[rtve] Add support for live stream

At the moment, only RTVE-1 seems to work flawlessly.
-2 seems geoblocked right now.
-TDP doesn't seem to be available outside of Spain.
This commit is contained in:
Philipp Hagemeister 2014-08-22 18:40:26 +02:00
parent ed2d6a1960
commit 2b9faf5542
3 changed files with 113 additions and 47 deletions

View file

@ -264,7 +264,7 @@
from .rtlnl import RtlXlIE
from .rtlnow import RTLnowIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE
from .rtve import RTVEALaCartaIE, RTVELiveIE
from .ruhd import RUHDIE
from .rutube import (
RutubeIE,

View file

@ -1,31 +1,18 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
import base64
import re
import time
from .common import InfoExtractor
from ..utils import (
struct_unpack,
remove_end,
)
class RTVEALaCartaIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta'
IE_DESC = 'RTVE a la carta'
_VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
'info_dict': {
'id': '2491869',
'ext': 'mp4',
'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
},
}
def _decrypt_url(self, png):
def _decrypt_url(png):
encrypted_data = base64.b64decode(png)
text_index = encrypted_data.find(b'tEXt')
text_chunk = encrypted_data[text_index - 4:]
@ -66,6 +53,31 @@ def _decrypt_url(self, png):
return url
class RTVEALaCartaIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta'
IE_DESC = 'RTVE a la carta'
_VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
'info_dict': {
'id': '2491869',
'ext': 'mp4',
'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
},
}, {
'note': 'Live stream',
'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
'info_dict': {
'id': '1694255',
'ext': 'flv',
'title': 'TODO',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
@ -74,11 +86,59 @@ def _real_extract(self, url):
video_id)['page']['items'][0]
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = self._decrypt_url(png)
video_url = _decrypt_url(png)
return {
'id': video_id,
'title': info['title'],
'url': video_url,
'thumbnail': info['image'],
'thumbnail': info.get('image'),
'page_url': url,
}
class RTVELiveIE(InfoExtractor):
IE_NAME = 'rtve.es:live'
IE_DESC = 'RTVE.es live streams'
_VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias(?=/directo-la-1)|television)/(?P<id>[a-zA-Z0-9-]+)'
_TESTS = [{
'url': 'http://www.rtve.es/noticias/directo-la-1/',
'info_dict': {
'id': 'directo-la-1',
'ext': 'flv',
'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
},
'params': {
'skip_download': 'live stream',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
start_time = time.gmtime()
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL')
title = remove_end(self._og_search_title(webpage), ' en directo')
title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
vidplayer_id = self._search_regex(
r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
print(video_url)
return {
'id': video_id,
'ext': 'flv',
'title': title,
'url': video_url,
'app': 'rtve-live-live?ovpfv=2.1.2',
'player_url': player_url,
'rtmp_live': True,
}

View file

@ -1285,6 +1285,12 @@ def remove_start(s, start):
return s
def remove_end(s, end):
if s.endswith(end):
return s[:-len(end)]
return s
def url_basename(url):
path = compat_urlparse.urlparse(url).path
return path.strip(u'/').split(u'/')[-1]