[telecinco] Add extractor (closes #4005)

It uses the same extraction process as mitele.es, but with a few small differences.
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-10-23 20:08:55 +02:00
parent 75da98e9e1
commit ad5f53ac72
3 changed files with 29 additions and 2 deletions

View file

@ -367,6 +367,7 @@ from .teachingchannel import TeachingChannelIE
from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE
from .ted import TEDIE
from .telecinco import TelecincoIE
from .telemb import TeleMBIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE

View file

@ -39,13 +39,21 @@ class MiTeleIE(InfoExtractor):
).replace('\'', '"')
embed_data = json.loads(embed_data_json)
info_url = embed_data['flashvars']['host']
domain = embed_data['mediaUrl']
if not domain.startswith('http'):
# only happens in telecinco.es videos
domain = 'http://' + domain
info_url = compat_urllib_parse.urljoin(
domain,
compat_urllib_parse.unquote(embed_data['flashvars']['host'])
)
info_el = self._download_xml(info_url, episode).find('./video/info')
video_link = info_el.find('videoUrl/link').text
token_query = compat_urllib_parse.urlencode({'id': video_link})
token_info = self._download_json(
'http://token.mitele.es/?' + token_query, episode,
embed_data['flashvars']['ov_tk'] + '?' + token_query,
episode,
transform_source=strip_jsonp
)

View file

@ -0,0 +1,18 @@
from __future__ import unicode_literals
from .mitele import MiTeleIE
class TelecincoIE(MiTeleIE):
IE_NAME = 'telecinco.es'
_VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<episode>.*?)\.html'
_TEST = {
'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
'info_dict': {
'id': 'MDSVID20141015_0058',
'ext': 'mp4',
'title': 'Con Martín Berasategui, hacer un bacalao al ...',
'duration': 662,
},
}