrapedtitle=" + scrapedtitle)
xbmc.output("scrapedurl=" + scrapedurl)
xbmc.output("scrapedthumbnail=" + scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo(
CHANNELCODE, "play", CHANNELNAME, "", scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
# Disable sorting...
# xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def episodios(params,url,category):
xbmc.output("[tresmellizas.py] episodios")
# Descarga la página
data = scrapertools.cachePage(url)
#xbmc.output(data)
# Extrae las entradas (videos, el parámetro url es el id de la serie)
'''
<tr>
<td width="106" valign="top"><img src="./img_captures/3bb_weare.jpg" alt="Som Les Tres Bebès" width="106" height="78" vspace="5" /></td>
<td width="119" valign="top">
<form id="form1" name="form1" method="post" action="cine.php">
<table width="50" border="0" cellpadding="0" cellspacing="0">
<tr>
<td><label><select name="idiomesCombo" id="idiomesCombo"><option value="3">English</option><option value="6">Français</option></select></label>
<label></label></td>
<td valign="middle"><input type="submit" name="enviar" id="enviar" value=">"/></td>
</tr>
</table>
<label></label>
<input name="idCapitol" type="hidden" id="idCapitol" value="4">
<input name="idIdiomaInterficie" type="hidden" id="idIdiomaInterficie" value="1">
</form> <p> </p></td>
</tr><tr>
<td width="5" rowspan="2" valign="top"> </td>
<td colspan="2" valign="top" class="titolcapitol">Les Tres Bebès Flors i papallones</td>
</tr>
'''
patronvideos = '<tr>[^<]+'
patronvideos += '<td[^>]+><img src="([^"]+)" alt="([^"]+)"[^>]+>.*?'
patronvideos += '<select name="idiomesCombo" id="idiomesCombo">(.*?)</select>.*?'
patronvideos += '<input name="idCapitol" type="hidden" id="idCapitol" value="([^"]+)">[^<]+'
patronvideos += '<input name="idIdiomaInterficie" type="hidden" id="idIdiomaInterficie" value="([^"]+)">'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if (DEBUG): scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = match[1]
scrapedurl = ""
scrapedthumbnail = urlparse.urljoin(url,match[0])
scrapedplot = ""
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
patronidiomas = '<option.*?value="([^"]+)">([^<]+)</option>'
matchesidiomas = re.compile(patronidiomas,re.DOTALL).findall(match[2])
for matchidioma in matchesidiomas:
scrapedtitle = scrapertools.entityunescape(match[1] + " (" + matchidioma[1] + ")")
scrapedurl = "idiomesCombo="+matchidioma[0]+"&enviar=%3E&idCapitol="+match[3]+"&idIdiomaInterficie="+match[4]
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 videolist(params,url,category):
xbmc.output("[publicotv.py] videolist")
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
#xbmc.output(data)
# Extrae los vídeos
patron = '<div class="video-overview a1">[^<]+'
patron += '<a href="([^"]+)" title="Play">'
patron += '<img.*?src="(.*?)".*?title="([^"]+)"[^>]+></a>\W*<h4></h4>\W*<p class="title">(.*?)</p>\W*<div class="video-info-line">\W*<p>(.*?)</p>\W*<p>(.*?)</p>\W*</div>\W*</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = match[3] + " ("+match[5]+") ("+match[4]+")"
scrapedurl = urlparse.urljoin(url,match[0])
scrapedthumbnail = urlparse.urljoin(url,match[1])
scrapedplot = scrapertools.entityunescape(match[2])
seppos = scrapedplot.find("--")
scrapedplot = scrapedplot[seppos+2:]
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELCODE , "play" , CHANNELNAME , "" , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
# Página siguiente
patron = '<a href="([^"]+)" title="Ir a la siguiente[^"]+">Siguiente \»\;</a></div>'
matches = re.compile(patron,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
if len(matches)>0:
match = matches[0]
scrapedtitle = "Página siguiente"
scrapedurl = urlparse.urljoin(url,match)
scrapedthumbnail = ""
scrapedplot = ""
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELCODE , "videolist" , CHANNELNAME , scrapedtitle , scrapedurl , scrapedthumbnail , scrapedplot )
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
# Disable sorting...
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def folderlist(params, url, category):
xbmc.output("[rtvemediateca.py] folderlist")
title = urllib.unquote_plus(params.get("title"))
url = "http://www.rtve.es/mediateca/video/" + category + "/medialist.inc"
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
# xbmc.output(data)
# --------------------------------------------------------
# Extrae las carpetas (nivel 1)
# --------------------------------------------------------
# primer nivel
# <li id="la-2-noticias" class="node-end"><a rel="nofollow" href="javascript://" onclick="loadVideos('noticias/la-2-noticias');" class="sup">La 2 Noticias</a></li>
# <li id="informativos-territoriales" class="expandable"><span onclick="loadVideos('noticias/informativos-territoriales');" class="closed">Informativos territoriales</span><ul>
# segundo nivel
# <li id="informatiu-balear"><a rel="nofollow" href="javascript://" onclick="loadVideos('noticias/informativos-territoriales/informatiu-balear');" class="inf">Informatiu Balear</a></li>
patron = '<li id="([^"]+)" class="([^"]+)"><.*?onclick="([^"]+)"[^>]*>([^<]+)<'
matches = re.compile(patron, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
try:
scrapedtitle = unicode(match[3], "utf-8").encode("iso-8859-1")
except:
scrapedtitle = match[3]
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
urlrelativa = match[2][12:-3]
# scrapedurl = "http://www.rtve.es/mediateca/video/"+urlrelativa+"/pagines_ajax/pagina1.html"
scrapedurl = match[0]
scrapedthumbnail = ""
scrapedplot = ""
if DEBUG:
xbmc.output("title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
# addvideo( scrapedtitle , scrapedurl , category )
if match[1] == "node-end":
xbmctools.addnewfolder(
CHANNELCODE, "videolist", urlrelativa, scrapedtitle, "", scrapedthumbnail, scrapedplot
)
elif match[1] == "expandable":
xbmctools.addnewfolder(
CHANNELCODE, "subfolderlist", category, scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
xbmcplugin.addSortMethod(handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def videolist2(params,url,category):
xbmc.output("[tva.py] videolist2")
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
#xbmc.output(data)
# --------------------------------------------------------
# Extrae los videos
# --------------------------------------------------------
#patron = '<div class="texto">.*?<a href="([^"]+)">([^<]+)(.*?)</div>.*?<img src="([^"]+)"'
titulo = params.get("title")
patron='urlToPlay=([^"]+)\'>'
match = re.compile(patron,re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(match)
xbmc.output(match[0])
scrapedtitle = scrapertools.entityunescape(match[0])
# TODO: Sacar la fecha de la descripcion
#patronfechas = "<p>Emissió: ([^<]+)<"
#matchesfechas = re.compile(patronfechas,re.DOTALL).findall(match[2])
#if len(matchesfechas)>0:
# scrapedtitle = scrapedtitle + " (" + matchesfechas[0] + ")"
scrapedurl = match[0]
scrapedthumbnail = ""
scrapedplot = ""
#scrapedplot = "%s" % match[2]
#scrapedplot = scrapedplot.strip()
#scrapedplot = scrapedplot.replace("</a>","")
#scrapedplot = scrapedplot.replace("</p>","")
#scrapedplot = scrapedplot.replace("<p>","")
#scrapedplot = scrapertools.entityunescape(scrapedplot)
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
#addvideo( scrapedtitle , scrapedurl , category )
xbmctools.addnewvideo( CHANNELCODE , "play" , CHANNELNAME , "" , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
#server = "Directo"
#xbmctools.playvideo(CHANNELNAME,server,scrapedurl,CHANNELNAME,scrapedtitle,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 videolist2(params,url,category):
xbmc.output("[tva.py] videolist2")
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
#xbmc.output(data)
# --------------------------------------------------------
# Extrae los videos
# --------------------------------------------------------
#patron = '<div class="texto">.*?<a href="([^"]+)">([^<]+)(.*?)</div>.*?<img src="([^"]+)"'
titulo = params.get("title")
patron='urlToPlay=([^"]+)\'>'
match = re.compile(patron,re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(match)
xbmc.output(match[0])
scrapedtitle = scrapertools.entityunescape(match[0])
# TODO: Sacar la fecha de la descripcion
#patronfechas = "<p>Emissió: ([^<]+)<"
#matchesfechas = re.compile(patronfechas,re.DOTALL).findall(match[2])
#if len(matchesfechas)>0:
# scrapedtitle = scrapedtitle + " (" + matchesfechas[0] + ")"
scrapedurl = match[0]
scrapedthumbnail = ""
scrapedplot = ""
#scrapedplot = "%s" % match[2]
#scrapedplot = scrapedplot.strip()
#scrapedplot = scrapedplot.replace("</a>","")
#scrapedplot = scrapedplot.replace("</p>","")
#scrapedplot = scrapedplot.replace("<p>","")
#scrapedplot = scrapertools.entityunescape(scrapedplot)
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
#addvideo( scrapedtitle , scrapedurl , category )
xbmctools.addnewvideo( CHANNELCODE , "play" , CHANNELNAME , "" , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
#server = "Directo"
#xbmctools.playvideo(CHANNELNAME,server,scrapedurl,CHANNELNAME,scrapedtitle,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 mainlist(params, url, category):
xbmc.output("[clantv.py] mainlist")
url = "http://www.rtve.es/infantil/videos-juegos/#/videos/clan/todos/"
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
# xbmc.output(data)
# --------------------------------------------------------
# Extrae las categorias (carpetas)
# --------------------------------------------------------
patron = '<li.*?><a rel="([^"]+)" title="[^"]+" href="([^"]+)"><strong>([^<]+)</strong><img src="([^"]+)".*?><span>([^<]+)</span>'
matches = re.compile(patron, re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
try:
scrapedtitle = unicode(match[2], "utf-8").encode("iso-8859-1")
except:
scrapedtitle = match[2]
scrapedtitle = scrapedtitle + " (" + match[4].replace("í", "i") + ")"
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# scrapedurl = "http://www.rtve.es/infantil/components/"+match[0]+"/videos/videos-1.inc"
scrapedurl = "http://www.rtve.es/infantil/components/" + match[0] + "/videos.xml.inc"
scrapedthumbnail = urlparse.urljoin(url, match[3])
scrapedplot = ""
# Depuracion
if DEBUG:
xbmc.output("scrapedtitle=" + scrapedtitle)
xbmc.output("scrapedurl=" + scrapedurl)
xbmc.output("scrapedthumbnail=" + scrapedthumbnail)
# Añade al listado de XBMC
# addvideo( scrapedtitle , scrapedurl , category )
xbmctools.addnewfolder(
CHANNELCODE, "videolist", CHANNELNAME, scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
# Disable sorting...
xbmcplugin.addSortMethod(handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE)
# End of directory...
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def anyadevideos(matches):
if DEBUG: scrapertools.printMatches(matches)
'''
patron = '<li id="video-(\d+)" class="videoThumbnail">[^<]+' [0] 244902
patron += '<div>[^<]+'
patron += "<a.*?href='([^']+)'[^>]+>[^<]+" [1] .shtml
patron += '<img src="([^"]+)" alt="([^"]+)"[^>]+>[^<]+' [2] .jpg [3] Telediario Internacional Edición 18 horas (10/04/10)
patron += '<img alt="Reproducir"[^<]+'
patron += '</a>[^<]+'
patron += '<h3>[^<]+'
patron += '<a[^>]+>([^<]+)</a>[^<]+' [4] TD Internacional 18h (10/04/10)
patron += '</h3>[^<]+'
patron += '<p>([^<]+)</p>[^<]+' [5] Polonia, de luto. El presidente del Parlamento asume las funciones de Kaczynski.
patron += '<span>([^<]+)<' [6] Emitido: 10/04/2010 / 18:00h
'''
for match in matches:
patron = "Emitido:\s+([^\s]+)\s+\/\s+(\d+)\:(\d+)h"
fechahora = re.compile(patron,re.DOTALL).findall(match[6])
if DEBUG: scrapertools.printMatches(fechahora)
if len(fechahora)>0:
scrapedtitle = scrapertools.entityunescape(match[4] + " ("+fechahora[0][0]+") (" + fechahora[0][1]+"'"+fechahora[0][2]+'")')
else:
scrapedtitle = scrapertools.entityunescape(match[4])
scrapedurl = urlparse.urljoin("http://www.rtve.es",match[1])
scrapedthumbnail = "http://www.rtve.es%s" % match[2]
scrapedplot = scrapertools.entityunescape(match[3].strip()+"\n"+match[5].strip())
# Depuracion
if (DEBUG):
xbmc.output("scrapedtitle="+scrapedtitle)
xbmc.output("scrapedurl="+scrapedurl)
xbmc.output("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELCODE , "play" , CHANNELNAME , "" , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
def listado(item):
logger.info("[totlol.py] listado")
# Descarga la página
data = scrapertools.cachePage(item.url)
#logger.info(data)
patron = '<select class="subnavbarform" name="vdoorderby"[^>]+>(.*?)</select>'
matches = re.compile(patron,re.DOTALL).findall(data)
#if DEBUG: scrapertools.printMatches(matches)
data = matches[0]
patron = "<option.*?value=([^>]+)>(.*?)</option>"
matches = re.compile(patron,re.DOTALL).findall(data)
'''
<select class="subnavbarform" name="vdoorderby" onchange="location.href = this[this.selectedIndex].value;">
<option value="http://www.totlol.com/videos?&orderby=df&u=&c=&search_id=&catid=0">- All Categories -</option>
<option value='http://www.totlol.com/videos?&catid=1&u=&c=&search_id='>Animals</option><option value='http://www.totlol.com/videos?&catid=6&u=&c=&search_id='>Animated</option><option value='http://www.totlol.com/videos?&catid=16&u=&c=&search_id='>Classic</option><option value='http://www.totlol.com/videos?&catid=17&u=&c=&search_id='>Dance</option><option value='http://www.totlol.com/videos?&catid=13&u=&c=&search_id='>Educational</option><option value='http://www.totlol.com/videos?&catid=24&u=&c=&search_id='>Filmed or Live action</option><option value='http://www.totlol.com/videos?&catid=8&u=&c=&search_id='>Food and Drinks</option><option value='http://www.totlol.com/videos?&catid=2&u=&c=&search_id='>Funny</option><option value='http://www.totlol.com/videos?&catid=9&u=&c=&search_id='>Games and Sports</option><option value='http://www.totlol.com/videos?&catid=7&u=&c=&search_id='>Holidays and Special Events</option><option value='http://www.totlol.com/videos?&catid=26&u=&c=&search_id='>Movie</option><option value='http://www.totlol.com/videos?&catid=23&u=&c=&search_id='>Music</option><option value='http://www.totlol.com/videos?&catid=14&u=&c=&search_id='>Places</option><option value='http://www.totlol.com/videos?&catid=19&u=&c=&search_id='>Puppets Etc.</option><option value='http://www.totlol.com/videos?&catid=3&u=&c=&search_id='>Songs</option><option value='http://www.totlol.com/videos?&catid=15&u=&c=&search_id='>Stories</option><option value='http://www.totlol.com/videos?&catid=4&u=&c=&search_id='>Transportation</option><option value='http://www.totlol.com/videos?&catid=27&u=&c=&search_id='>TV show</option><option value='http://www.totlol.com/videos?&catid=20&u=&c=&search_id='>Videos of Babies or Infants</option><option value='http://www.totlol.com/videos?&catid=22&u=&c=&search_id='>Videos of Kindergarten or School Kids</option><option value='http://www.totlol.com/videos?&catid=21&u=&c=&search_id='>Videos of Toddlers or Preschoolers</option><option value='http://www.totlol.com/videos?&catid=25&u=&c=&search_id='>Videos of Tweens or Teens</option>
</select>
'''
itemlist = []
import config
itemlist.append( Item(channel=CHANNELNAME, title=config.getLocalizedString(30103) , action="search" , folder=True) )
for match in matches:
scrapedtitle = match[1]
scrapedurl = scrapertools.entityunescape(match[0][1:-1])
scrapedthumbnail = ""
scrapedplot = ""
#if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado
itemlist.append( Item(channel=CHANNELNAME, title=scrapedtitle , action="listado" , url=scrapedurl, thumbnail=scrapedthumbnail, plot=scrapedplot , folder=True) )
return itemlist
def getlistpeliconcaratula(params,url,category):
logger.info("[cinetube.py] getlistpeliconcaratula")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
#logger.info(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
# seccion novedades
'''
<!--PELICULA-->
<div class="peli_item textcenter">
<div class="pelicula_img"><a href='/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html' >
<img src="http://caratulas.cinetube.es/pelis/7058.jpg" alt="Un segundo después 2" /></a>
</div><a href="/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html" ><div class="dvdrip"></div></a><a href='/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html' ><p class="white">Un segundo después 2</p></a><p><span class="rosa">DVD-RIP</span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div>
</div>
<!--FIN PELICULA-->
'''
# listado alfabetico
'''
<!--PELICULA-->
<div class="peli_item textcenter">
<div class="pelicula_img"><a href="/peliculas/musical/ver-pelicula-a-chorus-line.html">
<img src="http://caratulas.cinetube.es/pelis/246.jpg" alt="A Chorus Line" /></a>
</div>
<a href="/peliculas/musical/ver-pelicula-a-chorus-line.html"><p class="white">A Chorus Line</p></a>
<p><span class="rosa">DVD-RIP</span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div> </div>
<!--FIN PELICULA-->
'''
patronvideos = '<!--PELICULA-->[^<]+'
patronvideos += '<div class="peli_item textcenter">[^<]+'
patronvideos += '<div class="pelicula_img"><a[^<]+'
patronvideos += '<img src="([^"]+)"[^<]+</a>[^<]+'
patronvideos += '</div[^<]+<a href="([^"]+)".*?<p class="white">([^<]+)</p>.*?<p><span class="rosa">([^>]+)</span></p><div class="icos_lg">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
# Titulo
scrapedtitle = match[2] + " [" + match[3] + "]"
matchesconectores = re.compile('<img.*?alt="([^"]*)"',re.DOTALL).findall(match[4])
conectores = ""
for matchconector in matchesconectores:
logger.info("matchconector="+matchconector)
if matchconector=="":
matchconector = "megavideo"
conectores = conectores + matchconector + "/"
if len(matchesconectores)>0:
scrapedtitle = scrapedtitle + " (" + conectores[:-1] + ")"
# Convierte desde UTF-8 y quita entidades HTML
try:
scrapedtitle = unicode( scrapedtitle, "utf-8" ).encode("iso-8859-1")
except:
pass
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# procesa el resto
scrapedplot = ""
scrapedurl = urlparse.urljoin("http://www.cinetube.es/",match[1])
scrapedthumbnail = match[0]
if (DEBUG): logger.info("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
itemlist.append( Item(channel=CHANNELNAME, action="listmirrors", title=scrapedtitle , url=scrapedurl , thumbnail=scrapedthumbnail , plot=scrapedplot , folder=True) )
# ------------------------------------------------------
# Extrae el 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(url,matches[0])
itemlist.append( Item(channel=CHANNELNAME, action="listpeliconcaratula", title="!Página siguiente" , url=scrapedurl , folder=True) )
return itemlist
def listseriesincaratula(params, url, category):
logger.info("[cinetube.py] listseriesincaratula")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
# logger.info(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
"""
<!--SERIE-->
<div class="pelicula_bar_border">
<div class="pelicula_bar series iframe3">
<ul class="tabs-nav" id="video-1687">
<li><span style="cursor:pointer;" class="peli_ico_1 bold" onclick="location.href='/peliculas/drama/ver-pelicula-belleza-robada.html'">Belleza robada </a></span></li>
<li><a class="peli_ico_3" style="margin-left:10px;" href="/peliculas/drama/ver-pelicula-belleza-robada.html"><span> Ver ficha</span></a></li>
</ul>
</div>
<div id="p_ver1" class="peli_bg1" style="display:none;">
</div>
</div>
"""
"""
<!--SERIE-->
<div class="pelicula_bar_border">
<div class="pelicula_bar series iframe3">
<ul class="tabs-nav" id="video-1692">
<li><span style="cursor:pointer;" class="peli_ico_1 bold" onclick="location.href='/peliculas/terror/ver-pelicula-bendicion-mortal.html'">Bendición mortal </a></span></li>
<li><a class="peli_ico_3" style="margin-left:10px;" href="/peliculas/terror/ver-pelicula-bendicion-mortal.html"><span> Ver ficha</span></a></li>
</ul>
</div>
<div id="p_ver1" class="peli_bg1" style="display:none;">
</div>
</div>
"""
patronvideos = "<!--SERIE-->[^<]+"
patronvideos += '<div class="pelicula_bar_border">[^<]+'
patronvideos += '<div class="pelicula_bar series iframe3">[^<]+'
patronvideos += '<ul class="tabs-nav" id="([^"]+)">[^<]+'
patronvideos += "<li><span[^>]+>([^<]+)</a></span></li>[^<]+"
patronvideos += '<li><a.*?href="([^"]+)"'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Titulo
try:
scrapedtitle = unicode(match[1], "utf-8").encode("iso-8859-1")
except:
scrapedtitle = match[1]
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedplot = ""
scrapedurl = urlparse.urljoin(url, match[2])
scrapedthumbnail = ""
if DEBUG:
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
xbmctools.addnewfolder(
CHANNELNAME, "findvideos", category, scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
# ------------------------------------------------------
# Extrae el 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:
xbmctools.addnewfolder(
CHANNELNAME,
"listseriesincaratula",
category,
"!Página siguiente",
urlparse.urljoin(url, matches[0]),
"",
"",
)
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=int(sys.argv[1]), category=category)
xbmcplugin.addSortMethod(handle=int(sys.argv[1]), sortMethod=xbmcplugin.SORT_METHOD_TITLE)
xbmcplugin.endOfDirectory(handle=int(sys.argv[1]), succeeded=True)
def listserieconcaratula(params, url, category):
logger.info("[cinetube.py] listserieconcaratula")
# Descarga la página
data = scrapertools.cachePage(url)
# logger.info(data)
# Extrae las entradas
"""
<li>
<a href="/series/las-reglas-del-juego-leverage/temporada-3/capitulo-15/"><img src="http://caratulas.cinetube.es/series/166.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 Las reglas del juego (Leverage)" href="/series/las-reglas-del-juego-leverage/temporada-3/capitulo-15/">Las reglas del juego (Leverage) </a></p>
<p class="tem_fich">3a Temporada - Cap 15</p>
</li>
"""
patronvideos = "<li>[^<]+"
patronvideos += '<a href="([^"]+)"><img src="([^"]+)"[^>]+></a>.*?'
patronvideos += '<div class="icos_lg">(.*?)</div>[^<]+'
patronvideos += '<p class="tem_ficha">([^<]+)</p>[^<]+'
patronvideos += "</li>"
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[3].strip()
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] + ")"
# Convierte desde UTF-8 y quita entidades HTML
try:
scrapedtitle = unicode(scrapedtitle, "utf-8").encode("iso-8859-1")
except:
pass
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# procesa el resto
scrapedplot = ""
scrapedurl = urlparse.urljoin(url, match[0])
scrapedthumbnail = match[1]
if DEBUG:
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
xbmctools.addnewfolder(
CHANNELNAME, "findvideos", category, scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
# ------------------------------------------------------
# Extrae el 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:
xbmctools.addnewfolder(
CHANNELNAME,
"listserieconcaratula",
category,
"!Página siguiente",
urlparse.urljoin(url, matches[0]),
"",
"",
)
# 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 listpelisincaratula(item):
logger.info("[cinetube.py] listpelisincaratula")
url = item.url
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
# logger.info(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
"""
<!--SERIE-->
<div class="pelicula_bar_border">
<div class="pelicula_bar series iframe3">
<ul class="tabs-nav" id="video-1687">
<li><span style="cursor:pointer;" class="peli_ico_1 bold" onclick="location.href='/peliculas/drama/ver-pelicula-belleza-robada.html'">Belleza robada </a></span></li>
<li><a class="peli_ico_3" style="margin-left:10px;" href="/peliculas/drama/ver-pelicula-belleza-robada.html"><span> Ver ficha</span></a></li>
</ul>
</div>
<div id="p_ver1" class="peli_bg1" style="display:none;">
</div>
</div>
"""
"""
<!--SERIE-->
<div class="pelicula_bar_border">
<div class="pelicula_bar series iframe3">
<ul class="tabs-nav" id="video-1692">
<li><span style="cursor:pointer;" class="peli_ico_1 bold" onclick="location.href='/peliculas/terror/ver-pelicula-bendicion-mortal.html'">Bendición mortal </a></span></li>
<li><a class="peli_ico_3" style="margin-left:10px;" href="/peliculas/terror/ver-pelicula-bendicion-mortal.html"><span> Ver ficha</span></a></li>
</ul>
</div>
<div id="p_ver1" class="peli_bg1" style="display:none;">
</div>
</div>
"""
patronvideos = "<!--SERIE-->[^<]+"
patronvideos += '<div class="pelicula_bar_border">[^<]+'
patronvideos += '<div class="pelicula_bar series iframe3">[^<]+'
patronvideos += '<ul class="tabs-nav" id="([^"]+)">[^<]+'
patronvideos += "<li><span[^>]+?>.+?<a[^>]+?>([^<]+)</a></span></li>[^<]+"
patronvideos += '<li><a.*?href="([^"]+)"'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
itemlist = []
for match in matches:
try:
scrapedtitle = unicode(match[1], "utf-8").encode("iso-8859-1")
except:
scrapedtitle = match[1]
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedplot = ""
scrapedurl = urlparse.urljoin("http://www.cinetube.es/", match[2])
scrapedthumbnail = ""
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,
folder=True,
)
)
# ------------------------------------------------------
# Extrae el 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(url, matches[0])
itemlist.append(
Item(
channel=CHANNELNAME,
action="listpelisincaratula",
title="!Página siguiente",
url=scrapedurl,
folder=True,
)
)
return itemlist
def listserieconcaratula(params, url, category):
logger.info("[programastv.py] listserieconcaratula")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
#logger.info(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
'''
<li>
<a href="/series/the-middleman/temporada-1/"><img src="http://caratulas.programastv.es/series/233.jpg" alt="peli" /></a>
<p><span class="rosa"></span></p><div class="icos_lg"><img src="http://caratulas.programastv.es/img/cont/sub.png" alt="sub" /><img src="http://caratulas.programastv.es/img/cont/megavideo.png" alt="" /> </div> <p class="tit_ficha">The middleman </p>
<p class="tem_fich">1a Temporada</p>
</li>
'''
'''
<li>
<a href="/series/cranford-de-e-gaskell/"><img src="http://caratulas.programastv.es/series/64.jpg" alt="peli" /></a>
<p><span class="rosa"></span></p><div class="icos_lg"><img src="http://caratulas.programastv.es/img/cont/sub.png" alt="sub" /><img src="http://caratulas.programastv.es/img/cont/megavideo.png" alt="" /><img src="http://caratulas.programastv.es/img/cont/ddirecta.png" alt="descarga directa" /> </div> <p class="tit_ficha">Cranford, de E. Gaskell </p>
</li>
'''
patronvideos = '<li>[^<]+'
patronvideos += '<a href="([^"]+)"><img src="([^"]+)"[^>]+></a>[^<]+'
patronvideos += '<p><span class="rosa"></span></p><div class="icos_lg">(.*?)</div>[^<]+'
patronvideos += '<p class="tit_ficha">([^<]+)</p>[^<]+'
patronvideos += '</li>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[3].strip()
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] + ")"
# Convierte desde UTF-8 y quita entidades HTML
try:
scrapedtitle = unicode(scrapedtitle, "utf-8").encode("iso-8859-1")
except:
pass
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# procesa el resto
scrapedplot = ""
scrapedurl = urlparse.urljoin(url, match[0])
scrapedthumbnail = match[1]
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
xbmctools.addnewfolder(CHANNELNAME, "listmirrors", category,
scrapedtitle, scrapedurl, scrapedthumbnail,
scrapedplot)
# ------------------------------------------------------
# Extrae el 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:
xbmctools.addnewfolder(CHANNELNAME, "listserieconcaratula", category,
"!Página siguiente",
urlparse.urljoin(url, matches[0]), "", "")
# 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 ListarVideos(params, url, category):
url1 = "http://www.series21.com"
url1 = urlparse.urljoin(url1, url)
title = urllib.unquote_plus(params.get("title"))
thumbnail = urllib.unquote_plus(params.get("thumbnail"))
plot = urllib.unquote_plus(params.get("plot"))
data = scrapertools.cachePage(url1)
# Busca el area donde estan los videos y la descripcion
patronvideos = '<div id="content">(.*?)<!-- FIN #content-->'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
matchesBK = matches[0]
# Extrae las entradas (videos) para megavideo
patronvideos = '<span style="font-size:12px;"><strong>(.*?)</strong></span><br/>.*?'
patronvideos += '<span.*?>.*?<a href="http\:\/\/www.megavideo.com\/([\?v=|v/|\?d=]+)([A-Z0-9]{8}).*?" target'
matches = re.compile(patronvideos, re.DOTALL).findall(matches[0])
scrapertools.printMatches(matches)
encontrados = set()
for match in matches:
if match[2] not in encontrados:
encontrados.add(match[2])
if 'v' in match[1]:
server = "Megavideo"
else:
server = "Megaupload"
doblaje = scrapertools.entityunescape(match[0])
# Titulo
scrapedtitle = title + " - [" + doblaje + "]" + " (" + server + ")"
# URL
scrapedurl = match[2]
# Thumbnail
scrapedthumbnail = thumbnail
# Argumento
#print 'este es el plot %s ' %plot
#print ' doblaje %s ' %doblaje
scrapedplot = plot
if ("Español" in plot) and not (doblaje in plot):
scrapedplot = scrapedplot.replace("Español", doblaje)
elif "subtitulado" in plot and not (doblaje in plot):
scrapedplot = scrapedplot.replace(
"Versión original (subtitulado)", doblaje)
elif not doblaje in plot:
scrapedplot += "\n" + "Doblaje : " + doblaje
# Depuracion
if (DEBUG):
logger.info("scrapedtitle=" + scrapedtitle)
logger.info("scrapedurl=" + scrapedurl)
logger.info("scrapedthumbnail=" + scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo(CHANNELNAME, "play", category, server,
scrapedtitle, scrapedurl, scrapedthumbnail,
scrapedplot)
if len(matches) == 0:
listavideos = servertools.findvideos(data)
encontrados = set()
for titulo, scrapedurl, servidor in listavideos:
if scrapedurl.strip() not in encontrados:
encontrados.add(scrapedurl.strip())
xbmctools.addnewvideo(CHANNELNAME, "play", category, servidor,
title + " - %s" % titulo, scrapedurl,
thumbnail, plot)
patronvideos = '<span class="bloque-doblaje">(.+?)</span>[^<]+'
patronvideos += '<span class="bloque-link">[^<]+<a href="javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)"(.+?)</span>'
#patronvideos +='(?:\| <a href="javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)".*?)</span>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# URL
if "megavideo" in match[2]:
server = "Megavideo"
elif "megaupload" in match[2]:
server = "Megaupload"
if "esp.gif" in match[0]:
doblaje = "Español"
else:
doblaje = match[0].strip()
base64 = decrypt21.Base64()
try:
url2 = re.compile(
"javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)").findall(
match[3])[0]
scrapedurl2 = base64._extract_code(base64.decode(url2[0]))
scrapedurl = base64._extract_code(base64.decode(match[1]))
part1 = " Parte 1 "
part2 = " Parte 2 "
scrapedtitle2 = title + part2 + " - [" + doblaje + "]" + " (" + server + ")"
#print match[3]
except:
scrapedurl = base64._extract_code(base64.decode(match[1]))
part1 = ""
part2 = ""
scrapedtitle = title + part1 + " - [" + doblaje + "]" + " (" + server + ")"
# Thumbnail
scrapedthumbnail = thumbnail
# Argumento
scrapedplot = plot
# Depuracion
if (DEBUG):
logger.info("scrapedtitle=" + scrapedtitle)
logger.info("scrapedurl=" + scrapedurl)
logger.info("scrapedthumbnail=" + scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo(CHANNELNAME, "play", category, server,
scrapedtitle, scrapedurl, scrapedthumbnail,
scrapedplot)
if part2:
xbmctools.addnewvideo(CHANNELNAME, "play", category, server,
scrapedtitle2, scrapedurl2, scrapedthumbnail,
scrapedplot)
# Extrae las entradas (videos) directos
patronvideos = 'flashvars="file=([^\&]+)\&controlbar=over'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches) > 0:
data1 = scrapertools.cachePage(matches[0])
#logger.info(data)
patron = 'author">(.*?)</media:credit>.*?<media\:content url="([^"]+)"'
matches = re.compile(patron, re.DOTALL).findall(data1)
scrapertools.printMatches(matches)
for match in matches:
# Añade al listado de XBMC
xbmctools.addnewvideo(
CHANNELNAME, "play", category, "Directo",
title + " - [" + match[0] + "]" + " (Directo)", match[1],
thumbnail, plot)
# Busca el Spoiler
patronvideos = '(http://www.youtube.com[^"]+)"'
matchSpoiler = re.compile(patronvideos, re.DOTALL).findall(data)
if len(matchSpoiler) > 0:
encontrados = set()
for match in matchSpoiler:
if match not in encontrados:
encontrados.add(match)
# Añade al listado de XBMC
xbmctools.addnewvideo(CHANNELNAME, "youtubeplay", category,
"Directo",
"Ver El Spoiler de : " + title, match,
thumbnail, "Ver Video Spoiler")
# Lista series relacionadas
titulo = "Ver otros capitulos de esta temporada"
matches = buscarelacionados(matchesBK)
plot2 = "CAPITULOS DE ESTA TEMPORADA :\n\n"
for match in matches:
plot2 = plot2 + "-" + match[2] + "\n"
xbmctools.addnewfolderextra(CHANNELNAME, "listarelacionados", category,
titulo, url, thumbnail, plot2, matchesBK)
#<div class="film"><a href="/house/#t_57"><img src="/thumbs/temporadas/95/120/57.jpg"
# Cambiar de Temporada
patron = 'div class="film"><a href="([^"]+)"><img src="([^"]+)" style'
matchSerie = re.compile(patron, re.DOTALL).findall(matchesBK)
if len(matchSerie) > 1:
for temp in matchSerie:
url2 = urlparse.urljoin(url1, temp[0])
thumbnail = urlparse.urljoin(url1, temp[1])
titulo = "Cambiar a otras temporadas"
titulo_serie = temp[0].split("/")
titulo2 = titulo_serie[1].replace("-", " ")
#print ' titulo%s ' %titulo2
xbmctools.addnewfolderextra(CHANNELNAME, "listarTemporada",
category, titulo, url2, thumbnail,
plot, titulo2)
break
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
# Disable sorting...
xbmcplugin.addSortMethod(handle=pluginhandle,
sortMethod=xbmcplugin.SORT_METHOD_NONE)
# End of directory...
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def listvideos(params,url,category):
logger.info("[peliculas21.py] listvideos")
if url=="":
url = "http://www.peliculas21.com"
# Descarga la página
data = scrapertools.cachePage(url)
#logger.info(data)
#title = urllib.unquote_plus(params.get("title"))
#thumbnail = urllib.unquote_plus(params.get("thumbnail"))
#plot = urllib.unquote_plus(params.get("plot"))
# Busca el area donde estan los videos y la descripcion
patronvideos = '<div class="peliculadoblaje">(.*?)<!-- FIN #content-->'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
# busca el titulo y el thumbnail
patronvideos = '<img src="([^"]+)"[^>]+>[^<]+<[^>]+>([^<]+)</div>'
matches2 = re.compile(patronvideos,re.DOTALL).findall(matches[0])
for match in matches2:
title = match[1]
thumbnail = urlparse.urljoin(url,match[0])
plot = ""
patronvideos = '<b>Duración:</b>(.*?)<br />'
duracion = re.compile(patronvideos,re.DOTALL).findall(matches[0])
if len(duracion)>0:plot = "Duracion:"+duracion[0] + "\n"
patronvideos = '<b>Género:</b>(.*?)<br />'
genero = re.compile(patronvideos,re.DOTALL).findall(matches[0])
if len(genero)>0:plot = plot + "Genero: "+genero[0] +"\n"
patronvideos = '<b>Sinopsis:</b>(.*?)</div>'
sinopsis = re.compile(patronvideos,re.DOTALL).findall(matches[0])
# Busca los actores
matchesactores = buscactores(matches[0])
if len(matchesactores)>0:
plot = plot + "Actores: "
c = 0
actores = "ACTORES DE ESTA PELICULA :\n\n"
for match in matchesactores:
c = c + 1
actores = actores + "-"+match[1] + "\n"
if c == 3:
plot = plot + match[1] + "\n"
elif c == 4:
plot = plot + "* " + match[1]+" "
else:
plot = plot + match[1]+ " , "
plot = plot + "\nSinopsis: " + sinopsis[0]
plot = re.sub("<[^>]+>"," ",plot)
# Busca el trailer
patronvideos = '<param name="movie" value="([^"]+)"></param>'
matchtrailer = re.compile(patronvideos,re.DOTALL).findall(matches[0])
if len(matchtrailer)>0:
for match in matchtrailer:
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "youtubeplay" , category ,"Directo", "Ver El Trailer de : "+title , match , thumbnail, plot )
else:
import trailertools
print title
s = unicode( title, "latin-1" )
# Añade al listado de XBMC
xbmctools.addnewfolder( "trailertools" , "buscartrailer" , category , config.getLocalizedString(30110)+" "+title , url , os.path.join(IMAGES_PATH, 'trailertools.png'), plot ) # Buscar trailer para
matchesBK = matches[0]
# Extrae las entradas (videos) para megavideo con tipo de audio
patronvideos = '<span style="font-size:12px;"><strong>(.*?)</strong></span><br/>.*?'
patronvideos += '<span.*?>.*?<a href="http\:\/\/www.megavideo.com\/[\?v=|v/]+([A-Z0-9]{8}).*?" target="_blank">1</a>.</span><br />'
matches = re.compile(patronvideos,re.DOTALL).findall(matches[0])
scrapertools.printMatches(matches)
encontrados = set()
for match in matches:
if match[1] not in encontrados:
encontrados.add(match[1])
# Titulo
scrapedtitle = title + " - [" +scrapertools.entityunescape(match[0])+ "]" + " (Megavideo)"
# URL
scrapedurl = match[1]
# Thumbnail
scrapedthumbnail = thumbnail
# Argumento
scrapedplot = plot
# Depuracion
if (DEBUG):
logger.info("scrapedtitle="+scrapedtitle)
logger.info("scrapedurl="+scrapedurl)
logger.info("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,"Megavideo", scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
if len(matches)==0:
listavideos = servertools.findvideos(data)
encontrados = set()
for titulo,scrapedurl,servidor in listavideos:
if scrapedurl.strip() not in encontrados:
encontrados.add(scrapedurl.strip())
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,servidor, title+ " - %s" % titulo , scrapedurl , thumbnail, plot )
'''
<span class="bloque-uploader">Anónimo</span>
<span class="bloque-doblaje"><img src="../images/esp.gif" class="bandera" /></span>
<span class="bloque-link">Opción 8: <a href="javascript:goTo('aHR0cDovL3d3dy5tZWdhdmlkZW8uY29tLz92PTVOM0JYOVMx', 'megavideo.com')" rel="nofollow">Ver película</a></span>
'''
patronvideos = '<span class="bloque-doblaje">(.+?)</span>[^<]+'
patronvideos +='<span class="bloque-link">[^<]+<a href="javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)"(.+?)</span>'
#patronvideos +='(?:\| <a href="javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)".*?)</span>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# URL
if "megavideo" in match[2]:
server = "Megavideo"
elif "megaupload" in match[2]:
server = "Megaupload"
if "esp.gif" in match[0]:
doblaje = "Español"
else:
doblaje = match[0].strip()
base64 = decrypt21.Base64()
try:
url2 = re.compile("javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)").findall(match[3])[0]
scrapedurl2 = base64._extract_code(base64.decode(url2[0]))
scrapedurl = base64._extract_code(base64.decode(match[1]))
part1 = " Parte 1 "
part2 = " Parte 2 "
scrapedtitle2 = title + part2+ " - [" +doblaje+ "]" + " ("+server+")"
#print match[3]
except:
scrapedurl = base64._extract_code(base64.decode(match[1]))
part1 = ""
part2 = ""
scrapedtitle = title + part1+ " - [" +doblaje+ "]" + " ("+server+")"
# Thumbnail
scrapedthumbnail = thumbnail
# Argumento
scrapedplot = plot
# Depuracion
if (DEBUG):
logger.info("scrapedtitle="+scrapedtitle)
logger.info("scrapedurl="+scrapedurl)
logger.info("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,server, scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
if part2:
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,server, scrapedtitle2 , scrapedurl2 , scrapedthumbnail, scrapedplot )
# Extrae las entradas (videos) directos
patronvideos = 'flashvars="file=([^\&]+)\&controlbar=over'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
data1 = scrapertools.cachePage(matches[0])
#logger.info(data)
patron = 'author">(.*?)</media:credit>.*?<media\:content url="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(data1)
scrapertools.printMatches(matches)
for match in matches:
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category , "Directo" , title +" - ["+match[0]+"]"+ " (Directo)" , match[1] , thumbnail , plot )
# Busca otras peliculas relacionadas con los actores
if len(matchesactores)>0:
titulo = "Busca otros Films de los actores de esta pelicula"
xbmctools.addnewfolder( CHANNELNAME , "listaractores" , category , titulo , matchesBK , thumbnail, actores )
# Lista peliculas relacionadas
titulo = "Ver Peliculas Relacionadas"
matches = buscarelacionados(matchesBK)
plot2 = "PELICULAS RELACIONADAS :\n\n"
for match in matches:
plot2 = plot2 + "-"+match[1]+"\n"
xbmctools.addnewfolder( CHANNELNAME , "listarelacionados" , category , titulo , matchesBK , thumbnail, plot2 )
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
# Disable sorting...
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def videolist(params,url,category):
xbmc.output("[rtve.py] videolist")
title = urllib.unquote_plus( params.get("title") )
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
xbmc.output("[rtve.py] videolist descarga página principal "+url)
data = scrapertools.cachePage(url)
#xbmc.output(data)
# --------------------------------------------------------
# Extrae las categorias (carpetas)
# --------------------------------------------------------
patron = '<a href="(/alacarta/todos/[^"]+)".*?>([^<]+)</a>'
matches = re.compile(patron,re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
# Datos
scrapedtitle = scrapertools.entityunescape(match[1].strip())
scrapedurl = urlparse.urljoin("http://www.rtve.es", match[0])
scrapedthumbnail = ""
scrapedplot = ""
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
#addvideo( scrapedtitle , scrapedurl , category )
if scrapedtitle=="Recomendados" or scrapedtitle=="Temas" or scrapedtitle=="Todos A-Z" or scrapedtitle=="Archivo TVE" or scrapedtitle=="Ultimos 7 dias" or scrapedtitle=="Adelante":
pass
else:
xbmctools.addnewfolder( CHANNELCODE , "videolist" , CHANNELNAME , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
# --------------------------------------------------------
# Extrae los videos de la página actual
# --------------------------------------------------------
#patron = '<li id="video-(\d+)">\W*<div>\W*<a rel="facebox" href="([^"]+)"><img src="([^"]+)" alt="([^"]+)"><img alt="Reproducir" src="/css/i/mediateca/play.png" class="play_mini"></a>\W+<h3>\W+<a[^<]+</a>\W+</h3>\W+<p>([^<]+)</p>[^<]+<span>([^<]+)<'
patron = '<li id="video-(\d+)" class="videoThumbnail">[^<]+'
patron += '<div>[^<]+'
patron += "<a.*?href='([^']+)'[^>]+>[^<]+"
patron += '<img src="([^"]+)" alt="([^"]+)"[^>]+>[^<]+'
patron += '<img alt="Reproducir"[^<]+'
patron += '</a>[^<]+'
patron += '<h3>[^<]+'
patron += '<a[^>]+>([^<]+)</a>[^<]+'
patron += '</h3>[^<]+'
patron += '<p>([^<]+)</p>[^<]+'
patron += '<span>([^<]+)<'
matches = re.compile(patron,re.DOTALL).findall(data)
anyadevideos(matches)
# --------------------------------------------------------
# Extrae los videos del resto de páginas
# --------------------------------------------------------
xbmc.output("Paginación...")
'''
<a href="/alacarta/todos/recomendados/2.html" class="">
Adelante
</a>
'''
patronpaginas = '<a href="([^"]+)" class="">\s+Adelante\s+</a>'
paginas = re.compile(patronpaginas,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(paginas)
print paginas
# Hay al menos otra página
while len(paginas)>0:
urlpagina = urlparse.urljoin(url,paginas[0])
xbmc.output("urlpagina="+urlpagina)
datapagina = scrapertools.cachePage(urlpagina)
matches = re.compile(patron,re.DOTALL).findall(datapagina)
anyadevideos(matches)
paginas = re.compile(patronpaginas,re.DOTALL).findall(datapagina)
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
#xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_TITLE )
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def listseriesincaratula(params, url, category):
logger.info("[programastv.py] listseriesincaratula")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
#logger.info(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
'''
<!--SERIE-->
<div class="pelicula_bar_border">
<div class="pelicula_bar series iframe3">
<ul class="tabs-nav" id="video-1687">
<li><span style="cursor:pointer;" class="peli_ico_1 bold" onclick="location.href='/peliculas/drama/ver-pelicula-belleza-robada.html'">Belleza robada </a></span></li>
<li><a class="peli_ico_3" style="margin-left:10px;" href="/peliculas/drama/ver-pelicula-belleza-robada.html"><span> Ver ficha</span></a></li>
</ul>
</div>
<div id="p_ver1" class="peli_bg1" style="display:none;">
</div>
</div>
'''
'''
<!--SERIE-->
<div class="pelicula_bar_border">
<div class="pelicula_bar series iframe3">
<ul class="tabs-nav" id="video-1692">
<li><span style="cursor:pointer;" class="peli_ico_1 bold" onclick="location.href='/peliculas/terror/ver-pelicula-bendicion-mortal.html'">Bendición mortal </a></span></li>
<li><a class="peli_ico_3" style="margin-left:10px;" href="/peliculas/terror/ver-pelicula-bendicion-mortal.html"><span> Ver ficha</span></a></li>
</ul>
</div>
<div id="p_ver1" class="peli_bg1" style="display:none;">
</div>
</div>
'''
patronvideos = '<!--SERIE-->[^<]+'
patronvideos += '<div class="pelicula_bar_border">[^<]+'
patronvideos += '<div class="pelicula_bar series iframe3">[^<]+'
patronvideos += '<ul class="tabs-nav" id="([^"]+)">[^<]+'
patronvideos += '<li><span[^>]+>([^<]+)</a></span></li>[^<]+'
patronvideos += '<li><a.*?href="([^"]+)"'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# Titulo
try:
scrapedtitle = unicode(match[1], "utf-8").encode("iso-8859-1")
except:
scrapedtitle = match[1]
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedplot = ""
scrapedurl = urlparse.urljoin(url, match[2])
scrapedthumbnail = ""
if (DEBUG):
logger.info("title=[" + scrapedtitle + "], url=[" + scrapedurl +
"], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
xbmctools.addnewfolder(CHANNELNAME, "listmirrors", category,
scrapedtitle, scrapedurl, scrapedthumbnail,
scrapedplot)
# ------------------------------------------------------
# Extrae el 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:
xbmctools.addnewfolder(CHANNELNAME, "listseriesincaratula", category,
"!Página siguiente",
urlparse.urljoin(url, matches[0]), "", "")
# Label (top-right)...
xbmcplugin.setPluginCategory(handle=int(sys.argv[1]), category=category)
xbmcplugin.addSortMethod(handle=int(sys.argv[1]),
sortMethod=xbmcplugin.SORT_METHOD_TITLE)
xbmcplugin.endOfDirectory(handle=int(sys.argv[1]), succeeded=True)
def videolist(params, url, category):
xbmc.output("[rtvemediateca.py] videolist")
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
if url == "":
url = "http://www.rtve.es/mediateca/video/" + category + "/pagines_ajax/pagina1.html"
data = scrapertools.cachePage(url)
# xbmc.output(data)
# --------------------------------------------------------
# Extrae los videos
# --------------------------------------------------------
patron = '<div class="vthumb">.*?<a.*?href="([^"]+)"><img src="[^>]+><img src="([^"]+)[^>]+>.*?<a.*?href=[^>]+>([^<]+)</a></h2><span class="hour">([^<]+)</span>'
matches = re.compile(patron, re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
try:
scrapedtitle = unicode(match[2] + " (" + match[3] + ")", "utf-8").encode("iso-8859-1")
except:
scrapedtitle = match[2] + " (" + match[3] + ")"
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
scrapedurl = urlparse.urljoin(url, match[0])
try:
scrapedplot = unicode(match[2], "utf-8").encode("iso-8859-1")
except:
scrapedplot = match[2]
scrapedplot = scrapertools.entityunescape(scrapedplot)
scrapedthumbnail = urlparse.urljoin(url, match[1])
if DEBUG:
xbmc.output("title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
xbmctools.addnewvideo("rtve", "play", CHANNELNAME, "", scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot)
# --------------------------------------------------------
# Extrae los videos
# --------------------------------------------------------
patron = '<a onclick="([^"]+)" href="javascript\:\/\/" rel="nofollow">Siguiente<'
matches = re.compile(patron, re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
if len(matches) > 0:
# pagina('content_videos','2', '/mediateca/video/programas/series/aguila-roja')
# http://www.rtve.es/mediateca/video/programas/series/aguila-roja/pagines_ajax/pagina1.html
# http://www.rtve.es/mediateca/video/programas/series/aguila-roja/pagines_ajax/pagina2.html
scrapedtitle = "Página siguiente"
scrapedurl = "http://www.rtve.es" + matches[0][30:-2] + "/pagines_ajax/pagina" + matches[0][25:26] + ".html"
scrapedplot = ""
scrapedthumbnail = ""
if DEBUG:
xbmc.output("title=[" + scrapedtitle + "], url=[" + scrapedurl + "], thumbnail=[" + scrapedthumbnail + "]")
# Añade al listado de XBMC
xbmctools.addnewfolder(
CHANNELCODE, "videolist", category, scrapedtitle, scrapedurl, scrapedthumbnail, scrapedplot
)
xbmcplugin.setPluginCategory(handle=pluginhandle, category=category)
xbmcplugin.addSortMethod(handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE)
xbmcplugin.endOfDirectory(handle=pluginhandle, succeeded=True)
def espanoles(params,url,category):
xbmc.output("[rtveprogramas.py] espanoles")
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
data = scrapertools.cachePage(url)
#xbmc.output(data)
# --------------------------------------------------------
# Extrae las categorias (carpetas)
# --------------------------------------------------------
#<div class="mark"><div class="news bg01 comp"><span class="imgL"><a href="http://www.rtve.es/television/espanoles-en-el-mundo/camerun/" title="Destino#46 Camerún"><img src="/imagenes/destino46-camerun/1267557505140.jpg" alt="Destino#46 Camerún" title="Destino#46 Camerún"/></a></span><h3 class="M "><a href="http://www.rtve.es/television/espanoles-en-el-mundo/camerun/" title="Destino#46 Camerún">Destino#46 Camerún</a></h3><div class="chapeaux">Este destino es mucho más que un país... es todo un continente. <strong>Vuelve a verlo</strong>.</div></div></div>
#<div class="mark"><div class="news bg01 comp"><span class="imgT"><a href="http://www.rtve.es/television/espanoles-en-el-mundo/jalisco/" title="Destino#42 Jalisco (México)"><img src="/imagenes/destino42-jalisco-mexico/1264699947886.jpg" alt="Destino#42 Jalisco (México)" title="Destino#42 Jalisco (México)"/></a></span><h3 class="M "><a href="http://www.rtve.es/television/espanoles-en-el-mundo/jalisco/" title="Destino#42 Jalisco (México)">Destino#42 Jalisco (México)</a></h3><div class="chapeaux">¿Sabías que hay mariachis de chicas? ¿De dónde viene el tequila? <strong>Vuelve a verlo</strong>.</div></div></div><div class="mark"><div class="
patron = '<div class="mark"><div class="news bg01 comp"><span class="img."><a href="([^"]+)" title="([^"]+)"><img src="([^"]+)" alt="[^"]+" title="[^"]+"/></a></span><h. class=". "><a href="[^"]+" title="[^"]+">([^<]+)</a></h.><div class="chapeaux">([^<]+)<'
matches = re.compile(patron,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
for match in matches:
# Datos
scrapedtitle = scrapertools.entityunescape(match[3])
scrapedurl = urlparse.urljoin(url, match[0])
scrapedthumbnail = urlparse.urljoin(url, match[2])
scrapedplot = match[4]
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELCODE , "generico" , CHANNELNAME , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
# --------------------------------------------------------
# Descarga la página
# --------------------------------------------------------
url = "http://www.rtve.es/television/espanoles-en-el-mundo/programas-anteriores/"
data = scrapertools.cachePage(url)
#xbmc.output(data)
# --------------------------------------------------------
# Extrae las categorias (carpetas)
# --------------------------------------------------------
#<div class="news bg01 comp"><span class="imgT"><a href="http://www.rtve.es/television/espanoles-en-el-mundo/seul/" title="Destino#28 Seúl">
#<img src="/imagenes/destino28-seul/1264701360856.jpg" alt="Destino#28 Seúl" title="Destino#28 Seúl"/></a></span>
#<h3 class="M "><a href="http://www.rtve.es/television/espanoles-en-el-mundo/seul/" title="Destino#28 Seúl">Destino#28 Seúl</a></h3><div class="chapeaux"> Viajamos a la capital de Corea del Sur, la segunda urbe más poblada del planeta.<strong> Vuelve a verlo</strong></div>
patron = '<div class="news bg01 comp">[^<]*'
patron += '<span class="img."><a href="([^"]+)" title="[^"]+"><img src="([^"]+)" alt="[^"]+" title="[^"]+"/></a></span>[^<]*'
patron += '<h. class=". ">[^<]*'
patron += '<a href="[^"]+" title="([^"]+)">([^<]+)</a>[^<]*'
patron += '</h.>[^<]*'
patron += '<div class="chapeaux">(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
for match in matches:
# Datos
scrapedtitle = scrapertools.entityunescape(match[3])
scrapedurl = urlparse.urljoin(url, match[0])
scrapedthumbnail = urlparse.urljoin(url, match[1])
scrapedplot = match[4]
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELCODE , "generico" , CHANNELNAME , 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 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 listvideos(params,url,category):
logger.info("[peliculas21.py] listvideos")
if url=="":
url = "http://www.peliculas21.com"
# Descarga la página
data = scrapertools.cachePage(url)
#logger.info(data)
#title = urllib.unquote_plus(params.get("title"))
#thumbnail = urllib.unquote_plus(params.get("thumbnail"))
#plot = urllib.unquote_plus(params.get("plot"))
# Busca el area donde estan los videos y la descripcion
patronvideos = '<div class="peliculadoblaje">(.*?)<!-- FIN #content-->'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
# busca el titulo y el thumbnail
patronvideos = '<img src="([^"]+)"[^>]+>[^<]+<[^>]+>([^<]+)</div>'
matches2 = re.compile(patronvideos,re.DOTALL).findall(matches[0])
for match in matches2:
title = match[1]
thumbnail = urlparse.urljoin(url,match[0])
plot = ""
patronvideos = '<b>Duración:</b>(.*?)<br />'
duracion = re.compile(patronvideos,re.DOTALL).findall(matches[0])
if len(duracion)>0:plot = "Duracion:"+duracion[0] + "\n"
patronvideos = '<b>Género:</b>(.*?)<br />'
genero = re.compile(patronvideos,re.DOTALL).findall(matches[0])
if len(genero)>0:plot = plot + "Genero: "+genero[0] +"\n"
patronvideos = '<b>Sinopsis:</b>(.*?)</div>'
sinopsis = re.compile(patronvideos,re.DOTALL).findall(matches[0])
# Busca los actores
matchesactores = buscactores(matches[0])
if len(matchesactores)>0:
plot = plot + "Actores: "
c = 0
actores = "ACTORES DE ESTA PELICULA :\n\n"
for match in matchesactores:
c = c + 1
actores = actores + "-"+match[1] + "\n"
if c == 3:
plot = plot + match[1] + "\n"
elif c == 4:
plot = plot + "* " + match[1]+" "
else:
plot = plot + match[1]+ " , "
plot = plot + "\nSinopsis: " + sinopsis[0]
plot = re.sub("<[^>]+>"," ",plot)
# Busca el trailer
patronvideos = '<param name="movie" value="([^"]+)"></param>'
matchtrailer = re.compile(patronvideos,re.DOTALL).findall(matches[0])
if len(matchtrailer)>0:
for match in matchtrailer:
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "youtubeplay" , category ,"Directo", "Ver El Trailer de : "+title , match , thumbnail, plot )
else:
import trailertools
# Añade al listado de XBMC
xbmctools.addnewfolder( "trailertools" , "buscartrailer" , category , "Buscar trailer para : "+title , url , os.path.join(IMAGES_PATH, 'trailertools.png'), plot )
matchesBK = matches[0]
# Extrae las entradas (videos) para megavideo con tipo de audio
patronvideos = '<span style="font-size:12px;"><strong>(.*?)</strong></span><br/>.*?'
patronvideos += '<span.*?>.*?<a href="http\:\/\/www.megavideo.com\/[\?v=|v/]+([A-Z0-9]{8}).*?" target="_blank">1</a>.</span><br />'
matches = re.compile(patronvideos,re.DOTALL).findall(matches[0])
scrapertools.printMatches(matches)
encontrados = set()
for match in matches:
if match[1] not in encontrados:
encontrados.add(match[1])
# Titulo
scrapedtitle = title + " - [" +scrapertools.entityunescape(match[0])+ "]" + " (Megavideo)"
# URL
scrapedurl = match[1]
# Thumbnail
scrapedthumbnail = thumbnail
# Argumento
scrapedplot = plot
# Depuracion
if (DEBUG):
logger.info("scrapedtitle="+scrapedtitle)
logger.info("scrapedurl="+scrapedurl)
logger.info("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,"Megavideo", scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
if len(matches)==0:
listavideos = servertools.findvideos(data)
encontrados = set()
for titulo,scrapedurl,servidor in listavideos:
if scrapedurl.strip() not in encontrados:
encontrados.add(scrapedurl.strip())
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,servidor, title+ " - %s" % titulo , scrapedurl , thumbnail, plot )
# Extrae las entradas (videos) directos
patronvideos = 'flashvars="file=([^\&]+)\&controlbar=over'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
data1 = scrapertools.cachePage(matches[0])
#logger.info(data)
patron = 'author">(.*?)</media:credit>.*?<media\:content url="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(data1)
scrapertools.printMatches(matches)
for match in matches:
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category , "Directo" , title +" - ["+match[0]+"]"+ " (Directo)" , match[1] , thumbnail , plot )
# Busca otras peliculas relacionadas con los actores
if len(matchesactores)>0:
titulo = "Busca otros Films de los actores de esta pelicula"
xbmctools.addnewfolder( CHANNELNAME , "listaractores" , category , titulo , matchesBK , thumbnail, actores )
# Lista peliculas relacionadas
titulo = "Ver Peliculas Relacionadas"
matches = buscarelacionados(matchesBK)
plot2 = "PELICULAS RELACIONADAS :\n\n"
for match in matches:
plot2 = plot2 + "-"+match[1]+"\n"
xbmctools.addnewfolder( CHANNELNAME , "listarelacionados" , category , titulo , matchesBK , thumbnail, plot2 )
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
# Disable sorting...
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def ListarVideos(params,url,category):
url1 = "http://www.series21.com"
url1 = urlparse.urljoin(url1,url)
title = urllib.unquote_plus(params.get("title"))
thumbnail = urllib.unquote_plus(params.get("thumbnail"))
plot = urllib.unquote_plus(params.get("plot"))
data = scrapertools.cachePage(url1)
# Busca el area donde estan los videos y la descripcion
patronvideos = '<div id="content">(.*?)<!-- FIN #content-->'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
matchesBK = matches[0]
# Extrae las entradas (videos) para megavideo
patronvideos = '<span style="font-size:12px;"><strong>(.*?)</strong></span><br/>.*?'
patronvideos += '<span.*?>.*?<a href="http\:\/\/www.megavideo.com\/([\?v=|v/|\?d=]+)([A-Z0-9]{8}).*?" target'
matches = re.compile(patronvideos,re.DOTALL).findall(matches[0])
scrapertools.printMatches(matches)
encontrados = set()
for match in matches:
if match[2] not in encontrados:
encontrados.add(match[2])
if 'v' in match[1]:
server = "Megavideo"
else:
server = "Megaupload"
doblaje = scrapertools.entityunescape(match[0])
# Titulo
scrapedtitle = title + " - [" +doblaje+ "]" + " ("+server+")"
# URL
scrapedurl = match[2]
# Thumbnail
scrapedthumbnail = thumbnail
# Argumento
#print 'este es el plot %s ' %plot
#print ' doblaje %s ' %doblaje
scrapedplot = plot
if ("Español" in plot) and not (doblaje in plot):
scrapedplot = scrapedplot.replace("Español",doblaje)
elif "subtitulado" in plot and not (doblaje in plot):
scrapedplot = scrapedplot.replace("Versión original (subtitulado)",doblaje)
elif not doblaje in plot:
scrapedplot += "\n" + "Doblaje : " + doblaje
# Depuracion
if (DEBUG):
logger.info("scrapedtitle="+scrapedtitle)
logger.info("scrapedurl="+scrapedurl)
logger.info("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,server, scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
if len(matches)==0:
listavideos = servertools.findvideos(data)
encontrados = set()
for titulo,scrapedurl,servidor in listavideos:
if scrapedurl.strip() not in encontrados:
encontrados.add(scrapedurl.strip())
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,servidor, title+ " - %s" %titulo , scrapedurl , thumbnail, plot )
patronvideos = '<span class="bloque-doblaje">(.+?)</span>[^<]+'
patronvideos +='<span class="bloque-link">[^<]+<a href="javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)"(.+?)</span>'
#patronvideos +='(?:\| <a href="javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)".*?)</span>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
# URL
if "megavideo" in match[2]:
server = "Megavideo"
elif "megaupload" in match[2]:
server = "Megaupload"
if "esp.gif" in match[0]:
doblaje = "Español"
else:
doblaje = match[0].strip()
base64 = decrypt21.Base64()
try:
url2 = re.compile("javascript\:goTo\(\'([^\']+)\'\, \'([^\']+)\'\)").findall(match[3])[0]
scrapedurl2 = base64._extract_code(base64.decode(url2[0]))
scrapedurl = base64._extract_code(base64.decode(match[1]))
part1 = " Parte 1 "
part2 = " Parte 2 "
scrapedtitle2 = title + part2+ " - [" +doblaje+ "]" + " ("+server+")"
#print match[3]
except:
scrapedurl = base64._extract_code(base64.decode(match[1]))
part1 = ""
part2 = ""
scrapedtitle = title + part1+ " - [" +doblaje+ "]" + " ("+server+")"
# Thumbnail
scrapedthumbnail = thumbnail
# Argumento
scrapedplot = plot
# Depuracion
if (DEBUG):
logger.info("scrapedtitle="+scrapedtitle)
logger.info("scrapedurl="+scrapedurl)
logger.info("scrapedthumbnail="+scrapedthumbnail)
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,server, scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
if part2:
xbmctools.addnewvideo( CHANNELNAME , "play" , category ,server, scrapedtitle2 , scrapedurl2 , scrapedthumbnail, scrapedplot )
# Extrae las entradas (videos) directos
patronvideos = 'flashvars="file=([^\&]+)\&controlbar=over'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
if len(matches)>0:
data1 = scrapertools.cachePage(matches[0])
#logger.info(data)
patron = 'author">(.*?)</media:credit>.*?<media\:content url="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(data1)
scrapertools.printMatches(matches)
for match in matches:
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "play" , category , "Directo" , title +" - ["+match[0]+"]"+ " (Directo)" , match[1] , thumbnail , plot )
# Busca el Spoiler
patronvideos = '(http://www.youtube.com[^"]+)"'
matchSpoiler = re.compile(patronvideos,re.DOTALL).findall(data)
if len(matchSpoiler)>0:
encontrados = set()
for match in matchSpoiler:
if match not in encontrados:
encontrados.add(match)
# Añade al listado de XBMC
xbmctools.addnewvideo( CHANNELNAME , "youtubeplay" , category ,"Directo", "Ver El Spoiler de : "+title , match , thumbnail, "Ver Video Spoiler" )
# Lista series relacionadas
titulo = "Ver otros capitulos de esta temporada"
matches = buscarelacionados(matchesBK)
plot2 = "CAPITULOS DE ESTA TEMPORADA :\n\n"
for match in matches:
plot2 = plot2 + "-"+match[2]+"\n"
xbmctools.addnewfolderextra( CHANNELNAME , "listarelacionados" , category , titulo , url , thumbnail, plot2,matchesBK )
#<div class="film"><a href="/house/#t_57"><img src="/thumbs/temporadas/95/120/57.jpg"
# Cambiar de Temporada
patron = 'div class="film"><a href="([^"]+)"><img src="([^"]+)" style'
matchSerie= re.compile(patron,re.DOTALL).findall(matchesBK)
if len(matchSerie)>1:
for temp in matchSerie:
url2 = urlparse.urljoin(url1,temp[0])
thumbnail = urlparse.urljoin(url1,temp[1])
titulo = "Cambiar a otras temporadas"
titulo_serie = temp[0].split("/")
titulo2 = titulo_serie[1].replace("-"," ")
#print ' titulo%s ' %titulo2
xbmctools.addnewfolderextra( CHANNELNAME , "listarTemporada" , category , titulo , url2 , thumbnail, plot,titulo2 )
break
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
# Disable sorting...
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
def peliculas(item):
logger.info("[cinetube.py] peliculas")
url = item.url
# Descarga la página
data = scrapertools.cachePage(url)
# Extrae las entradas
'''
<!--PELICULA-->
<div class="peli_item textcenter">
<div class="pelicula_img"><a href='/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html' >
<img src="http://caratulas.cinetube.es/pelis/7058.jpg" alt="Un segundo después 2" /></a>
</div><a href="/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html" ><div class="dvdrip"></div></a><a href='/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html' ><p class="white">Un segundo después 2</p></a><p><span class="rosa">DVD-RIP</span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div>
</div>
<!--FIN PELICULA-->
'''
# listado alfabetico
'''
<!--PELICULA-->
<div class="peli_item textcenter">
<div class="pelicula_img"><a href="/peliculas/musical/ver-pelicula-a-chorus-line.html">
<img src="http://caratulas.cinetube.es/pelis/246.jpg" alt="A Chorus Line" /></a>
</div>
<a href="/peliculas/musical/ver-pelicula-a-chorus-line.html"><p class="white">A Chorus Line</p></a>
<p><span class="rosa">DVD-RIP</span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div> </div>
<!--FIN PELICULA-->
'''
'''
<!--PELICULA-->
<div class="peli_item textcenter"><a href="/documentales/otros/ver-documental-tu-cerebro-inmortal.html">
<div class="pelicula_img">
<img src="http://caratulas.cinetube.es/docus/9570.jpg" alt="Tu Cerebro Inmortal" />
</div>
<p class="white"><a class="white" href="/documentales/otros/ver-documental-tu-cerebro-inmortal.html" title="Ver documental Tu Cerebro Inmortal">Tu Cerebro Inmortal</a></p></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/espanol.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> </div>
<!--FIN PELICULA-->
'''
patronvideos = '<!--PELICULA-->[^<]+'
patronvideos += '<div class="peli_item textcenter">[^<]+'
patronvideos += '<div class="pelicula_img"><a[^<]+'
patronvideos += '<img src=["|\']([^"]+?)["|\'][^<]+</a>[^<]+'
patronvideos += '</div[^<]+<a href=["|\']([^"]+?)["|\'].*?<p class="white">([^<]+)</p>.*?<p><span class="rosa">([^>]+)</span></p><div class="icos_lg">(.*?)</div>'
matches = re.compile(patronvideos, re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
scrapedtitle = match[2] + " [" + match[3] + "]"
matchesconectores = re.compile('<img.*?alt="([^"]*)"',
re.DOTALL).findall(match[4])
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")
# Convierte desde UTF-8 y quita entidades HTML
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# procesa el resto
scrapedplot = ""
scrapedurl = urlparse.urljoin("http://www.cinetube.es/", match[1])
scrapedthumbnail = match[0]
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
#<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(url, matches[0])
itemlist.append(
Item(channel=CHANNELNAME,
action="peliculas",
title="!Página siguiente",
url=scrapedurl,
folder=True))
return itemlist
def listtemporadacaratula(params,url,category):
xbmc.output("[cinetube.py] listtemporadacaratula")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
#xbmc.output(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
'''
<li>
<a href="/series/the-middleman/temporada-1/"><img src="http://caratulas.cinetube.es/series/233.jpg" alt="peli" /></a>
<p><span class="rosa"></span></p><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="" /> </div> <p class="tit_ficha">The middleman </p>
<p class="tem_fich">1a Temporada</p>
</li>
'''
'''
<li>
<a href="/series/cranford-de-e-gaskell/"><img src="http://caratulas.cinetube.es/series/64.jpg" alt="peli" /></a>
<p><span class="rosa"></span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div> <p class="tit_ficha">Cranford, de E. Gaskell </p>
</li>
'''
patronvideos = '<li>[^<]+'
patronvideos += '<a href="([^"]+)"><img src="([^"]+)"[^>]+></a>[^<]+'
patronvideos += '<p><span class="rosa"></span></p><div class="icos_lg">(.*?)</div>[^<]+'
patronvideos += '<p class="tit_ficha">([^<]+)</p>[^<]+'
patronvideos += '<p class="tem_fich">([^<]+)</p>[^<]+'
patronvideos += '</li>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[3].strip() + " - " + match[4].strip()
matchesconectores = re.compile('<img.*?alt="([^"]*)"',re.DOTALL).findall(match[2])
conectores = ""
for matchconector in matchesconectores:
xbmc.output("matchconector="+matchconector)
if matchconector=="":
matchconector = "megavideo"
conectores = conectores + matchconector + "/"
if len(matchesconectores)>0:
scrapedtitle = scrapedtitle + " (" + conectores[:-1] + ")"
# Convierte desde UTF-8 y quita entidades HTML
try:
scrapedtitle = unicode( scrapedtitle, "utf-8" ).encode("iso-8859-1")
except:
pass
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# procesa el resto
scrapedplot = ""
scrapedurl = urlparse.urljoin(url,match[0])
scrapedthumbnail = match[1]
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELNAME , "listmirrors" , category , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
# ------------------------------------------------------
# Extrae el 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:
xbmctools.addnewfolder( CHANNELNAME , "listtemporadacaratula" , category , "!Página siguiente" , urlparse.urljoin(url,matches[0]) , "", "" )
# 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 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 peliculas(item):
logger.info("[cinetube.py] peliculas")
url = item.url
# Descarga la página
data = scrapertools.cachePage(url)
# Extrae las entradas
'''
<!--PELICULA-->
<div class="peli_item textcenter">
<div class="pelicula_img"><a href='/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html' >
<img src="http://caratulas.cinetube.es/pelis/7058.jpg" alt="Un segundo después 2" /></a>
</div><a href="/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html" ><div class="dvdrip"></div></a><a href='/peliculas/thriller/ver-pelicula-un-segundo-despues-2.html' ><p class="white">Un segundo después 2</p></a><p><span class="rosa">DVD-RIP</span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div>
</div>
<!--FIN PELICULA-->
'''
# listado alfabetico
'''
<!--PELICULA-->
<div class="peli_item textcenter">
<div class="pelicula_img"><a href="/peliculas/musical/ver-pelicula-a-chorus-line.html">
<img src="http://caratulas.cinetube.es/pelis/246.jpg" alt="A Chorus Line" /></a>
</div>
<a href="/peliculas/musical/ver-pelicula-a-chorus-line.html"><p class="white">A Chorus Line</p></a>
<p><span class="rosa">DVD-RIP</span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div> </div>
<!--FIN PELICULA-->
'''
'''
<!--PELICULA-->
<div class="peli_item textcenter"><a href="/documentales/otros/ver-documental-tu-cerebro-inmortal.html">
<div class="pelicula_img">
<img src="http://caratulas.cinetube.es/docus/9570.jpg" alt="Tu Cerebro Inmortal" />
</div>
<p class="white"><a class="white" href="/documentales/otros/ver-documental-tu-cerebro-inmortal.html" title="Ver documental Tu Cerebro Inmortal">Tu Cerebro Inmortal</a></p></a>
<div class="icos_lg"><img src="http://caratulas.cinetube.es/img/cont/espanol.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> </div>
<!--FIN PELICULA-->
'''
patronvideos = '<!--PELICULA-->[^<]+'
patronvideos += '<div class="peli_item textcenter">[^<]+'
patronvideos += '<div class="pelicula_img"><a[^<]+'
patronvideos += '<img src=["|\']([^"]+?)["|\'][^<]+</a>[^<]+'
patronvideos += '</div[^<]+<a href=["|\']([^"]+?)["|\'].*?<p class="white">([^<]+)</p>.*?<p><span class="rosa">([^>]+)</span></p><div class="icos_lg">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
itemlist = []
for match in matches:
scrapedtitle = match[2] + " [" + match[3] + "]"
matchesconectores = re.compile('<img.*?alt="([^"]*)"',re.DOTALL).findall(match[4])
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")
# Convierte desde UTF-8 y quita entidades HTML
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# procesa el resto
scrapedplot = ""
scrapedurl = urlparse.urljoin("http://www.cinetube.es/",match[1])
scrapedthumbnail = match[0]
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
#<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(url,matches[0])
itemlist.append( Item(channel=CHANNELNAME, action="peliculas", title="!Página siguiente" , url=scrapedurl , folder=True) )
return itemlist
def listpeliconcaratula(params,url,category):
xbmc.output("[cinetube.py] listpeliconcaratula")
# ------------------------------------------------------
# Descarga la página
# ------------------------------------------------------
data = scrapertools.cachePage(url)
#xbmc.output(data)
# ------------------------------------------------------
# Extrae las entradas
# ------------------------------------------------------
'''
<!--PELICULA-->
<div class="peli_item textcenter" style="cursor:pointer;" onclick="location.href='/peliculas/intriga/ver-pelicula-a-espaldas-de-la-ley.html'">
<div class="pelicula_img">
<img src="http://caratulas.cinetube.es/pelis/251.jpg" alt="A espaldas de la ley" />
</div>
<p class="white">A espaldas de la ley</p>
<p><span class="rosa">DVD-RIP</span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div> </div>
'''
'''
DOCUMENTAL
<!--PELICULA-->
<div class="peli_item textcenter" style="cursor:pointer;" onclick="location.href='/documentales/serie-documental/ver-documental-planeta-azul.html'">
<div class="pelicula_img">
<img src="http://caratulas.cinetube.es/docus/366.jpg" alt="Planeta Azul" />
</div>
<p class="white">Planeta Azul</p>
<p><span class="rosa"></span></p><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="" /><img src="http://caratulas.cinetube.es/img/cont/ddirecta.png" alt="descarga directa" /> </div> </div>
'''
patronvideos = '<!--PELICULA-->[^<]+'
patronvideos += '<div class="peli_item textcenter" style="cursor:pointer;" onclick="location.href=\'/([^\']+)\'">[^<]+'
patronvideos += '<div class="pelicula_img">[^<]+'
patronvideos += '<img src="([^"]+)" alt="[^"]+" />[^<]+'
patronvideos += '</div>[^<]*<p class="white">([^<]+)</p>[^<]*<p><span class="rosa">([^<]+)</span></p>'
patronvideos += '<div class="icos_lg">(.*?)</div>'
matches = re.compile(patronvideos,re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
# Titulo
scrapedtitle = match[2] + " [" + match[3] + "]"
matchesconectores = re.compile('<img.*?alt="([^"]*)"',re.DOTALL).findall(match[4])
conectores = ""
for matchconector in matchesconectores:
xbmc.output("matchconector="+matchconector)
if matchconector=="":
matchconector = "megavideo"
conectores = conectores + matchconector + "/"
if len(matchesconectores)>0:
scrapedtitle = scrapedtitle + " (" + conectores[:-1] + ")"
# Convierte desde UTF-8 y quita entidades HTML
try:
scrapedtitle = unicode( scrapedtitle, "utf-8" ).encode("iso-8859-1")
except:
pass
scrapedtitle = scrapertools.entityunescape(scrapedtitle)
# procesa el resto
scrapedplot = ""
scrapedurl = urlparse.urljoin("http://www.cinetube.es/",match[0])
scrapedthumbnail = match[1]
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Añade al listado de XBMC
xbmctools.addnewfolder( CHANNELNAME , "listmirrors" , category , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
# ------------------------------------------------------
# Extrae el 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:
xbmctools.addnewfolder( CHANNELNAME , "listpeliconcaratula" , category , "!Página siguiente" , urlparse.urljoin(url,matches[0]) , "", "" )
# 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 videolist(params,url,category):
xbmc.output("[skai_folders.py] videolist")
# --------------------------------------------------------
# DDownload page
# --------------------------------------------------------
data = scrapertools.cachePage(url)
# Extrae los vídeos
patron = '<p><a href=\'(.*?)\' title=.*?<img alt="([^<]+)" src="(.*?)" /></a></p>.*?<dd> <p>(.*?)</dd>'
pattern = '<meta name="description" content="(.*?)">'
matches = re.compile(patron,re.DOTALL).findall(data)
if DEBUG:
scrapertools.printMatches(matches)
for match in matches:
scrapedtitle = match[1]
scrapedurl = urlparse.urljoin(url,unescape(match[0]))
scrapedthumbnail = urlparse.urljoin(url,match[2])
data1 = scrapertools.cachePage(scrapedurl)
matches1 = re.compile(pattern,re.DOTALL).findall(data1)
if len(matches1)>0:
match1 = matches1[0]
scrapedplot = scrapertools.entityunescape(match1)
scrapedplot = unescape(HTMLParser.HTMLParser().unescape(scrapedplot))
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Add to the list of XBMC
xbmctools.addnewvideo( CHANNELCODE , "play" , CHANNELNAME , "" , scrapedtitle , scrapedurl , scrapedthumbnail, scrapedplot )
# Next Page
pattern = 'class="next_page" rel="next" href="(.*?)">'+("Next","Επόμενη",)[int(config.getSetting("locale"))]+'</a></p>'
matches = re.compile(pattern,re.DOTALL).findall(data)
if DEBUG: scrapertools.printMatches(matches)
if len(matches)>0:
match = matches[0]
scrapedtitle = ">>> Next Page >>>"
scrapedurl = urlparse.urljoin(url,match)
scrapedthumbnail = ""
scrapedplot = ""
if (DEBUG): xbmc.output("title=["+scrapedtitle+"], url=["+scrapedurl+"], thumbnail=["+scrapedthumbnail+"]")
# Add to the list of XBMC
#xbmctools.addnewfolder( CHANNELCODE , "videolist" , CHANNELNAME , scrapedtitle , scrapedurl , scrapedthumbnail , scrapedplot )
### recursion for flattening the pages ###
videolist(params,scrapedurl,category)
# Label (top-right)...
xbmcplugin.setPluginCategory( handle=pluginhandle, category=category )
# Disable sorting...
xbmcplugin.addSortMethod( handle=pluginhandle, sortMethod=xbmcplugin.SORT_METHOD_NONE )
# End of directory...
xbmcplugin.endOfDirectory( handle=pluginhandle, succeeded=True )
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 )
