1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-24 15:27:55 +01:00

add JukeboxIE

This commit is contained in:
mc2avr 2013-06-25 13:28:59 +02:00
parent f8bf74575a
commit 28ef06f7c2
2 changed files with 61 additions and 0 deletions

View File

@ -22,6 +22,7 @@ from .hypem import HypemIE
from .ina import InaIE from .ina import InaIE
from .infoq import InfoQIE from .infoq import InfoQIE
from .justintv import JustinTVIE from .justintv import JustinTVIE
from .jukebox import JukeboxIE
from .keek import KeekIE from .keek import KeekIE
from .liveleak import LiveLeakIE from .liveleak import LiveLeakIE
from .metacafe import MetacafeIE from .metacafe import MetacafeIE
@ -125,6 +126,7 @@ def gen_extractors():
GametrailersIE(), GametrailersIE(),
StatigramIE(), StatigramIE(),
BreakIE(), BreakIE(),
JukeboxIE(),
GenericIE() GenericIE()
] ]

View File

@ -0,0 +1,59 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unescapeHTML,
)
class JukeboxIE(InfoExtractor):
_VALID_URL = r'^http://www\.jukebox\.es\/.+[,](?P<video_id>[a-z0-9]+).html'
_IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
_VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
_TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'
_NOT_AVAILABLE = r'<span>Este video no está disponible por el momento [!]</span>'
_IS_YOUTUBE = r'config":{"file":"(?P<youtube_url>http:[\\][/][\\][/]www[.]youtube[.]com[\\][/]watch[?]v=[^"]+)"'
IE_NAME = u'jukebox'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('video_id')
html = self._download_webpage(url, video_id)
mobj = re.search(self._IFRAME, html)
if mobj is None:
raise ExtractorError(u'Cannot extract iframe url')
iframe_url = unescapeHTML(mobj.group('iframe'))
iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
mobj = re.search(self._NOT_AVAILABLE, iframe_html)
if mobj is not None:
raise ExtractorError(u'Video is not available(in your country?)!')
self.report_extraction(video_id)
mobj = re.search(self._VIDEO_URL, iframe_html)
if mobj is None:
mobj = re.search(self._IS_YOUTUBE, iframe_html)
if mobj is None:
raise ExtractorError(u'Cannot extract video url')
youtube_url = unescapeHTML(mobj.group('youtube_url')).replace('\/','/')
#TODO: call YoutubeIE !?
raise ExtractorError(u'found YT video. Please run youtube-dl again and use the following link: '+youtube_url+' ')
video_url = unescapeHTML(mobj.group('video_url')).replace('\/','/')
video_ext = unescapeHTML(mobj.group('video_ext'))
mobj = re.search(self._TITLE, html)
if mobj is None:
raise ExtractorError(u'Cannot extract title')
title = unescapeHTML(mobj.group('title'))
artist = unescapeHTML(mobj.group('artist'))
return [{'id': video_id,
'url': video_url,
'title': artist + '-' + title,
'ext': video_ext
}]