[vice] Re-add extractor (fixes #4120)

The generic extraction no longer works.
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-11-06 21:44:07 +01:00
parent 5d63b0aa93
commit 1fe8fb8c20
2 changed files with 39 additions and 0 deletions

View file

@ -421,6 +421,7 @@
from .vevo import VevoIE from .vevo import VevoIE
from .vgtv import VGTVIE from .vgtv import VGTVIE
from .vh1 import VH1IE from .vh1 import VH1IE
from .vice import ViceIE
from .viddler import ViddlerIE from .viddler import ViddlerIE
from .videobam import VideoBamIE from .videobam import VideoBamIE
from .videodetective import VideoDetectiveIE from .videodetective import VideoDetectiveIE

View file

@ -0,0 +1,38 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..utils import ExtractorError
class ViceIE(InfoExtractor):
_VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)'
_TEST = {
'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
'info_dict': {
'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
'ext': 'mp4',
'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
},
'params': {
# Requires ffmpeg (m3u8 manifest)
'skip_download': True,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
try:
embed_code = self._search_regex(
r'embedCode=([^&\'"]+)', webpage,
'ooyala embed code')
ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
print(ooyala_url)
except ExtractorError:
raise ExtractorError('The page doesn\'t contain a video', expected=True)
return self.url_result(ooyala_url, ie='Ooyala')