def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.servers.adn40 get_video_url(page_url='%s')" %
page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.server.rtve get_video_url result=" + repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append([
"[adn40]",
scrapertools.safe_unicode(result['url']).encode('utf-8')
])
else:
if "entries" in result:
for entry in result["entries"]:
logger.info("entry=" + repr(entry))
video_urls.append([
scrapertools.safe_unicode(entry["ext"]).encode('utf-8') +
" [adn40]",
scrapertools.safe_unicode(entry['url']).encode('utf-8')
])
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.server.populartvcantabria get_video_url page_url" +
page_url)
data = scrapertools.cache_page(page_url)
video_id = scrapertools.find_single_match(data, 'data-video_id="([^"]+)"')
logger.info("tvalacarta.server.populartvcantabria video_id=" + video_id)
youtube_url = "https://www.youtube.com/watch?v=" + video_id
logger.info("tvalacarta.server.populartvcantabria youtube_url=" +
youtube_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(youtube_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry=" + repr(entry))
if 'http' in entry['protocol']:
video_urls.append([
scrapertools.safe_unicode(entry['format']).encode('utf-8'),
scrapertools.safe_unicode(entry['url']).encode('utf-8')
])
#logger.info('Append: {}'.format(entry['url']))
video_urls.reverse()
return video_urls
def get_video_url(page_url, premium=False, user="", password="", video_password="", page_data=""):
logger.info("tvalacarta.server.rtve get_video_url page_url" + page_url)
video_urls = []
ydl = youtube_dl.YoutubeDL({"outtmpl": u"%(id)s%(ext)s"})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.server.rtve get_video_url result=" + repr(result))
if "ext" in result and "url" in result:
video_urls.append(["(opción 1) [rtve]", scrapertools.safe_unicode(result["url"]).encode("utf-8")])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append(["(opción 1) [rtve]", scrapertools.safe_unicode(entry["url"]).encode("utf-8")])
try:
alternate_video_urls = descargavideos.get_video_url(page_url)
for video_url in alternate_video_urls:
video_urls.append(["(opción 2) [rtve]", video_url[1]])
except:
import traceback
logger.info("tvalacarta.server.rtve get_video_url " + traceback.format_exc())
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("tvalacarta.server.rtvcm get_video_url page_url"+page_url)
data = scrapertools.cache_page(page_url)
#<script src="http://cdnapi.kaltura.com/p/2288691/sp/228869100/embedIframeJs/uiconf_id/39784151/partner_id/2288691?autoembed=true&playerId=kaltura_player_1496914486&entry_id=0_3e1eijre&flashvars[streamerType]=auto&width=640&height=360&flashvars[streamerType]=auto"></script> </div>
partner_id = scrapertools.find_single_match(data,'<script src="http://cdnapi.kaltura.com/p/\d+/sp/\d+/embedIframeJs/uiconf_id/\d+/partner_id/(\d+)')
logger.info("tvalacarta.server.rtvcm get_video_url partner_id="+partner_id)
video_id = scrapertools.find_single_match(data,'<script src="http://cdnapi.kaltura.com/p/\d+/sp/\d+/embedIframeJs/uiconf_id/\d+/partner_id/\d+.autoembed=true&playerId=kaltura_player_\d+&entry_id=([^\&]+)\&')
logger.info("tvalacarta.server.rtvcm get_video_url video_id="+video_id)
media_url = "kaltura:"+partner_id+":"+video_id
logger.info("tvalacarta.server.rtvcm get_video_url media_url="+media_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(media_url, download=False)
logger.info("tvalacarta.server.rtvcm get_video_url result="+repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append(["[rtvcm]", scrapertools.safe_unicode(result['url']).encode('utf-8')+"|User-Agent=Mozilla/5.0"])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append(["[rtvcm]", scrapertools.safe_unicode(entry['url']).encode('utf-8')+"|User-Agent=Mozilla/5.0"])
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.server.navarratv get_video_url page_url" +
page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry=" + repr(entry))
if 'http' in entry['protocol']:
video_urls.append([
scrapertools.safe_unicode(entry['format']).encode('utf-8'),
scrapertools.safe_unicode(entry['url']).encode('utf-8')
])
#logger.info('Append: {}'.format(entry['url']))
video_urls.reverse()
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.servers.youtube get_video_url page_url=" +
page_url)
if not page_url.startswith("http"):
page_url = "http://www.youtube.com/watch?v=" + page_url
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry=" + repr(entry))
video_urls.append([
scrapertools.safe_unicode(entry['format']).encode('utf-8'),
scrapertools.safe_unicode(entry['url']).encode('utf-8')
])
video_urls.reverse()
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("tvalacarta.server.rtvcm get_video_url page_url"+page_url)
data = scrapertools.cache_page(page_url)
partner_id = scrapertools.find_single_match(data,'<meta property="og:image" content="https://www.kaltura.com/p/(\d+)/sp/\d+/thumbnail')
logger.info("tvalacarta.server.rtvcm get_video_url partner_id="+partner_id)
video_id = scrapertools.find_single_match(data,'<meta property="og:image" content="https://www.kaltura.com/p/\d+/sp/\d+/thumbnail/entry_id/([^/]+)')
logger.info("tvalacarta.server.rtvcm get_video_url video_id="+video_id)
media_url = "kaltura:"+partner_id+":"+video_id
logger.info("tvalacarta.server.rtvcm get_video_url media_url="+media_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(media_url, download=False)
logger.info("tvalacarta.server.rtvcm get_video_url result="+repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append(["[rtvcm]", scrapertools.safe_unicode(result['url']).encode('utf-8')+"|User-Agent=Mozilla/5.0"])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append(["[rtvcm]", scrapertools.safe_unicode(entry['url']).encode('utf-8')+"|User-Agent=Mozilla/5.0"])
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("tvalacarta.servers.telemadrid get_video_url(page_url='%s')" %
page_url)
'''
<video id="5c04f64ee88f4"
data-video-id="5971764264001"
data-account="104403117001"
data-player="SkevQBitbl"
data-embed="default"
class="video-js"
controls></video>
'''
#http://players.brightcove.net/104403117001/SkevQBitbl_default/index.html?videoId=5971764264001
data = scrapertools.cache_page(page_url)
account = scrapertools.find_single_match(data, 'data-account="([^"]+)"')
logger.info("account=" + account)
player = scrapertools.find_single_match(data, 'data-player="([^"]+)"')
logger.info("player=" + account)
video_id = scrapertools.find_single_match(data, 'data-video-id="([^"]+)"')
logger.info("video_id=" + video_id)
api_url = "http://players.brightcove.net/" + account + "/" + player + "_default/index.html?videoId=" + video_id
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(api_url, download=False)
logger.info("tvalacarta.servers.telemadrid get_video_url result=" +
repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append([
"(.m3u8)",
scrapertools.safe_unicode(result['url']).encode('utf-8')
])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append([
"(.m3u8)",
scrapertools.safe_unicode(entry['url']).encode('utf-8')
])
for video_url in video_urls:
logger.info("tvalacarta.servers.telemadrid %s - %s" %
(video_url[0], video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.servers.beteve get_video_url(page_url='%s')" %
page_url)
data = scrapertools.cache_page(page_url)
#<meta property="og:image" content="https://cdnsecakmi.kaltura.com/p/2346171/thumbnail/entry_id/1_vfk43038/height/weight/76kXI.jpg" />
thumb = scrapertools.find_single_match(
data, '<meta property="og:image" content="([^"]+)"')
p = scrapertools.find_single_match(thumb, "p\/([^\/]+)\/")
entry_id = scrapertools.find_single_match(thumb, "entry_id\/([^\/]+)\/")
url = "kaltura:" + p + ":" + entry_id
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.server.beteve get_video_url result=" +
repr(result))
video_urls = []
try:
if "ext" in result and "url" in result:
video_urls.append([
"(.m3u8)",
scrapertools.safe_unicode(result['url']).encode('utf-8') +
"|User-Agent=Mozilla/5.0"
])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append([
"(.m3u8)",
scrapertools.safe_unicode(entry['url']).encode('utf-8')
+ "|User-Agent=Mozilla/5.0"
])
except:
import traceback
logger.info("tvalacarta.server.beteve get_video_url " +
traceback.format_exc())
for video_url in video_urls:
logger.info("tvalacarta.servers.beteve %s - %s" %
(video_url[0], video_url[1]))
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.server.rtvcm get_video_url page_url" + page_url)
data = scrapertools.cache_page(page_url)
#<script src="http://cdnapi.kaltura.com/p/2288691/sp/228869100/embedIframeJs/uiconf_id/39784151/partner_id/2288691?autoembed=true&playerId=kaltura_player_1496914486&entry_id=0_3e1eijre&flashvars[streamerType]=auto&width=640&height=360&flashvars[streamerType]=auto"></script> </div>
partner_id = scrapertools.find_single_match(
data,
'<script src="http://cdnapi.kaltura.com/p/\d+/sp/\d+/embedIframeJs/uiconf_id/\d+/partner_id/(\d+)'
)
logger.info("tvalacarta.server.rtvcm get_video_url partner_id=" +
partner_id)
video_id = scrapertools.find_single_match(
data,
'<script src="http://cdnapi.kaltura.com/p/\d+/sp/\d+/embedIframeJs/uiconf_id/\d+/partner_id/\d+.autoembed=true&playerId=kaltura_player_\d+&entry_id=([^\&]+)\&'
)
logger.info("tvalacarta.server.rtvcm get_video_url video_id=" + video_id)
media_url = "kaltura:" + partner_id + ":" + video_id
logger.info("tvalacarta.server.rtvcm get_video_url media_url=" + media_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(media_url, download=False)
logger.info("tvalacarta.server.rtvcm get_video_url result=" + repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append([
"[rtvcm]",
scrapertools.safe_unicode(result['url']).encode('utf-8') +
"|User-Agent=Mozilla/5.0"
])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append([
"[rtvcm]",
scrapertools.safe_unicode(entry['url']).encode('utf-8') +
"|User-Agent=Mozilla/5.0"
])
return video_urls
def episodios(item,load_all_pages=True):
logger.info("tvalacarta.channels.navarratv episodios")
itemlist = []
# Descarga la página
data = scrapertools.cache_page(item.url)
patron = '<div class="Programa"[^<]+'
patron += '<a href="([^"]+)"[^<]+'
patron += '<img src="([^"]+)" alt="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(data)
for scrapedurl,scrapedthumbnail,scrapedtitle in matches:
thumbnail = urlparse.urljoin(item.url,scrapedthumbnail)
yt_id = scrapertools.find_single_match(scrapedurl,"p=([A-Za-z0-9_\-]+)")
url = "https://www.youtube.com/watch?v="+yt_id
title = scrapertools.safe_unicode(scrapedtitle).encode("utf-8").strip()
plot = ""
itemlist.append( Item(channel=__channel__, action="play", server="youtube", title=title, url=url, thumbnail=thumbnail, fanart=thumbnail, show=item.show, plot=plot, folder=True))
return itemlist
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.servers.azteca get_video_url page_url=" + page_url)
data = scrapertools.cache_page(page_url)
page_url = scrapertools.find_single_match(
data, '<meta property="og:video" content="([^"]+)"/>')
logger.info("tvalacarta.servers.azteca get_video_url page_url=" + page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry=" + repr(entry))
'''
{u'http_headers':
{
u'Accept-Charset': u'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
u'Accept-Language': u'en-us,en;q=0.5',
u'Accept-Encoding': u'gzip, deflate',
u'Accept': u'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
u'User-Agent': u'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/44.0 (Chrome)'},
u'protocol': u'm3u8_native',
u'format': u'hls-582 - 640x360',
u'url': u'http://tvazvod-i.akamaihd.net/i/p/459791/sp/45979100/serveFlavor/entryId/0_pcso1cnx/v/2/flavorId/0_qx9uhlyx/index_0_av.m3u8',
u'tbr': 582,
u'height': 360,
u'width': 640,
u'ext': u'mp4',
u'preference': None,
u'format_id': u'hls-582'
}
'''
video_urls.append([
scrapertools.safe_unicode(entry['format']).encode('utf-8'),
scrapertools.safe_unicode(entry['url']).encode('utf-8')
])
#logger.info('Append: {}'.format(entry['url']))
video_urls.reverse()
return video_urls
def episodios(item, load_all_pages=True):
logger.info("tvalacarta.channels.navarratv episodios")
itemlist = []
# Descarga la página
data = scrapertools.cache_page(item.url)
"""
<div class="Bloque2Noticias">
<div class="ImpactoBloque W50 H120 FranjaRoja ">
<div class="ImpactoBloqueImagen W98" style="height: 150px;">
<div class="ImpactoContenedorImagen" style="height: 150px; cursor: pointer; background-image: url('https://i.ytimg.com/vi/RXBDpg7oduk/mqdefault.jpg');" onclick="location.href='/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/yt/RXBDpg7oduk/IMPLICADOS-18-DE-JUNIO-DE-2016';"/></div>
</div>
<div class="ImpactoBloqueContenido W98">
<h2><a href="/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/yt/RXBDpg7oduk/IMPLICADOS-18-DE-JUNIO-DE-2016" class="TextoNeutro">IMPLICADOS 18 DE JUNIO DE 2016</a></h2>
<p>IMPLICADOS 18 DE JUNIO DE 2016</p>
</div>
</div>
<div class="W3"></div>
"""
patron = '<div class="Bloque2Noticias"[^<]+'
patron += '<div class="ImpactoBloque W50 H120 FranjaRoja[^<]+'
patron += '<div class="ImpactoBloqueImagen[^<]+'
patron += "<div class=\"ImpactoContenedorImagen\".*?url\('([^']+)'\)[^<]+</div[^<]+"
patron += "</div[^<]+"
patron += '<div class="ImpactoBloqueContenido[^<]+'
patron += '<h2><a href="([^"]+)" class="TextoNeutro">([^<]+)</a></h2[^<]+'
patron += "<p>([^<]*)</p>"
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedthumbnail, scrapedurl, scrapedtitle, scrapedplot in matches:
thumbnail = urlparse.urljoin(item.url, scrapedthumbnail)
yt_id = scrapertools.find_single_match(scrapedurl, "/yt/([^/]+)/")
url = "https://www.youtube.com/watch?v=" + yt_id
title = scrapertools.safe_unicode(scrapedtitle).encode("utf-8").strip()
plot = ""
itemlist.append(
Item(
channel=__channel__,
action="play",
server="youtube",
title=title,
url=url,
thumbnail=thumbnail,
fanart=thumbnail,
show=item.show,
plot=plot,
folder=True,
)
)
return itemlist
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("tvalacarta.server.rtve get_video_url page_url"+page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.server.rtve get_video_url result="+repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append(["."+scrapertools.safe_unicode(result['ext']).encode('utf-8')+" [rtve]", scrapertools.safe_unicode(result['url']).encode('utf-8')])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append(["."+scrapertools.safe_unicode(entry['ext']).encode('utf-8')+" [rtve]", scrapertools.safe_unicode(entry['url']).encode('utf-8')])
return video_urls
def episodios(item, load_all_pages=True):
logger.info("tvalacarta.channels.navarratv episodios")
itemlist = []
# Descarga la página
data = scrapertools.cache_page(item.url)
'''
<div class="Bloque2Noticias">
<div class="ImpactoBloque W50 H120 FranjaRoja ">
<div class="ImpactoBloqueImagen W98" style="height: 150px;">
<div class="ImpactoContenedorImagen" style="height: 150px; cursor: pointer; background-image: url('https://i.ytimg.com/vi/RXBDpg7oduk/mqdefault.jpg');" onclick="location.href='/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/yt/RXBDpg7oduk/IMPLICADOS-18-DE-JUNIO-DE-2016';"/></div>
</div>
<div class="ImpactoBloqueContenido W98">
<h2><a href="/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/yt/RXBDpg7oduk/IMPLICADOS-18-DE-JUNIO-DE-2016" class="TextoNeutro">IMPLICADOS 18 DE JUNIO DE 2016</a></h2>
<p>IMPLICADOS 18 DE JUNIO DE 2016</p>
</div>
</div>
<div class="W3"></div>
'''
patron = '<div class="Bloque2Noticias"[^<]+'
patron += '<div class="ImpactoBloque W50 H120 FranjaRoja[^<]+'
patron += '<div class="ImpactoBloqueImagen[^<]+'
patron += "<div class=\"ImpactoContenedorImagen\".*?url\('([^']+)'\)[^<]+</div[^<]+"
patron += '</div[^<]+'
patron += '<div class="ImpactoBloqueContenido[^<]+'
patron += '<h2><a href="([^"]+)" class="TextoNeutro">([^<]+)</a></h2[^<]+'
patron += '<p>([^<]*)</p>'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedthumbnail, scrapedurl, scrapedtitle, scrapedplot in matches:
thumbnail = urlparse.urljoin(item.url, scrapedthumbnail)
yt_id = scrapertools.find_single_match(scrapedurl, "/yt/([^/]+)/")
url = "https://www.youtube.com/watch?v=" + yt_id
title = scrapertools.safe_unicode(scrapedtitle).encode("utf-8").strip()
plot = scrapedplot.strip()
aired_date = scrapertools.parse_date(title)
itemlist.append(
Item(channel=__channel__,
action="play",
server="navarratv",
title=title,
url=url,
thumbnail=thumbnail,
fanart=thumbnail,
show=item.show,
aired_date=aired_date,
plot=plot,
folder=False))
return itemlist
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password="",
page_data=""):
logger.info("tvalacarta.server.rtve get_video_url page_url" + page_url)
video_urls = []
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.server.rtve get_video_url result=" + repr(result))
if "ext" in result and "url" in result:
video_urls.append([
"(opción 1) [rtve]",
scrapertools.safe_unicode(result['url']).encode('utf-8') +
"|User-Agent=Mozilla/5.0"
])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append([
"(opción 1) [rtve]",
scrapertools.safe_unicode(entry['url']).encode('utf-8') +
"|User-Agent=Mozilla/5.0"
])
try:
alternate_video_urls = descargavideos.get_video_url(page_url)
for video_url in alternate_video_urls:
video_urls.append([
"(opción 2) [rtve]", video_url[1] + "|User-Agent=Mozilla/5.0"
])
except:
import traceback
logger.info("tvalacarta.server.rtve get_video_url " +
traceback.format_exc())
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("tvalacarta.servers.telemadrid get_video_url(page_url='%s')" %
page_url)
data = scrapertools.cache_page(page_url)
iframe = scrapertools.find_single_match(
data, '<iframe id="miVideotm"[^<]+</iframe')
media_url = scrapertools.find_single_match(iframe, 'src="([^"]+)"')
media_url = media_url + "http:"
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(media_url, download=False)
logger.info("tvalacarta.servers.telemadrid get_video_url result=" +
repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append([
"[telemadrid]",
scrapertools.safe_unicode(result['url']).encode('utf-8')
])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append([
"[telemadrid]",
scrapertools.safe_unicode(entry['url']).encode('utf-8')
])
for video_url in video_urls:
logger.info("tvalacarta.servers.telemadrid %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("[mitele.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.server.mitele get_video_url result="+repr(result))
for entries in result["formats"]:
if entries["ext"] != "rtmp":
video_url = scrapertools.safe_unicode(entries['url']).encode('utf-8')
video_url = video_url.replace("http://ignore.mediaset.es", "http://miteleooyala-a.akamaihd.net")
if entries["ext"] != "mp4":
title = scrapertools.safe_unicode(entries["format"]).encode('utf-8')
elif entries["ext"] == "mp4":
if entries.has_key("vbr"):
title = "mp4-" + scrapertools.safe_unicode(str(entries["vbr"])).encode('utf-8') + " " + scrapertools.safe_unicode(entries["format"]).encode('utf-8').rsplit("-",1)[1]
else:
title = scrapertools.safe_unicode(entries["format"]).encode('utf-8')
try:
calidad = int(scrapertools.safe_unicode(str(entries["vbr"])))
except:
try:
calidad = int(title.split("-")[1].strip())
except:
calidad = 3000
video_urls.append(["%s" % title, video_url, 0, False, calidad])
video_urls.sort(key=lambda video_urls: video_urls[4], reverse=True)
for url in video_urls:
logger.info("[mitele.py] %s - %s" % (url[0],url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("[mitele.py] get_video_url(page_url='%s')" % page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry="+repr(entry))
if 'hls' in entry['format']:
video_urls.append([scrapertools.safe_unicode(entry['format']).encode('utf-8'), scrapertools.safe_unicode(entry['url']).encode('utf-8')])
video_urls.reverse()
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("tvalacarta.server.rtvcm get_video_url page_url"+page_url)
data = scrapertools.cache_page(page_url)
#<iframe id="flumotion_iframe_player" name="flumotion_iframe_player" src="http://cdnapi.kaltura.com/p/2288691/sp/228869100/embedIframeJs/uiconf_id/39784151/partner_id/2288691?iframeembed=true&playerId=kaltura_player_1496914486&entry_id=0_7nkaf0ce&flashvars[streamerType]=auto"
media_url = scrapertools.find_single_match(data,'<iframe id="flumotion_iframe_player" name="flumotion_iframe_player" src="([^"]+)"')
video_urls = []
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(media_url, download=False)
logger.info("tvalacarta.server.rtvcm get_video_url result="+repr(result))
if "ext" in result and "url" in result:
video_urls.append(["[rtvcm]", scrapertools.safe_unicode(result['url']).encode('utf-8')+"|User-Agent=Mozilla/5.0"])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append(["[rtvcm]", scrapertools.safe_unicode(entry['url']).encode('utf-8')+"|User-Agent=Mozilla/5.0"])
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("tvalacarta.servers.telemundo get_video_url page_url="+page_url)
video_urls = []
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.servers.telemadrid get_video_url result="+repr(result))
video_urls = []
if "ext" in result and "url" in result:
video_urls.append(["[telemundo]", scrapertools.safe_unicode(result['url']).encode('utf-8')])
else:
if "entries" in result:
for entry in result["entries"]:
video_urls.append(["[telemundo]", scrapertools.safe_unicode(entry['url']).encode('utf-8')])
for video_url in video_urls:
logger.info("tvalacarta.servers.telemundo %s - %s" % (video_url[0],video_url[1]))
return video_urls
def programas(item):
logger.info("tvalacarta.channels.navarratv programas")
itemlist = []
# Descarga la página
data = scrapertools.cache_page(item.url)
"""
<div class="ImpactoBloque W50 H120 FranjaRoja Noticia2Col">
<div class="ImpactoBloqueImagen W98" style="height: 150px;">
<div class="ImpactoContenedorImagen" style="height: 150px; cursor: pointer; background-image: url('http://i.natv.es/imagenes/A82E542A-FD3D-485F-C933A8E7C294C438.JPG');" onclick="location.href='/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/Implicados';"/></div>
</div>
<div class="ImpactoBloqueContenido W98">
<h2><a href="/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/Implicados" class="TextoNeutro">Implicados</a></h2>
<p>Programa semanal que presenta el periodista Alejandro Palacios y que sirve para dar a conocer la labor de las personas que se implican por lograr una sociedad mejor.</p>
</div>
</div>
"""
patron = '<div class="ImpactoBloque W50 H120 FranjaRoja[^<]+'
patron += '<div class="ImpactoBloqueImagen[^<]+'
patron += "<div class=\"ImpactoContenedorImagen\".*?url\('([^']+)'\)[^<]+</div[^<]+"
patron += "</div[^<]+"
patron += '<div class="ImpactoBloqueContenido[^<]+'
patron += '<h2><a href="([^"]+)" class="TextoNeutro">([^<]+)</a></h2[^<]+'
patron += "<p>([^<]*)</p>"
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedthumbnail, scrapedurl, scrapedtitle, scrapedplot in matches:
thumbnail = urlparse.urljoin(item.url, scrapedthumbnail)
url = urlparse.urljoin(item.url, scrapedurl)
title = scrapertools.safe_unicode(scrapedtitle).encode("utf-8").strip()
plot = scrapedplot.strip()
itemlist.append(
Item(
channel=__channel__,
action="episodios",
title=title,
show=title,
url=url,
thumbnail=thumbnail,
fanart=thumbnail,
plot=plot,
folder=True,
)
)
return itemlist
def programas(item):
logger.info("tvalacarta.channels.navarratv programas")
itemlist = []
item.url = "http://www.natv.es/Alacarta"
item.view = "programs"
# Descarga la página
data = scrapertools.cache_page(item.url)
'''
<div class="ImpactoBloque W50 H120 FranjaRoja Noticia2Col">
<div class="ImpactoBloqueImagen W98" style="height: 150px;">
<div class="ImpactoContenedorImagen" style="height: 150px; cursor: pointer; background-image: url('http://i.natv.es/imagenes/A82E542A-FD3D-485F-C933A8E7C294C438.JPG');" onclick="location.href='/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/Implicados';"/></div>
</div>
<div class="ImpactoBloqueContenido W98">
<h2><a href="/AlaCarta/92C813D7-1676-E17B-1AB1E57E2065947C/Implicados" class="TextoNeutro">Implicados</a></h2>
<p>Programa semanal que presenta el periodista Alejandro Palacios y que sirve para dar a conocer la labor de las personas que se implican por lograr una sociedad mejor.</p>
</div>
</div>
'''
patron = '<div class="ImpactoBloque W50 H120 FranjaRoja[^<]+'
patron += '<div class="ImpactoBloqueImagen[^<]+'
patron += "<div class=\"ImpactoContenedorImagen\".*?url\('([^']+)'\)[^<]+</div[^<]+"
patron += '</div[^<]+'
patron += '<div class="ImpactoBloqueContenido[^<]+'
patron += '<h2><a href="([^"]+)" class="TextoNeutro">([^<]+)</a></h2[^<]+'
patron += '<p>([^<]*)</p>'
matches = re.compile(patron, re.DOTALL).findall(data)
for scrapedthumbnail, scrapedurl, scrapedtitle, scrapedplot in matches:
thumbnail = urlparse.urljoin(item.url, scrapedthumbnail)
url = urlparse.urljoin(item.url, scrapedurl)
title = scrapertools.safe_unicode(scrapedtitle).encode("utf-8").strip()
plot = scrapedplot.strip()
itemlist.append(
Item(channel=__channel__,
action="episodios",
title=title,
show=title,
url=url,
thumbnail=thumbnail,
fanart=thumbnail,
plot=plot,
folder=True))
return itemlist
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("[discoverymax.py] get_video_url(page_url='%s')" % page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s', 'no_color': True})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
video_urls.append( [scrapertools.safe_unicode(entry['format']).encode('utf-8') , scrapertools.safe_unicode(entry['url']).encode('utf-8') ])
# Para que ponga la calidad más alta primero
video_urls.reverse()
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("[discoverymax.py] get_video_url(page_url='%s')" % page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s', 'no_color': True})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
video_urls.append( [scrapertools.safe_unicode(entry['format']).encode('utf-8') , scrapertools.safe_unicode(entry['url']).encode('utf-8') ])
# Para que ponga la calidad más alta primero
video_urls.reverse()
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("[eitb.py] get_video_url(page_url='%s')" % page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry="+repr(entry))
if 'http' in entry['protocol']:
video_urls.append([scrapertools.safe_unicode(entry['format']).encode('utf-8'), scrapertools.safe_unicode(entry['url']).encode('utf-8')])
#logger.info('Append: {}'.format(entry['url']))
video_urls.reverse()
return video_urls
def get_video_url(page_url,
premium=False,
user="",
password="",
video_password=""):
logger.info("[mitele.py] get_video_url(page_url='%s')" % page_url)
video_urls = []
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("tvalacarta.server.mitele get_video_url result=" +
repr(result))
for entries in result["formats"]:
if entries["ext"] != "rtmp":
video_url = scrapertools.safe_unicode(
entries['url']).encode('utf-8')
video_url = video_url.replace(
"http://ignore.mediaset.es",
"http://miteleooyala-a.akamaihd.net")
if entries["ext"] != "mp4":
title = scrapertools.safe_unicode(
entries["format"]).encode('utf-8')
elif entries["ext"] == "mp4":
if entries.has_key("vbr"):
title = "mp4-" + scrapertools.safe_unicode(
str(entries["vbr"])
).encode('utf-8') + " " + scrapertools.safe_unicode(
entries["format"]).encode('utf-8').rsplit("-", 1)[1]
else:
title = scrapertools.safe_unicode(
entries["format"]).encode('utf-8')
try:
calidad = int(scrapertools.safe_unicode(str(entries["vbr"])))
except:
try:
calidad = int(title.split("-")[1].strip())
except:
calidad = 3000
video_urls.append(["%s" % title, video_url, 0, False, calidad])
video_urls.sort(key=lambda video_urls: video_urls[4], reverse=True)
for url in video_urls:
logger.info("[mitele.py] %s - %s" % (url[0], url[1]))
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
if not page_url.startswith("http"):
page_url = "http://www.youtube.com/watch?v="+page_url
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry="+repr(entry))
video_urls.append([scrapertools.safe_unicode(entry['format']).encode('utf-8'), scrapertools.safe_unicode(entry['url']).encode('utf-8')])
video_urls.reverse()
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="" ):
logger.info("tvalacarta.servers.disneychannel get_video_url(page_url='%s')" % page_url)
video_urls = []
data = scrapertools.cache_page(page_url)
page_url = scrapertools.find_single_match(data,'"downloadUrl"\:"([^"]+)"')
logger.info("tvalacarta.servers.disneychannel get_video_url page_url="+page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry="+repr(entry))
'''
{u'http_headers':
{
u'Accept-Charset': u'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
u'Accept-Language': u'en-us,en;q=0.5',
u'Accept-Encoding': u'gzip, deflate',
u'Accept': u'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
u'User-Agent': u'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/44.0 (Chrome)'},
u'protocol': u'm3u8_native',
u'format': u'hls-582 - 640x360',
u'url': u'http://tvazvod-i.akamaihd.net/i/p/459791/sp/45979100/serveFlavor/entryId/0_pcso1cnx/v/2/flavorId/0_qx9uhlyx/index_0_av.m3u8',
u'tbr': 582,
u'height': 360,
u'width': 640,
u'ext': u'mp4',
u'preference': None,
u'format_id': u'hls-582'
}
'''
video_urls.append(["."+scrapertools.safe_unicode(entry['ext']).encode('utf-8'), scrapertools.safe_unicode(entry['url']).encode('utf-8')])
#logger.info('Append: {}'.format(entry['url']))
video_urls.reverse()
return video_urls
def programas(item):
logger.info("tvalacarta.channels.navarratv programas")
itemlist = []
# Descarga la página
data = scrapertools.cache_page(item.url)
patron = '<div class="Programa"[^<]+'
patron += '<a href="([^"]+)"[^<]+'
patron += '<img src="([^"]+)" alt="([^"]+)"'
matches = re.compile(patron,re.DOTALL).findall(data)
for scrapedurl,scrapedthumbnail,scrapedtitle in matches:
thumbnail = urlparse.urljoin(item.url,scrapedthumbnail)
url = urlparse.urljoin(item.url,scrapedurl)
title = scrapertools.safe_unicode(scrapedtitle).encode("utf-8").strip()
plot = ""
itemlist.append( Item(channel=__channel__, action="episodios", title=title, show=title, url=url, thumbnail=thumbnail, fanart=thumbnail, plot=plot, folder=True))
return itemlist
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
if not page_url.startswith("http"):
page_url = "http://www.youtube.com/watch?v="+page_url
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
# Quita la playlist
if "&list=" in page_url:
import re
page_url = re.compile("\&list\=[A-Za-z0-9\-_]+",re.DOTALL).sub("",page_url)
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
if "?list=" in page_url:
import re
page_url = re.compile("\?list\=[^\&]+&",re.DOTALL).sub("?",page_url)
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("result="+repr(result))
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry="+repr(entry))
extension = ""
try:
if entry['ext'] is not None:
extension = scrapertools.safe_unicode("("+entry['ext']+")").encode('utf-8')
except:
import traceback
logger.info(traceback.format_exc())
resolution = ""
try:
if entry['width'] is not None and entry['height'] is not None:
resolution = scrapertools.safe_unicode(" ("+str(entry['width'])+"x"+str(entry['height'])+")").encode('utf-8')
except:
import traceback
logger.info(traceback.format_exc())
tag = ""
try:
if entry['acodec']=='none':
tag=" (Solo video)"
if entry['vcodec']=='none':
tag=" (Solo audio)"
if config.get_setting("youtube_special_formats")=="false" and tag<>"":
continue
except:
import traceback
logger.info(traceback.format_exc())
video_urls.append([ extension+resolution+tag , scrapertools.safe_unicode(entry['url']).encode('utf-8')])
video_urls.reverse()
return video_urls
def get_video_url( page_url , premium = False , user="" , password="", video_password="", page_data="" ):
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
if not page_url.startswith("http"):
page_url = "http://www.youtube.com/watch?v="+page_url
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
# Quita la playlist
if "&list=" in page_url:
import re
page_url = re.compile("\&list\=[A-Za-z0-9\-_]+",re.DOTALL).sub("",page_url)
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
if "?list=" in page_url:
import re
page_url = re.compile("\?list\=[^\&]+&",re.DOTALL).sub("?",page_url)
logger.info("tvalacarta.servers.youtube get_video_url page_url="+page_url)
ydl = youtube_dl.YoutubeDL({'outtmpl': u'%(id)s%(ext)s'})
result = ydl.extract_info(page_url, download=False)
logger.info("result="+repr(result))
video_urls = []
if 'formats' in result:
for entry in result['formats']:
logger.info("entry="+repr(entry))
extension = ""
try:
if entry['ext'] is not None:
extension = scrapertools.safe_unicode("("+entry['ext']+")").encode('utf-8')
except:
import traceback
logger.info(traceback.format_exc())
resolution = ""
try:
if entry['width'] is not None and entry['height'] is not None:
resolution = scrapertools.safe_unicode(" ("+str(entry['width'])+"x"+str(entry['height'])+")").encode('utf-8')
except:
import traceback
logger.info(traceback.format_exc())
tag = ""
try:
if entry['acodec']=='none':
tag=" (Solo video)"
if entry['vcodec']=='none':
tag=" (Solo audio)"
if config.get_setting("youtube_special_formats")=="false" and tag<>"":
continue
except:
import traceback
logger.info(traceback.format_exc())
video_urls.append([ extension+resolution+tag , scrapertools.safe_unicode(entry['url']).encode('utf-8')])
video_urls.reverse()
return video_urls