Add an extractor for spike.com (#2072)

Added a generic _real_extract to MTVServicesInfoExtractor
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-01-21 20:54:47 +01:00
parent e4f320a4d0
commit 8d9453b9e8
3 changed files with 33 additions and 0 deletions

View File

@ -171,6 +171,7 @@ from .southparkstudios import (
from .space import SpaceIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE
from .spike import SpikeIE
from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE
from .steam import SteamIE

View File

@ -7,6 +7,8 @@ from ..utils import (
compat_urllib_parse,
ExtractorError,
fix_xml_ampersands,
url_basename,
RegexNotFoundError,
)
def _media_xml_tag(tag):
@ -89,6 +91,17 @@ class MTVServicesInfoExtractor(InfoExtractor):
'Downloading info', transform_source=fix_xml_ampersands)
return [self._get_video_info(item) for item in idoc.findall('.//item')]
def _real_extract(self, url):
title = url_basename(url)
webpage = self._download_webpage(url, title)
try:
# the url is in the format http://media.mtvnservices.com/fb/{mgid}.swf
fb_url = self._og_search_video_url(webpage)
mgid = url_basename(fb_url).rpartition('.')[0]
except RegexNotFoundError:
mgid = self._search_regex(r'data-mgid="(.*?)"', webpage, u'mgid')
return self._get_videos_info(mgid)
class MTVIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)^https?://

View File

@ -0,0 +1,19 @@
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
class SpikeIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://www\.spike\.com/(video-clips|episodes)/.+'
_TEST = {
'url': 'http://www.spike.com/video-clips/lhtu8m/auction-hunters-can-allen-ride-a-hundred-year-old-motorcycle',
'md5': '1a9265f32b0c375793d6c4ce45255256',
'info_dict': {
'id': 'b9c8221a-4e50-479a-b86d-3333323e38ba',
'ext': 'mp4',
'title': 'Can Allen Ride A Hundred Year-Old Motorcycle?',
'description': 'md5:fbed7e82ed5fad493615b3094a9499cb',
},
}
_FEED_URL = 'http://www.spike.com/feeds/mrss/'