def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[upafile.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
data = scrapertools.cache_page(page_url)
#<script type='text/javascript'>eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('11 0=10 z(\'2://4.3/6/6.y\',\'6\',\'x\',\'w\',\'9\');0.5(\'v\',\'u\');0.5(\'t\',\'s\');0.5(\'r\',\'q\');0.1(\'p\',\'\');0.1(\'o\',\'2://a.4.3:n/d/m/8.l\');0.1(\'k\',\'2://a.4.3/i/j/h.g\');0.1(\'7\',\'8\');0.1(\'7\',\'2\');0.1(\'2.f\',\'e\');0.c(\'b\');',36,38,'s1|addVariable|http|com|upafile|addParam|player|provider|video||s82|flvplayer|write||start|startparam|jpg|idyoybh552bf||00024|image|mp4|k65ufdsgg7pvam5r5o22urriqvsqzkkf4cu3biws2xwxsvgmrfmjyfbz|182|file|duration|opaque|wmode|always|allowscriptaccess|true|allowfullscreen|400|500|swf|SWFObject|new|var'.split('|')))
patron = "<script type='text/javascript'>(eval\(function\(p,a,c,k,e,d\).*?)</script>"
matches = re.compile(patron,re.DOTALL).findall(data)
cifrado=""
for match in matches:
logger.info("match="+match)
if "mp4" in match or "flv" in match or "video" in match:
cifrado = match
break
# Extrae la URL del vídeo
logger.info("cifrado="+cifrado)
descifrado = unpackerjs.unpackjs(cifrado)
descifrado = descifrado.replace("\\","")
logger.info("descifrado="+descifrado)
#s1.addVariable('file','http://s82.upafile.com:182/d/k65ufdsgg7pvam5r5o22urriqvsqzkkf4cu3biws2xwxsvgmrfkxwzx4/video.mp4')
media_url = scrapertools.get_match(descifrado,"addVariable\('file','([^']+)'")
if len(matches)>0:
video_urls.append( [ scrapertools.get_filename_from_url(media_url)[-4:]+" [upafile]",media_url])
for video_url in video_urls:
logger.info("[upafile.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("pelisalacarta.gamovideo get_video_url(page_url='%s')" % page_url)
# Lo pide una vez
headers = [['User-Agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14']]
data = scrapertools.cache_page( page_url , headers=headers )
#logger.info("data="+data)
try:
'''
<input type="hidden" name="op" value="download1">
<input type="hidden" name="usr_login" value="">
<input type="hidden" name="id" value="auoxxtvyquoy">
<input type="hidden" name="fname" value="Star.Trek.Into.Darkness.2013.HD.m720p.LAT.avi">
<input type="hidden" name="referer" value="">
<input type="hidden" name="hash" value="1624-83-46-1377796069-b5e6b8f9759d080a3667adad637f00ac">
<input type="submit" name="imhuman" value="Continue to Video" id="btn_download">
'''
op = scrapertools.get_match(data,'<input type="hidden" name="op" value="(down[^"]+)"')
usr_login = ""
id = scrapertools.get_match(data,'<input type="hidden" name="id" value="([^"]+)"')
fname = scrapertools.get_match(data,'<input type="hidden" name="fname" value="([^"]+)"')
referer = scrapertools.get_match(data,'<input type="hidden" name="referer"\s+value="([^"]*)"')
hashvalue = scrapertools.get_match(data,'<input type="hidden" name="hash" value="([^"]*)"')
submitbutton = scrapertools.get_match(data,'<input type="submit" name="imhuman" value="([^"]+)"').replace(" ","+")
import time
time.sleep(5)
# Lo pide una segunda vez, como si hubieras hecho click en el banner
#op=download1&usr_login=&id=auoxxtvyquoy&fname=Star.Trek.Into.Darkness.2013.HD.m720p.LAT.avi&referer=&hash=1624-83-46-1377796019-c2b422f91da55d12737567a14ea3dffe&imhuman=Continue+to+Video
#op=search&usr_login=&id=auoxxtvyquoy&fname=Star.Trek.Into.Darkness.2013.HD.m720p.LAT.avi&referer=&hash=1624-83-46-1377796398-8020e5629f50ff2d7b7de99b55bdb177&imhuman=Continue+to+Video
post = "op="+op+"&usr_login="******"&id="+id+"&fname="+fname+"&referer="+referer+"&hash="+hashvalue+"&imhuman="+submitbutton
headers.append(["Referer",page_url])
data = scrapertools.cache_page( page_url , post=post, headers=headers )
#logger.info("data="+data)
except:
import traceback
traceback.print_exc()
# Extrae la URL
logger.info("data="+data)
data = scrapertools.find_single_match(data,"<script type='text/javascript'>(.*?)</script>")
logger.info("data="+data)
data = unpackerjs.unpackjs(data)
logger.info("data="+data)
pfile = scrapertools.get_match(data,'file\s*\:\s*"([^"]+)"')
pstreamer = scrapertools.get_match(data,'streamer\s*\:\s*"([^"]+)"')
media_url = pstreamer+" playpath="+pfile
video_urls = []
video_urls.append( [ "RTMP [gamovideo]",media_url])
for video_url in video_urls:
logger.info("[gamovideo.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("videostoring get_video_url(page_url='%s')" % page_url)
if not "embed" in page_url:
page_url = page_url.replace(
"http://www.videostoring.com/",
"http://www.videostoring.com/embed-") + ".html"
data = scrapertools.cache_page(page_url)
data = scrapertools.find_single_match(
data, "<script type='text/javascript'>(.*?)</script>")
data = unpackerjs.unpackjs(data)
url = scrapertools.get_match(data, '<param name="src"value="([^"]+)"/>')
video_urls = []
video_urls.append([
scrapertools.get_filename_from_url(url)[-4:] + " [videostoring]", url
])
for video_url in video_urls:
logger.info("[videostoring.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("pelisalacarta.gamovideo get_video_url(page_url='%s')" %
page_url)
if not "embed" in page_url:
page_url = page_url.replace(
"http://gamovideo.com/",
"http://gamovideo.com/embed-") + "-640x360.html"
data = scrapertools.cache_page(page_url)
data = scrapertools.find_single_match(
data, "<script type='text/javascript'>(.*?)</script>")
data = unpackerjs.unpackjs(data)
host = scrapertools.get_match(data, 'image:"(http://[^/]+/)')
flv_url = scrapertools.get_match(data, ',\{file:"([^"]+)"')
rtmp_url = scrapertools.get_match(data, '\[\{file:"([^"]+)"')
flv = host + flv_url.split("=")[1] + "/v.flv"
video_urls = []
video_urls.append(
[scrapertools.get_filename_from_url(flv)[-4:] + " [gamovideo]", flv])
#video_urls.append(["RTMP [gamovideo]",rtmp_url])
for video_url in video_urls:
logger.info("[gamovideo.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[vidxden.py] url="+page_url)
if ".html" not in page_url:
logger.info("[vidxden.py] URL incompleta")
data = scrapertools.cache_page(page_url)
patron = '<input name="fname" type="hidden" value="([^"]+)">'
matches = re.compile(patron,re.DOTALL).findall(data)
page_url = page_url+"/"+matches[0]+".html"
# Lo pide una vez
scrapertools.cache_page( page_url , headers=[['User-Agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14']] )
# Lo pide una segunda vez, como si hubieras hecho click en el banner
patron = 'http\:\/\/www\.vidxden\.com/([^\/]+)/(.*?)\.html'
matches = re.compile(patron,re.DOTALL).findall(page_url)
logger.info("[vidxden.py] fragmentos de la URL")
scrapertools.printMatches(matches)
codigo = ""
nombre = ""
if len(matches)>0:
codigo = matches[0][0]
nombre = matches[0][1]
post = "op=download1&usr_login=&id="+codigo+"&fname="+nombre+"&referer=&method_free=Free+Stream"
data = scrapertools.cache_page( page_url , post=post, headers=[['User-Agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14'],['Referer',page_url]] )
# Extrae el trozo cifrado
patron = '<div id="embedcontmvshre"[^>]+>(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
data = ""
if len(matches)>0:
data = matches[0]
logger.info("[vidxden.py] bloque packed="+data)
else:
logger.info("[vidxden.py] no encuentra bloque packed="+data)
return ""
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
# Extrae la URL del vídeo
logger.info("descifrado="+descifrado)
# Extrae la URL
patron = '<param name="src"value="([^"]+)"/>'
matches = re.compile(patron,re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
video_urls = []
if len(matches)>0:
video_urls.append( ["."+matches[0].rsplit('.',1)[1]+" [vidxden]",matches[0]])
for video_url in video_urls:
logger.info("[vidxden.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[downupload.py] get_video_url(page_url='%s')" % page_url)
page_url = page_url.replace("amp;","")
data = scrapertools.cache_page(page_url)
video_urls = []
# s1.addVariable('file','http://78.140.181.136:182/d/kka3sx52abiuphevyzfirfaqtihgyq5xlvblnetok2mj4llocdeturoy/video.mp4');
# http://downupload.com:182/d/k2a3kxf2abiuphevyzfirgajremkk3if57xcpelwboz4hbzjnfsvbit6/video.mp4
patron = "(http://[\S]+\.mp4)"
matches = re.compile(patron,re.DOTALL).findall(data)
if len(matches)>0:
scrapertools.printMatches(matches)
for match in matches:
videourl = match
videourl = videourl.replace('%5C','')
videourl = urllib.unquote(videourl)
video_urls.append( [ ".mp4 [Downupload]" , videourl ] )
else:
# Si es un enlace de Descarga se busca el archivo
patron = '<div id="player_code">.*?value[\W]name[\W]param[\W]com[\W]http[\W]false[\W](.*?)[\W]divx[\W]previewImage[\W].*?[\W]custommode[\W](.*?)[\W](.*?)[\W](.*?)[\W]src'
matches = re.compile(patron,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
videourl = "http://"+match[0]+".com:"+match[3]+"/d/"+match[2]+"/video."+match[1]
videourl = videourl.replace('|','.')
videourl = urllib.unquote(videourl)
video_urls.append( [ "."+match[1]+" [Downupload]" , videourl ] )
# Localiza enlaces con IP
if len(matches)==0:
patron = '<div id="player_code">.*?value[\W]name[\W]param[\W]http[\W]false[\W](.*?)[\W](.*?)[\W](.*?)[\W](.*?)[\W]divx[\W]previewImage[\W].*?[\W]custommode[\W](.*?)[\W](.*?)[\W](.*?)[\W]src'
matches = re.compile(patron,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
for match in matches:
videourl = "http://"+match[3]+"."+match[2]+"."+match[1]+"."+match[0]+":"+match[6]+"/d/"+match[5]+"/video."+match[4]
videourl = videourl.replace('|','')
videourl = urllib.unquote(videourl)
video_urls.append( [ "."+match[4]+" [Downupload]" , videourl ] )
# Otro metodo de busqueda
if len(matches)==0:
url = unpackerjs.unpackjs(data)
logger.info("[unpackerjs.py] "+url)
patron = 'src"value="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(url)
for match in matches:
videourl = match
videourl = videourl.replace('|','')
videourl = urllib.unquote(videourl)
video_urls.append( [ "."+videourl.rsplit('.',1)[1]+" [Downupload]" , videourl ] )
for video_url in video_urls:
logger.info("[downupload.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[upafile.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
data = scrapertools.cache_page(page_url)
#<script type='text/javascript'>eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('11 0=10 z(\'2://4.3/6/6.y\',\'6\',\'x\',\'w\',\'9\');0.5(\'v\',\'u\');0.5(\'t\',\'s\');0.5(\'r\',\'q\');0.1(\'p\',\'\');0.1(\'o\',\'2://a.4.3:n/d/m/8.l\');0.1(\'k\',\'2://a.4.3/i/j/h.g\');0.1(\'7\',\'8\');0.1(\'7\',\'2\');0.1(\'2.f\',\'e\');0.c(\'b\');',36,38,'s1|addVariable|http|com|upafile|addParam|player|provider|video||s82|flvplayer|write||start|startparam|jpg|idyoybh552bf||00024|image|mp4|k65ufdsgg7pvam5r5o22urriqvsqzkkf4cu3biws2xwxsvgmrfmjyfbz|182|file|duration|opaque|wmode|always|allowscriptaccess|true|allowfullscreen|400|500|swf|SWFObject|new|var'.split('|')))
patron = "<script type='text/javascript'>(eval\(function\(p,a,c,k,e,d\).*?)</script>"
matches = re.compile(patron,re.DOTALL).findall(data)
cifrado=""
for match in matches:
logger.info("match="+match)
if "mp4" in match or "flv" in match or "video" in match:
cifrado = match
break
# Extrae la URL del vídeo
logger.info("cifrado="+cifrado)
descifrado = unpackerjs.unpackjs(cifrado)
descifrado = descifrado.replace("\\","")
logger.info("descifrado="+descifrado)
#s1.addVariable('file','http://s82.upafile.com:182/d/k65ufdsgg7pvam5r5o22urriqvsqzkkf4cu3biws2xwxsvgmrfkxwzx4/video.mp4')
media_url = scrapertools.get_match(descifrado,"addVariable\('file','([^']+)'")
if len(matches)>0:
video_urls.append( [ scrapertools.get_filename_from_url(media_url)[-4:]+" [upafile]",media_url])
for video_url in video_urls:
logger.info("[upafile.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[vidbux.py] url="+page_url)
if ".html" not in page_url:
logger.info("[vidbux.py] URL incompleta")
data = scrapertools.cache_page(page_url)
patron = '<input name="fname" type="hidden" value="([^"]+)">'
matches = re.compile(patron,re.DOTALL).findall(data)
page_url = page_url+"/"+matches[0]+".html"
# Lo pide una vez
scrapertools.cache_page( page_url , headers=[['User-Agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14']] )
# Lo pide una segunda vez, como si hubieras hecho click en el banner
patron = 'http\:\/\/www\.vidbux\.com/([^\/]+)/(.*?)\.html'
matches = re.compile(patron,re.DOTALL).findall(page_url)
logger.info("[vidbux.py] fragmentos de la URL")
scrapertools.printMatches(matches)
codigo = ""
nombre = ""
if len(matches)>0:
codigo = matches[0][0]
nombre = matches[0][1]
post = "op=download1&usr_login=&id="+codigo+"&fname="+nombre+"&referer=&method_free=Free+Stream"
data = scrapertools.cache_page( page_url , post=post, headers=[['User-Agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14'],['Referer',page_url]] )
# Extrae el trozo cifrado
patron = '<div id="embedcontmvshre"[^>]+>(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
data = ""
if len(matches)>0:
data = matches[0]
logger.info("[vidbux.py] bloque packed="+data)
else:
logger.info("[vidbux.py] no encuentra bloque packed="+data)
return ""
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
# Extrae la URL del vídeo
logger.info("descifrado="+descifrado)
# Extrae la URL
patron = '<param name="src"value="([^"]+)"/>'
matches = re.compile(patron,re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
video_urls = []
if len(matches)>0:
video_urls.append( ["[vidbux]",matches[0]])
for video_url in video_urls:
logger.info("[vidbux.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[nosvideo.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
# Lee la URL
data = scrapertools.cache_page(page_url)
bloque = scrapertools.get_match(data, '<Form method="POST"(.*)</.orm>')
#logger.info("bloque="+bloque)
op = scrapertools.get_match(
bloque, '<input type="hidden" name="op" value="([^"]+)"')
id = scrapertools.get_match(
bloque, '<input type="hidden" name="id" value="([^"]+)"')
rand = scrapertools.get_match(
bloque, '<input type="hidden" name="rand" value="([^"]*)"')
referer = scrapertools.get_match(
bloque, '<input type="hidden" name="referer" value="([^"]*)"')
usr_login = scrapertools.get_match(
bloque, '<input type="hidden" name="usr_login" value="([^"]*)"')
fname = scrapertools.get_match(
bloque, '<input type="hidden" name="fname" value="([^"]+)"')
method_free = scrapertools.get_match(
bloque, '<input type="[^"]+" name="method_free" value="([^"]*)"')
method_premium = scrapertools.get_match(
bloque, '<input type="[^"]+" name="method_premium" value="([^"]*)"')
# Simula el botón
#op=download1&id=iij5rw25kh4c&rand=&referer=&usr_login=&fname=TED-TS-Screener.Castellano.Ro_dri.avi&method_free=&method_premium=&down_script=1&method_free=Continue+to+Video
post = "op=" + op + "&id=" + id + "&rand=" + rand + "&referer=" + referer + "&usr_login="******"&fname=" + fname + "&method_free=&method_premium=" + method_premium + "&down_script=1&method_free=" + method_free
data = scrapertools.cache_page(page_url, post=post)
#logger.info("data="+data)
# Saca el bloque packed y lo descifra
packed = scrapertools.get_match(
data,
"(<script type='text/javascript'>eval\(function\(p,a,c,k,e,d\).*?</script>)"
)
from core import unpackerjs
unpacked = unpackerjs.unpackjs(packed)
logger.info("unpacked=" + unpacked)
# Extrae el descriptor
playlist = scrapertools.get_match(unpacked, "playlist\=(.*?\.xml)")
data = scrapertools.cache_page(playlist)
location = scrapertools.get_match(data, "<file>([^<]+)</file>")
video_urls.append([
scrapertools.get_filename_from_url(location)[-4:] + " [nosvideo]",
location
])
for video_url in video_urls:
logger.info("[nosvideo.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[vidxden.py] url="+page_url)
# Lo pide una vez
headers = []
headers.append(['User-Agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14'])
data = scrapertools.cache_page( page_url , headers=headers )
fname = scrapertools.get_match(data,'<input name="fname" type="hidden" value="([^"]+)">')
codigo = scrapertools.get_match(page_url,'vidxden.com/(\w+)')
# Lo pide una segunda vez, como si hubieras hecho click en el banner
#op=download1&usr_login=&id=qtrv0ufkz3e4&fname=El_cazador_de_sue_os-dvd.avi&referer=&method_free=Continue+to+Video
headers.append(['Referer',page_url])
post = "op=download1&usr_login=&id="+codigo+"&fname="+fname+"&referer=&method_free=Continue+to+Video"
data = scrapertools.cache_page( page_url , post=post, headers=headers )
logger.info("data="+data)
# Extrae el trozo cifrado
#<div id="embedcontmvshre" style="position: absolute; top: 0; left: 0; visibility: hidden;"><script type='text/javascript'>eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('1i.1h(\'<8 10="1g"1f="1e:1d-1c-1b-1a-19"q="p"o="n"18="3://b.7.4/a/17.16"><2 1="u"0="t"/><2 1="s"0="r"/><2 1="m"0="3://i/l/6.k"/><2 1="f"0="5"><2 1="g"0="5"/><2 1="e"0="c"/><2 1="j"0="h"/><2 1="z"0="3://y.x.4:w/d/v/6"/><9 10="15"14="13/7"z="3://y.x.4:w/d/v/6"u="t"s="r"q="p"o="n"m="3://i/l/6.k"j="h"g="5"f="5"e="c"12="3://b.7.4/a/11/"></9></8>\');',36,55,'value|name|param|http|com|false|qtrv0ufkz3e4|divx|object|embed|plugin|go|Play||previewMessage|allowContextMenu|bannerEnabled|true||autoPlay|jpg|00249|previewImage|318|height|640|width|transparent|wmode|Stage6|custommode|opujxvaorizu2mdg6fst2fjdzlrn4p437h3lsbz5fjkxs|364|divxden|s31|src|id|download|pluginspage|video|type|np_vid|cab|DivXBrowserPlugin|codebase|CC0F21721616|9C46|41fa|D0AB|67DABFBF|clsid|classid|ie_vid|write|document'.split('|')))</script></div>
patron = "(<script type='text/javascript'>eval\(function.*?</script>)"
matches = re.compile(patron,re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
data = ""
if len(matches)>0:
data = matches[0]
logger.info("[vidxden.py] bloque packed="+data)
else:
logger.info("[vidxden.py] no encuentra bloque packed="+data)
return ""
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
# Extrae la URL del vídeo
logger.info("descifrado="+descifrado)
# Extrae la URL
patron = '<param name="src"value="([^"]+)"/>'
matches = re.compile(patron,re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
if len(matches)==0:
descifrado = descifrado.replace("\\","")
patron = "file','([^']+)'"
matches = re.compile(patron,re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
video_urls = []
if len(matches)>0:
video_urls.append( ["[vidxden]",matches[0]+"|Referer="+urllib.quote(page_url)+"&User-Agent="+urllib.quote('Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14')])
for video_url in video_urls:
logger.info("[vidxden.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[meuvideos.py] url="+page_url)
if not "embed" in page_url:
page_url = page_url.replace("http://meuvideos.com/","http://meuvideos.com/embed-") + ".html"
data = scrapertools.cache_page(page_url)
data = "eval" + scrapertools.find_single_match(data,"<script type='text/javascript'>eval(.*?)</script>")
data = unpackerjs.unpackjs(data)
url = scrapertools.get_match(data, 'file:"([^"]+)"')
video_urls = []
video_urls.append( [ scrapertools.get_filename_from_url(url)[-4:]+" [meuvideos]",url])
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[vidbull.py] url=" + page_url)
data = scrapertools.cache_page(
page_url,
headers=[[
'User-Agent',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14'
]])
logger.info("data=" + data)
# Extrae el trozo cifrado
'''
<script type='text/javascript'>eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('2j 2=2i 2h(\'6://8.5/b/b.2g\',\'b\',\'2f\',\'2e\',\'9\');2.g(\'2d\',\'k\');2.g(\'2c\',\'2b\');2.g(\'2a\',\'29\');2.4(\'28\',\'../b/27.26\');2.4(\'25\',\'24\');2.4(\'l\',\'6://n.8.5:23/d/21/20.1z\');2.4(\'1y\',\'6://n.8.5/i/1x/e.1w\');2.4(\'1v\',\'6\');2.4(\'1u.j\',\'1t\');2.4(\'1s\',\'1r\');2.4(\'1q\',\'f-3\');2.4(\'f.h\',\'6://8.5/e\');2.4(\'f.1p\',\'%1o%1n%1m%1l%1k%1j%1i.5%1h-e-1g.1f%22%1e%c%1d%c%1c%c%1b%1a%19%18%17%16%m%14%13%m\');2.4(\'a.l\',\'6://8.5/12/11.10\');2.4(\'a.z\',\'k\');2.4(\'a.y\',\'15\');2.4(\'a.x\',\'1\');2.4(\'a.w\',\'0.7\');2.4(\'a.j\',\'v-u\');2.4(\'a.h\',\'6://8.5\');2.4(\'t\',\'s r\');2.4(\'q\',\'6://8.5\');2.p(\'o\');',36,92,'||s1||addVariable|com|http||vidbull||logo|player|3D0||erk3r6bpfyxy|sharing|addParam|link||position|true|file|3E|fs11|flvplayer|write|aboutlink|dlf|VidBull|abouttext|right|top|out|over|timeout|hide|png|vidbull_playerlogo|images|2FIFRAME|3C||3D338|20HEIGHT|3D640|20WIDTH|3DNO|20SCROLLING|20MARGINHEIGHT|20MARGINWIDTH|20FRAMEBORDER|html|640x318|2Fembed|2Fvidbull|2F|3A|22http|3D|20SRC|3CIFRAME|code|plugins|uniform|stretching|left|dock|provider|jpg|00031|image|flv|video|45sbu63kljrwuxim7e6xp2koxj4sxpaxyivgkrzwu27ggj5rdrrayurf||182|2606|duration|zip|modieus1|skin|opaque|wmode|always|allowscriptaccess|allowfullscreen|318|640|swf|SWFObject|new|var'.split('|')))
'''
patron = "<script type='text/javascript'>(eval\(function\(p,a,c,k,e,d\).*?)</script>"
matches = re.compile(patron, re.DOTALL).findall(data)
cifrado = ""
for match in matches:
logger.info("match=" + match)
if "mp4" in match or "flv" in match or "video" in match:
cifrado = match
break
# Extrae la URL del vídeo
logger.info("cifrado=" + cifrado)
descifrado = unpackerjs.unpackjs(cifrado)
descifrado = descifrado.replace("\\", "")
logger.info("descifrado=" + descifrado)
# Extrae la URL
media_url = scrapertools.get_match(descifrado,
"addVariable\('file','([^']+)'")
video_urls = []
if len(matches) > 0:
video_urls.append([
scrapertools.get_filename_from_url(media_url)[-4:] + " [vidbull]",
media_url
])
for video_url in video_urls:
logger.info("[vidbull.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[ovfile.py] url=" + page_url)
if page_url.startswith('http'):
page_url = extract_id(page_url)
if page_url == "": return []
page_url = 'http://ovfile.com/embed-' + page_url + '-600x340.html'
# Lo pide una vez
data = scrapertools.cache_page(page_url)
# Extrae el trozo cifrado
patron = "src='http://ovfile.com/player/swfobject.js'></script>[^<]+"
patron += "<script type='text/javascript'>(.*?)</script>"
matches = re.compile(patron, re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
data = ""
if len(matches) > 0:
data = matches[0]
logger.info("[ovfile.py] bloque packed=" + data)
else:
logger.info("[ovfile.py] no encuentra bloque packed=" + data)
return ""
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
descifrado = descifrado.replace("\\'", "'")
# Extrae la URL del vídeo
logger.info("descifrado=" + descifrado)
# Extrae la URL
patron = "'file','([^']+)'"
matches = re.compile(patron, re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
video_urls = []
if len(matches) > 0:
url = "%s?file=%s" % (matches[0], matches[0])
video_urls.append(
["." + matches[0].rsplit('.', 1)[1] + " [ovfile]", url])
for video_url in video_urls:
logger.info("[ovfile.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[allbox4.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
# Descarga
data = scrapertools.cache_page(page_url)
try:
paramstext = scrapertools.get_match(
data, '<param name="flashvars" value="([^"]+)"')
params = paramstext.split("&")
file = ""
token = ""
start = ""
for param in params:
if param.startswith("file="):
file = param[5:]
if param.startswith("token="):
token = param[6:]
if param.startswith("start="):
start = param[6:]
media_url = file + "?" + start + "&" + token
except:
packed = scrapertools.get_match(
data,
"<div id=\"player_coded\">(<script type='text/javascript'>eval\(function\(p,a,c,k,e,d.*?</script>)</div>"
)
from core import unpackerjs
unpacked = unpackerjs.unpackjs(packed)
logger.info("unpacked=" + unpacked)
media_url = scrapertools.get_match(
unpacked, '<embed id="np_vid"type="video/divx"src="([^"]+)"')
video_urls = []
video_urls.append([
scrapertools.get_filename_from_url(media_url)[-4:] + " [allbox4]",
media_url
])
for video_url in video_urls:
logger.info("[allbox4.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[ovfile.py] url="+page_url)
if page_url.startswith('http'):
page_url = extract_id(page_url)
if page_url=="":return []
page_url = 'http://ovfile.com/embed-'+page_url+'-600x340.html'
# Lo pide una vez
data = scrapertools.cache_page( page_url)
# Extrae el trozo cifrado
patron = "src='http://ovfile.com/player/swfobject.js'></script>[^<]+"
patron +="<script type='text/javascript'>(.*?)</script>"
matches = re.compile(patron,re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
data = ""
if len(matches)>0:
data = matches[0]
logger.info("[ovfile.py] bloque packed="+data)
else:
logger.info("[ovfile.py] no encuentra bloque packed="+data)
return ""
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
descifrado = descifrado.replace("\\'","'")
# Extrae la URL del vídeo
logger.info("descifrado="+descifrado)
# Extrae la URL
patron = "'file','([^']+)'"
matches = re.compile(patron,re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
video_urls = []
if len(matches)>0:
url = "%s?file=%s" %(matches[0],matches[0])
video_urls.append( ["."+matches[0].rsplit('.',1)[1]+" [ovfile]",url])
for video_url in video_urls:
logger.info("[ovfile.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url(page_url, premium=False, user="", password="", video_password=""):
logger.info("videostoring get_video_url(page_url='%s')" % page_url)
if not "embed" in page_url:
page_url = page_url.replace("http://www.videostoring.com/", "http://www.videostoring.com/embed-") + ".html"
data = scrapertools.cache_page(page_url)
data = scrapertools.find_single_match(data, "<script type='text/javascript'>(.*?)</script>")
data = unpackerjs.unpackjs(data)
url = scrapertools.get_match(data, '<param name="src"value="([^"]+)"/>')
video_urls = []
video_urls.append([scrapertools.get_filename_from_url(url)[-4:] + " [videostoring]", url])
for video_url in video_urls:
logger.info("[videostoring.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[meuvideos.py] url=" + page_url)
if not "embed" in page_url:
page_url = page_url.replace("http://meuvideos.com/",
"http://meuvideos.com/embed-") + ".html"
data = scrapertools.cache_page(page_url)
data = "eval" + scrapertools.find_single_match(
data, "<script type='text/javascript'>eval(.*?)</script>")
data = unpackerjs.unpackjs(data)
url = scrapertools.get_match(data, 'file:"([^"]+)"')
video_urls = []
video_urls.append(
[scrapertools.get_filename_from_url(url)[-4:] + " [meuvideos]", url])
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[nosvideo.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
# Lee la URL
data = scrapertools.cache_page( page_url )
bloque = scrapertools.get_match(data,'<Form method="POST"(.*)</.orm>')
#logger.info("bloque="+bloque)
op = scrapertools.get_match(bloque,'<input type="hidden" name="op" value="([^"]+)"')
id = scrapertools.get_match(bloque,'<input type="hidden" name="id" value="([^"]+)"')
rand = scrapertools.get_match(bloque,'<input type="hidden" name="rand" value="([^"]*)"')
referer = scrapertools.get_match(bloque,'<input type="hidden" name="referer" value="([^"]*)"')
usr_login = scrapertools.get_match(bloque,'<input type="hidden" name="usr_login" value="([^"]*)"')
fname = scrapertools.get_match(bloque,'<input type="hidden" name="fname" value="([^"]+)"')
method_free = scrapertools.get_match(bloque,'<input type="[^"]+" name="method_free" value="([^"]*)"')
method_premium = scrapertools.get_match(bloque,'<input type="[^"]+" name="method_premium" value="([^"]*)"')
# Simula el botón
#op=download1&id=iij5rw25kh4c&rand=&referer=&usr_login=&fname=TED-TS-Screener.Castellano.Ro_dri.avi&method_free=&method_premium=&down_script=1&method_free=Continue+to+Video
post = "op="+op+"&id="+id+"&rand="+rand+"&referer="+referer+"&usr_login="******"&fname="+fname+"&method_free=&method_premium="+method_premium+"&down_script=1&method_free="+method_free
data = scrapertools.cache_page( page_url , post=post )
#logger.info("data="+data)
# Saca el bloque packed y lo descifra
packed = scrapertools.get_match(data,"(<script type='text/javascript'>eval\(function\(p,a,c,k,e,d\).*?</script>)")
from core import unpackerjs
unpacked = unpackerjs.unpackjs(packed)
logger.info("unpacked="+unpacked)
# Extrae el descriptor
playlist = scrapertools.get_match(unpacked,"playlist\=(.*?\.xml)")
data = scrapertools.cache_page( playlist )
location = scrapertools.get_match(data,"<file>([^<]+)</file>")
video_urls.append( [ scrapertools.get_filename_from_url(location)[-4:] + " [nosvideo]",location ] )
for video_url in video_urls:
logger.info("[nosvideo.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[allbox4.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
# Descarga
data = scrapertools.cache_page( page_url )
try:
paramstext = scrapertools.get_match( data , '<param name="flashvars" value="([^"]+)"')
params = paramstext.split("&")
file=""
token=""
start=""
for param in params:
if param.startswith("file="):
file=param[5:]
if param.startswith("token="):
token=param[6:]
if param.startswith("start="):
start=param[6:]
media_url = file+"?"+start+"&"+token
except:
packed = scrapertools.get_match(data,"<div id=\"player_coded\">(<script type='text/javascript'>eval\(function\(p,a,c,k,e,d.*?</script>)</div>")
from core import unpackerjs
unpacked = unpackerjs.unpackjs(packed)
logger.info("unpacked="+unpacked)
media_url = scrapertools.get_match(unpacked,'<embed id="np_vid"type="video/divx"src="([^"]+)"')
video_urls = []
video_urls.append( [ scrapertools.get_filename_from_url(media_url)[-4:] + " [allbox4]",media_url ] )
for video_url in video_urls:
logger.info("[allbox4.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[vidbull.py] url="+page_url)
data = scrapertools.cache_page( page_url , headers=[['User-Agent','Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14']] )
logger.info("data="+data)
# Extrae el trozo cifrado
'''
<script type='text/javascript'>eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('2j 2=2i 2h(\'6://8.5/b/b.2g\',\'b\',\'2f\',\'2e\',\'9\');2.g(\'2d\',\'k\');2.g(\'2c\',\'2b\');2.g(\'2a\',\'29\');2.4(\'28\',\'../b/27.26\');2.4(\'25\',\'24\');2.4(\'l\',\'6://n.8.5:23/d/21/20.1z\');2.4(\'1y\',\'6://n.8.5/i/1x/e.1w\');2.4(\'1v\',\'6\');2.4(\'1u.j\',\'1t\');2.4(\'1s\',\'1r\');2.4(\'1q\',\'f-3\');2.4(\'f.h\',\'6://8.5/e\');2.4(\'f.1p\',\'%1o%1n%1m%1l%1k%1j%1i.5%1h-e-1g.1f%22%1e%c%1d%c%1c%c%1b%1a%19%18%17%16%m%14%13%m\');2.4(\'a.l\',\'6://8.5/12/11.10\');2.4(\'a.z\',\'k\');2.4(\'a.y\',\'15\');2.4(\'a.x\',\'1\');2.4(\'a.w\',\'0.7\');2.4(\'a.j\',\'v-u\');2.4(\'a.h\',\'6://8.5\');2.4(\'t\',\'s r\');2.4(\'q\',\'6://8.5\');2.p(\'o\');',36,92,'||s1||addVariable|com|http||vidbull||logo|player|3D0||erk3r6bpfyxy|sharing|addParam|link||position|true|file|3E|fs11|flvplayer|write|aboutlink|dlf|VidBull|abouttext|right|top|out|over|timeout|hide|png|vidbull_playerlogo|images|2FIFRAME|3C||3D338|20HEIGHT|3D640|20WIDTH|3DNO|20SCROLLING|20MARGINHEIGHT|20MARGINWIDTH|20FRAMEBORDER|html|640x318|2Fembed|2Fvidbull|2F|3A|22http|3D|20SRC|3CIFRAME|code|plugins|uniform|stretching|left|dock|provider|jpg|00031|image|flv|video|45sbu63kljrwuxim7e6xp2koxj4sxpaxyivgkrzwu27ggj5rdrrayurf||182|2606|duration|zip|modieus1|skin|opaque|wmode|always|allowscriptaccess|allowfullscreen|318|640|swf|SWFObject|new|var'.split('|')))
'''
patron = "<script type='text/javascript'>(eval\(function\(p,a,c,k,e,d\).*?)</script>"
matches = re.compile(patron,re.DOTALL).findall(data)
cifrado=""
for match in matches:
logger.info("match="+match)
if "mp4" in match or "flv" in match or "video" in match:
cifrado = match
break
# Extrae la URL del vídeo
logger.info("cifrado="+cifrado)
descifrado = unpackerjs.unpackjs(cifrado)
descifrado = descifrado.replace("\\","")
logger.info("descifrado="+descifrado)
# Extrae la URL
media_url = scrapertools.get_match(descifrado,"addVariable\('file','([^']+)'")
video_urls = []
if len(matches)>0:
video_urls.append( [ scrapertools.get_filename_from_url(media_url)[-4:]+" [vidbull]",media_url])
for video_url in video_urls:
logger.info("[vidbull.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("pelisalacarta.gamovideo get_video_url(page_url='%s')" % page_url)
if not "embed" in page_url:
page_url = page_url.replace("http://gamovideo.com/","http://gamovideo.com/embed-") + "-640x360.html"
data = scrapertools.cache_page(page_url)
data = scrapertools.find_single_match(data,"<script type='text/javascript'>(.*?)</script>")
data = unpackerjs.unpackjs(data)
host = scrapertools.get_match(data, 'image:"(http://[^/]+/)')
flv_url = scrapertools.get_match(data, ',\{file:"([^"]+)"')
rtmp_url = scrapertools.get_match(data, '\[\{file:"([^"]+)"')
flv = host+flv_url.split("=")[1]+"/v.flv"
video_urls = []
video_urls.append([scrapertools.get_filename_from_url(flv)[-4:]+" [gamovideo]",flv])
#video_urls.append(["RTMP [gamovideo]",rtmp_url])
for video_url in video_urls:
logger.info("[gamovideo.py] %s - %s" % (video_url[0],video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("pelisalacarta.gamovideo get_video_url(page_url='%s')" %
page_url)
# Lo pide una vez
headers = [[
'User-Agent',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14'
]]
data = scrapertools.cache_page(page_url, headers=headers)
#logger.info("data="+data)
try:
'''
<input type="hidden" name="op" value="download1">
<input type="hidden" name="usr_login" value="">
<input type="hidden" name="id" value="auoxxtvyquoy">
<input type="hidden" name="fname" value="Star.Trek.Into.Darkness.2013.HD.m720p.LAT.avi">
<input type="hidden" name="referer" value="">
<input type="hidden" name="hash" value="1624-83-46-1377796069-b5e6b8f9759d080a3667adad637f00ac">
<input type="submit" name="imhuman" value="Continue to Video" id="btn_download">
'''
op = scrapertools.get_match(
data, '<input type="hidden" name="op" value="(down[^"]+)"')
usr_login = ""
id = scrapertools.get_match(
data, '<input type="hidden" name="id" value="([^"]+)"')
fname = scrapertools.get_match(
data, '<input type="hidden" name="fname" value="([^"]+)"')
referer = scrapertools.get_match(
data, '<input type="hidden" name="referer"\s+value="([^"]*)"')
hashvalue = scrapertools.get_match(
data, '<input type="hidden" name="hash" value="([^"]*)"')
submitbutton = scrapertools.get_match(
data,
'<input type="submit" name="imhuman" value="([^"]+)"').replace(
" ", "+")
import time
time.sleep(5)
# Lo pide una segunda vez, como si hubieras hecho click en el banner
#op=download1&usr_login=&id=auoxxtvyquoy&fname=Star.Trek.Into.Darkness.2013.HD.m720p.LAT.avi&referer=&hash=1624-83-46-1377796019-c2b422f91da55d12737567a14ea3dffe&imhuman=Continue+to+Video
#op=search&usr_login=&id=auoxxtvyquoy&fname=Star.Trek.Into.Darkness.2013.HD.m720p.LAT.avi&referer=&hash=1624-83-46-1377796398-8020e5629f50ff2d7b7de99b55bdb177&imhuman=Continue+to+Video
post = "op=" + op + "&usr_login="******"&id=" + id + "&fname=" + fname + "&referer=" + referer + "&hash=" + hashvalue + "&imhuman=" + submitbutton
headers.append(["Referer", page_url])
data = scrapertools.cache_page(page_url, post=post, headers=headers)
#logger.info("data="+data)
except:
import traceback
traceback.print_exc()
# Extrae la URL
logger.info("data=" + data)
data = scrapertools.find_single_match(
data, "<script type='text/javascript'>(.*?)</script>")
logger.info("data=" + data)
data = unpackerjs.unpackjs(data)
logger.info("data=" + data)
pfile = scrapertools.get_match(data, 'file\s*\:\s*"([^"]+)"')
pstreamer = scrapertools.get_match(data, 'streamer\s*\:\s*"([^"]+)"')
media_url = pstreamer + " playpath=" + pfile
video_urls = []
video_urls.append(["RTMP [gamovideo]", media_url])
for video_url in video_urls:
logger.info("[gamovideo.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def geturl(urlvideo):
logger.info("[metadivx.py] url="+urlvideo)
# ---------------------------------------
# Inicializa la libreria de las cookies
# ---------------------------------------
ficherocookies = COOKIEFILE
try:
os.remove(ficherocookies)
except:
pass
# the path and filename to save your cookies in
cj = None
ClientCookie = None
cookielib = None
# Let's see if cookielib is available
try:
import cookielib
except ImportError:
# If importing cookielib fails
# let's try ClientCookie
try:
import ClientCookie
except ImportError:
# ClientCookie isn't available either
urlopen = urllib2.urlopen
Request = urllib2.Request
else:
# imported ClientCookie
urlopen = ClientCookie.urlopen
Request = ClientCookie.Request
cj = ClientCookie.LWPCookieJar()
else:
# importing cookielib worked
urlopen = urllib2.urlopen
Request = urllib2.Request
cj = cookielib.LWPCookieJar()
# This is a subclass of FileCookieJar
# that has useful load and save methods
# ---------------------------------
# Instala las cookies
# ---------------------------------
if cj is not None:
# we successfully imported
# one of the two cookie handling modules
if os.path.isfile(ficherocookies):
# if we have a cookie file already saved
# then load the cookies into the Cookie Jar
cj.load(ficherocookies)
# Now we need to get our Cookie Jar
# installed in the opener;
# for fetching URLs
if cookielib is not None:
# if we use cookielib
# then we get the HTTPCookieProcessor
# and install the opener in urllib2
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
else:
# if we use ClientCookie
# then we get the HTTPCookieProcessor
# and install the opener in ClientCookie
opener = ClientCookie.build_opener(ClientCookie.HTTPCookieProcessor(cj))
ClientCookie.install_opener(opener)
#print "-------------------------------------------------------"
url=urlvideo
#print url
#print "-------------------------------------------------------"
theurl = url
# an example url that sets a cookie,
# try different urls here and see the cookie collection you can make !
txdata = None
# if we were making a POST type request,
# we could encode a dictionary of values here,
# using urllib.urlencode(somedict)
txheaders = {'User-Agent':'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)'}
# fake a user agent, some websites (like google) don't like automated exploration
req = Request(theurl, txdata, txheaders)
handle = urlopen(req)
cj.save(ficherocookies) # save the cookies again
data=handle.read()
handle.close()
#print data
# Lo pide una segunda vez, como si hubieras hecho click en el banner
patron = 'http\:\/\/www\.metadivx\.com/([^\/]+)/(.*?)\.html'
matches = re.compile(patron,re.DOTALL).findall(url)
logger.info("[metadivx.py] fragmentos de la URL")
scrapertools.printMatches(matches)
codigo = ""
nombre = ""
if len(matches)>0:
codigo = matches[0][0]
nombre = matches[0][1]
txdata = "op=download1&usr_login=&id="+codigo+"&fname="+nombre+"&referer=&method_free=Continue"
logger.info(txdata)
req = Request(theurl, txdata, txheaders)
handle = urlopen(req)
cj.save(ficherocookies) # save the cookies again
data=handle.read()
handle.close()
#print data
patron = '<div id="embedcontmvshre[^>]+>(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
scrapertools.printMatches(matches)
logger.info("[metadivx.py] bloque packed")
if len(matches)>0:
logger.info(matches[0])
'''
<center>
<script type='text/javascript'>eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('1e.1d(\'<7 w="1c"1b="1a:19-18-17-16-15"h="g"f="e"14="4://a.6.3/9/13.12"><2 1="j"0="i"><2 1="v"0="u"><2 1="b"0="5"/><2 1="c"0="5"/><2 1="t"0="4://s.r.q.p:o/d/n/m.3.-l.k"/><8 w="11"v="u"10="z/6"t="4://s.r.q.p:o/d/n/m.3.-l.k"j="i"h="g"f="e"c="5"b="5"y="4://a.6.3/9/x/"></8></7>\');',36,51,'value|name|param|com|http|false|divx|object|embed|plugin|go|bannerEnabled|autoPlay||320px|height|630px|width|none|custommode|avi|El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_|Capitancinema|pfq3vaf2xypwtrv77uw334hb55ctx5tcd6dva|182|206|45|73|76|src|auto|bufferingMode|id|download|pluginspage|video|type|embedmvshre|cab|DivXBrowserPlugin|codebase|CC0F21721616|9C46|41fa|D0AB|67DABFBF|clsid|classid|embedcontmvshre|write|document'.split('|')))
</script>
</center>
'''
# El javascript empaquetado es
#eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('1e.1d(\'<7 w="1c"1b="1a:19-18-17-16-15"h="g"f="e"14="4://a.6.3/9/13.12"><2 1="j"0="i"><2 1="v"0="u"><2 1="b"0="5"/><2 1="c"0="5"/><2 1="t"0="4://s.r.q.p:o/d/n/m.3.-l.k"/><8 w="11"v="u"10="z/6"t="4://s.r.q.p:o/d/n/m.3.-l.k"j="i"h="g"f="e"c="5"b="5"y="4://a.6.3/9/x/"></8></7>\');',36,51,'value|name|param|com|http|false|divx|object|embed|plugin|go|bannerEnabled|autoPlay||320px|height|630px|width|none|custommode|avi|El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_|Capitancinema|pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa|182|206|45|73|76|src|auto|bufferingMode|id|download|pluginspage|video|type|embedmvshre|cab|DivXBrowserPlugin|codebase|CC0F21721616|9C46|41fa|D0AB|67DABFBF|clsid|classid|embedcontmvshre|write|document'.split('|')))
'''
eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('1e.1d(\'
<7 w="1c"1b="1a:19-18-17-16-15"h="g"f="e"14="4://a.6.3/9/13.12">
<2 1="j"0="i">
<2 1="v"0="u">
<2 1="b"0="5"/>
<2 1="c"0="5"/>
<2 1="t"0="4://s.r.q.p:o/d/n/m.3.-l.k"/>
<8 w="11"v="u"10="z/6"t="4://s.r.q.p:o/d/n/m.3.-l.k"j="i"h="g"f="e"c="5"b="5"y="4://a.6.3/9/x/">
<embed id="embedmvshre"bufferingMode="auto"type="video/divx"src="http://76.73.45.206:182/d/pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa/Capitancinema.com.-El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_.avi"custommode="none"width="630px"height="320px"autoPlay="false"bannerEnabled="false"pluginspage="http://go.divx.com/plugin/download/">
</8>
</7>\');',36,51,
0'value
1|name
2|param
3|com
4|http
5|false
6|divx
7|object
8|embed
9|plugin
a|go
b|bannerEnabled
c|autoPlay
d|
e|320px
f|height
g|630px
h|width
i|none
j|custommode
k|avi
l|El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_
m|Capitancinema
n|pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa
o|182
p|206
q|45
r|73
s|76
t|src
u|auto
v|bufferingMode
w|id
x|download
y|pluginspage
z|video
10|type
11|embedmvshre
12|cab
13|DivXBrowserPlugin
14|codebase
15|CC0F21721616
16|9C46
17|41fa
18|D0AB
19|67DABFBF
1a|clsid
1b|classid
1c|embedcontmvshre
1d|write
1e|document
'.split('
|')))
'''
# El javascript desempaquetado es
#document.write('<object id="embedcontmvshre"classid="clsid:67DABFBF-D0AB-41fa-9C46-CC0F21721616"width="630px"height="320px"codebase="http://go.divx.com/plugin/DivXBrowserPlugin.cab"><param name="custommode"value="none"><param name="bufferingMode"value="auto"><param name="bannerEnabled"value="false"/><param name="autoPlay"value="false"/><param name="src"value="http://76.73.45.206:182/d/pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa/Capitancinema.com.-El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_.avi"/><embed id="embedmvshre"bufferingMode="auto"type="video/divx"src="http://76.73.45.206:182/d/pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa/Capitancinema.com.-El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_.avi"custommode="none"width="630px"height="320px"autoPlay="false"bannerEnabled="false"pluginspage="http://go.divx.com/plugin/download/"></embed></object>');
'''
<object id="embedcontmvshre"classid="clsid:67DABFBF-D0AB-41fa-9C46-CC0F21721616"width="630px"height="320px"codebase="http://go.divx.com/plugin/DivXBrowserPlugin.cab">
<param name="custommode"value="none">
<param name="bufferingMode"value="auto">
<param name="bannerEnabled"value="false"/>
<param name="autoPlay"value="false"/>
<param name="src"value="http://76.73.45.206:182/d/pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa/Capitancinema.com.-El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_.avi"/>
<embed id="embedmvshre"bufferingMode="auto"type="video/divx"src="http://76.73.45.206:182/d/pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa/Capitancinema.com.-El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_.avi"custommode="none"width="630px"height="320px"autoPlay="false"bannerEnabled="false"pluginspage="http://go.divx.com/plugin/download/">
</embed>
</object>');
'''
# La URL del video es
#http://76.73.45.206:182/d/pfq3vaf2xypwtrv77uw334hb55ctx5qa5wdfa/Capitancinema.com.-El_Concierto__BrSc__Spanish_HOMIEZTEAM__2010_.avi
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
logger.info("descifrado="+descifrado)
# Extrae la URL
patron = '<param name="src"value="([^"]+)"/>'
matches = re.compile(patron,re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
url = ""
if len(matches)>0:
url = matches[0]
logger.info("[metadivx.py] url="+url)
return url
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[videopremium.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
# Lee la URL
data = scrapertools.cache_page(page_url)
logger.info("data=" + data)
bloque = scrapertools.get_match(data, '<Form[^>]*method="POST"(.*)</.orm>')
logger.info("bloque=" + bloque)
op = scrapertools.get_match(
bloque, '<input type="hidden" name="op" value="([^"]+)"')
usr_login = scrapertools.get_match(
bloque, '<input type="hidden" name="usr_login" value="([^"]*)"')
id = scrapertools.get_match(
bloque, '<input type="hidden" name="id" value="([^"]+)"')
fname = scrapertools.get_match(
bloque, '<input type="hidden" name="fname" value="([^"]+)"')
referer = scrapertools.get_match(
bloque, '<input type="hidden" name="referer" value="([^"]*)"')
method_free = scrapertools.get_match(
bloque, '<input type="[^"]+" name="method_free" value="([^"]+)"')
# Simula el botón
#op=download1&usr_login=&id=buq4b8zunbm6&fname=Snow.Buddies-Avventura.In.Alaska.2008.iTALiAN.AC3.DVDRip.H264-PsYcOcReW.avi&referer=&method_free=Watch+Free%21
post = "op=" + op + "&usr_login="******"&id=" + id + "&fname=" + fname + "&referer=" + referer + "&method_free=" + method_free
data = scrapertools.cache_page(page_url, post=post)
#logger.info("data="+data)
try:
packed = scrapertools.get_match(
data,
"(<script type='text/javascript'>eval\(function\(p,a,c,k,e,d\).*?</script>)"
)
except:
packed = scrapertools.get_match(
data, "(function\(p, a, c, k, e, d\).*?</script>)")
packed = "<script type='text/javascript'>eval(" + packed
logger.info("packed=" + packed)
from core import unpackerjs
unpacked = unpackerjs.unpackjs(packed)
logger.info("unpacked=" + unpacked)
'''
23:47:40 T:2955980800 NOTICE: unpacked=('var vast=\'\';var flashvars={"comment":"VideoPremium.NET","st":"http://videopremium.net/uplayer/styles/video156-623.txt",
"file":"rtmp://tengig0.lb.videopremium.net/play/mp4:8x0mq9hanl3a.f4v",
p2pkey:"mp4:8x0mq9hanl3a.f4v",vast_preroll:vast};var params={bgcolor:"#ffffff",allowFullScreen:"true",allowScriptAccess:"always",id:"vplayer"};new swfobject.embedSWF("http://videopremium.net/uplayer/uppod.swf","vplayer","728","450","9.0.115.0",false,flashvars,params);',,paramsflashvars,
'''
'''
Property 'app' String 'play'
Property 'swfUrl' String 'http://videopremium.net/uplayer/uppod.swf'
Property 'pageUrl' String 'http://videopremium.net/8x0mq9hanl3a'
Property 'tcUrl' String 'rtmp://e5.videopremium.net/play'
play: String 'mp4:8x0mq9hanl3a.f4v'
'''
'''
00:55:30 T:2955980800 ERROR: Valid RTMP options are:
00:55:30 T:2955980800 ERROR: socks string Use the specified SOCKS proxy
00:55:30 T:2955980800 ERROR: app string Name of target app on server
00:55:30 T:2955980800 ERROR: tcUrl string URL to played stream
00:55:30 T:2955980800 ERROR: pageUrl string URL of played media's web page
00:55:30 T:2955980800 ERROR: swfUrl string URL to player SWF file
00:55:30 T:2955980800 ERROR: flashver string Flash version string (default MAC 10,0,32,18)
00:55:30 T:2955980800 ERROR: conn AMF Append arbitrary AMF data to Connect message
00:55:30 T:2955980800 ERROR: playpath string Path to target media on server
00:55:30 T:2955980800 ERROR: playlist boolean Set playlist before play command
00:55:30 T:2955980800 ERROR: live boolean Stream is live, no seeking possible
00:55:30 T:2955980800 ERROR: subscribe string Stream to subscribe to
00:55:30 T:2955980800 ERROR: jtv string Justin.tv authentication token
00:55:30 T:2955980800 ERROR: weeb string Weeb.tv authentication token
00:55:30 T:2955980800 ERROR: token string Key for SecureToken response
00:55:30 T:2955980800 ERROR: swfVfy boolean Perform SWF Verification
00:55:30 T:2955980800 ERROR: swfAge integer Number of days to use cached SWF hash
00:55:30 T:2955980800 ERROR: swfsize integer Size of the decompressed SWF file
00:55:30 T:2955980800 ERROR: swfhash string SHA256 hash of the decompressed SWF file
00:55:30 T:2955980800 ERROR: start integer Stream start position in milliseconds
00:55:30 T:2955980800 ERROR: stop integer Stream stop position in milliseconds
00:55:30 T:2955980800 ERROR: buffer integer Buffer time in milliseconds
00:55:30 T:2955980800 ERROR: timeout integer Session timeout in seconds
'''
rtmpurl = scrapertools.get_match(unpacked, '"file"\:"([^"]+)"').replace(
"tengig0.lb.videopremium.net", "e4.videopremium.net")
playpath = scrapertools.get_match(unpacked, 'p2pkey\:"([^"]+)"')
swfurl = scrapertools.get_match(unpacked, 'embedSWF\("([^"]+)"')
pageurl = page_url
app = "play"
tcurl = "rtmp://e4.videopremium.net/play"
location = rtmpurl + " playpath=" + playpath + " swfurl=" + swfurl + " pageUrl=" + page_url + " tcurl=" + tcurl + " app=" + app #swfvfy=true
logger.info("location=" + location)
video_urls.append(["RTMP [videopremium]", location])
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[vidxden.py] url=" + page_url)
# Lo pide una vez
headers = []
headers.append([
'User-Agent',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14'
])
data = scrapertools.cache_page(page_url, headers=headers)
fname = scrapertools.get_match(
data, '<input name="fname" type="hidden" value="([^"]+)">')
codigo = scrapertools.get_match(page_url, 'vidxden.com/(\w+)')
# Lo pide una segunda vez, como si hubieras hecho click en el banner
#op=download1&usr_login=&id=qtrv0ufkz3e4&fname=El_cazador_de_sue_os-dvd.avi&referer=&method_free=Continue+to+Video
headers.append(['Referer', page_url])
post = "op=download1&usr_login=&id=" + codigo + "&fname=" + fname + "&referer=&method_free=Continue+to+Video"
data = scrapertools.cache_page(page_url, post=post, headers=headers)
logger.info("data=" + data)
# Extrae el trozo cifrado
#<div id="embedcontmvshre" style="position: absolute; top: 0; left: 0; visibility: hidden;"><script type='text/javascript'>eval(function(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}('1i.1h(\'<8 10="1g"1f="1e:1d-1c-1b-1a-19"q="p"o="n"18="3://b.7.4/a/17.16"><2 1="u"0="t"/><2 1="s"0="r"/><2 1="m"0="3://i/l/6.k"/><2 1="f"0="5"><2 1="g"0="5"/><2 1="e"0="c"/><2 1="j"0="h"/><2 1="z"0="3://y.x.4:w/d/v/6"/><9 10="15"14="13/7"z="3://y.x.4:w/d/v/6"u="t"s="r"q="p"o="n"m="3://i/l/6.k"j="h"g="5"f="5"e="c"12="3://b.7.4/a/11/"></9></8>\');',36,55,'value|name|param|http|com|false|qtrv0ufkz3e4|divx|object|embed|plugin|go|Play||previewMessage|allowContextMenu|bannerEnabled|true||autoPlay|jpg|00249|previewImage|318|height|640|width|transparent|wmode|Stage6|custommode|opujxvaorizu2mdg6fst2fjdzlrn4p437h3lsbz5fjkxs|364|divxden|s31|src|id|download|pluginspage|video|type|np_vid|cab|DivXBrowserPlugin|codebase|CC0F21721616|9C46|41fa|D0AB|67DABFBF|clsid|classid|ie_vid|write|document'.split('|')))</script></div>
patron = "(<script type='text/javascript'>eval\(function.*?</script>)"
matches = re.compile(patron, re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
data = ""
if len(matches) > 0:
data = matches[0]
logger.info("[vidxden.py] bloque packed=" + data)
else:
logger.info("[vidxden.py] no encuentra bloque packed=" + data)
return ""
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
# Extrae la URL del vídeo
logger.info("descifrado=" + descifrado)
# Extrae la URL
patron = '<param name="src"value="([^"]+)"/>'
matches = re.compile(patron, re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
if len(matches) == 0:
descifrado = descifrado.replace("\\", "")
patron = "file','([^']+)'"
matches = re.compile(patron, re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
video_urls = []
if len(matches) > 0:
video_urls.append([
"[vidxden]", matches[0] + "|Referer=" + urllib.quote(page_url) +
"&User-Agent=" + urllib.quote(
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.1.14) Gecko/20080404 Firefox/2.0.0.14'
)
])
for video_url in video_urls:
logger.info("[vidxden.py] %s - %s" % (video_url[0], video_url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("[videopremium.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
# Lee la URL
data = scrapertools.cache_page( page_url )
logger.info("data="+data)
bloque = scrapertools.get_match(data,'<Form[^>]*method="POST"(.*)</.orm>')
logger.info("bloque="+bloque)
op = scrapertools.get_match(bloque,'<input type="hidden" name="op" value="([^"]+)"')
usr_login = scrapertools.get_match(bloque,'<input type="hidden" name="usr_login" value="([^"]*)"')
id = scrapertools.get_match(bloque,'<input type="hidden" name="id" value="([^"]+)"')
fname = scrapertools.get_match(bloque,'<input type="hidden" name="fname" value="([^"]+)"')
referer = scrapertools.get_match(bloque,'<input type="hidden" name="referer" value="([^"]*)"')
method_free = scrapertools.get_match(bloque,'<input type="[^"]+" name="method_free" value="([^"]+)"')
# Simula el botón
#op=download1&usr_login=&id=buq4b8zunbm6&fname=Snow.Buddies-Avventura.In.Alaska.2008.iTALiAN.AC3.DVDRip.H264-PsYcOcReW.avi&referer=&method_free=Watch+Free%21
post = "op="+op+"&usr_login="******"&id="+id+"&fname="+fname+"&referer="+referer+"&method_free="+method_free
data = scrapertools.cache_page( page_url , post=post )
#logger.info("data="+data)
try:
packed = scrapertools.get_match(data,"(<script type='text/javascript'>eval\(function\(p,a,c,k,e,d\).*?</script>)")
except:
packed = scrapertools.get_match(data,"(function\(p, a, c, k, e, d\).*?</script>)")
packed = "<script type='text/javascript'>eval("+packed
logger.info("packed="+packed)
from core import unpackerjs
unpacked = unpackerjs.unpackjs(packed)
logger.info("unpacked="+unpacked)
'''
23:47:40 T:2955980800 NOTICE: unpacked=('var vast=\'\';var flashvars={"comment":"VideoPremium.NET","st":"http://videopremium.net/uplayer/styles/video156-623.txt",
"file":"rtmp://tengig0.lb.videopremium.net/play/mp4:8x0mq9hanl3a.f4v",
p2pkey:"mp4:8x0mq9hanl3a.f4v",vast_preroll:vast};var params={bgcolor:"#ffffff",allowFullScreen:"true",allowScriptAccess:"always",id:"vplayer"};new swfobject.embedSWF("http://videopremium.net/uplayer/uppod.swf","vplayer","728","450","9.0.115.0",false,flashvars,params);',,paramsflashvars,
'''
'''
Property 'app' String 'play'
Property 'swfUrl' String 'http://videopremium.net/uplayer/uppod.swf'
Property 'pageUrl' String 'http://videopremium.net/8x0mq9hanl3a'
Property 'tcUrl' String 'rtmp://e5.videopremium.net/play'
play: String 'mp4:8x0mq9hanl3a.f4v'
'''
'''
00:55:30 T:2955980800 ERROR: Valid RTMP options are:
00:55:30 T:2955980800 ERROR: socks string Use the specified SOCKS proxy
00:55:30 T:2955980800 ERROR: app string Name of target app on server
00:55:30 T:2955980800 ERROR: tcUrl string URL to played stream
00:55:30 T:2955980800 ERROR: pageUrl string URL of played media's web page
00:55:30 T:2955980800 ERROR: swfUrl string URL to player SWF file
00:55:30 T:2955980800 ERROR: flashver string Flash version string (default MAC 10,0,32,18)
00:55:30 T:2955980800 ERROR: conn AMF Append arbitrary AMF data to Connect message
00:55:30 T:2955980800 ERROR: playpath string Path to target media on server
00:55:30 T:2955980800 ERROR: playlist boolean Set playlist before play command
00:55:30 T:2955980800 ERROR: live boolean Stream is live, no seeking possible
00:55:30 T:2955980800 ERROR: subscribe string Stream to subscribe to
00:55:30 T:2955980800 ERROR: jtv string Justin.tv authentication token
00:55:30 T:2955980800 ERROR: weeb string Weeb.tv authentication token
00:55:30 T:2955980800 ERROR: token string Key for SecureToken response
00:55:30 T:2955980800 ERROR: swfVfy boolean Perform SWF Verification
00:55:30 T:2955980800 ERROR: swfAge integer Number of days to use cached SWF hash
00:55:30 T:2955980800 ERROR: swfsize integer Size of the decompressed SWF file
00:55:30 T:2955980800 ERROR: swfhash string SHA256 hash of the decompressed SWF file
00:55:30 T:2955980800 ERROR: start integer Stream start position in milliseconds
00:55:30 T:2955980800 ERROR: stop integer Stream stop position in milliseconds
00:55:30 T:2955980800 ERROR: buffer integer Buffer time in milliseconds
00:55:30 T:2955980800 ERROR: timeout integer Session timeout in seconds
'''
rtmpurl=scrapertools.get_match(unpacked,'"file"\:"([^"]+)"').replace("tengig0.lb.videopremium.net","e4.videopremium.net")
playpath=scrapertools.get_match(unpacked,'p2pkey\:"([^"]+)"')
swfurl=scrapertools.get_match(unpacked,'embedSWF\("([^"]+)"')
pageurl = page_url
app="play"
tcurl="rtmp://e4.videopremium.net/play"
location = rtmpurl+" playpath="+playpath+" swfurl="+swfurl+" pageUrl="+page_url+" tcurl="+tcurl+" app="+app #swfvfy=true
logger.info("location="+location)
video_urls.append( [ "RTMP [videopremium]",location ] )
return video_urls
def geturl(urlvideo):
logger.info("[divxlink.py] url="+urlvideo)
# ---------------------------------------
# Inicializa la libreria de las cookies
# ---------------------------------------
ficherocookies = COOKIEFILE
try:
os.remove(ficherocookies)
except:
pass
# the path and filename to save your cookies in
cj = None
ClientCookie = None
cookielib = None
# Let's see if cookielib is available
try:
import cookielib
except ImportError:
# If importing cookielib fails
# let's try ClientCookie
try:
import ClientCookie
except ImportError:
# ClientCookie isn't available either
urlopen = urllib2.urlopen
Request = urllib2.Request
else:
# imported ClientCookie
urlopen = ClientCookie.urlopen
Request = ClientCookie.Request
cj = ClientCookie.LWPCookieJar()
else:
# importing cookielib worked
urlopen = urllib2.urlopen
Request = urllib2.Request
cj = cookielib.LWPCookieJar()
# This is a subclass of FileCookieJar
# that has useful load and save methods
# ---------------------------------
# Instala las cookies
# ---------------------------------
if cj is not None:
# we successfully imported
# one of the two cookie handling modules
if os.path.isfile(ficherocookies):
# if we have a cookie file already saved
# then load the cookies into the Cookie Jar
cj.load(ficherocookies)
# Now we need to get our Cookie Jar
# installed in the opener;
# for fetching URLs
if cookielib is not None:
# if we use cookielib
# then we get the HTTPCookieProcessor
# and install the opener in urllib2
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
else:
# if we use ClientCookie
# then we get the HTTPCookieProcessor
# and install the opener in ClientCookie
opener = ClientCookie.build_opener(ClientCookie.HTTPCookieProcessor(cj))
ClientCookie.install_opener(opener)
#print "-------------------------------------------------------"
url=urlvideo
#print url
#print "-------------------------------------------------------"
theurl = url
# an example url that sets a cookie,
# try different urls here and see the cookie collection you can make !
txdata = None
# if we were making a POST type request,
# we could encode a dictionary of values here,
# using urllib.urlencode(somedict)
txheaders = {'User-Agent':'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)'}
# fake a user agent, some websites (like google) don't like automated exploration
req = Request(theurl, txdata, txheaders)
handle = urlopen(req)
cj.save(ficherocookies) # save the cookies again
data=handle.read()
handle.close()
#print data
# Lo pide una segunda vez, como si hubieras hecho click en el banner
patron = 'http\:\/\/www\.divxlink\.com/([^\/]+)/(.*?)\.html'
matches = re.compile(patron,re.DOTALL).findall(url)
logger.info("[divxlink.py] fragmentos de la URL")
scrapertools.printMatches(matches)
codigo = ""
nombre = ""
if len(matches)>0:
codigo = matches[0][0]
nombre = matches[0][1]
patron = '<input type="hidden" name="rand" value="([^"]+)">'
matches = re.compile(patron,re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
randomstring=""
if len(matches)>0:
randomstring=matches[0]
logger.info("[divxlink.py] randomstring="+randomstring)
txdata = "op=download2&id="+codigo+"&rand="+randomstring+"&referer=&method_free=&method_premium=&down_direct=1"
logger.info(txdata)
req = Request(theurl, txdata, txheaders)
handle = urlopen(req)
cj.save(ficherocookies) # save the cookies again
data=handle.read()
handle.close()
#print data
patron = '<div id="embedcontmvshre"[^>]+>(.*?)</div>'
matches = re.compile(patron,re.DOTALL).findall(data)
#scrapertools.printMatches(matches)
data = ""
if len(matches)>0:
data = matches[0]
logger.info("[divxlink.py] bloque packed="+data)
else:
return ""
# Lo descifra
descifrado = unpackerjs.unpackjs(data)
logger.info("descifrado="+descifrado)
# Extrae la URL
patron = '<param name="src"value="([^"]+)"/>'
matches = re.compile(patron,re.DOTALL).findall(descifrado)
scrapertools.printMatches(matches)
url = ""
if len(matches)>0:
url = matches[0]
logger.info("[divxlink.py] url="+url)
return url
