[spike] Fix full episodes extraction

This commit is contained in:
Mark Lee 2016-11-29 08:06:01 -08:00 committed by Sergey M
parent cc61fc3934
commit 6303fc8204
2 changed files with 23 additions and 2 deletions

View file

@ -13,6 +13,7 @@
fix_xml_ampersands,
float_or_none,
HEADRequest,
NO_DEFAULT,
RegexNotFoundError,
sanitized_Request,
strip_or_none,
@ -201,7 +202,7 @@ def _get_videos_info_from_url(self, url, video_id):
[self._get_video_info(item) for item in idoc.findall('.//item')],
playlist_title=title, playlist_description=description)
def _extract_mgid(self, webpage):
def _extract_mgid(self, webpage, default=NO_DEFAULT):
try:
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
# or http://media.mtvnservices.com/{mgid}
@ -221,7 +222,7 @@ def _extract_mgid(self, webpage):
sm4_embed = self._html_search_meta(
'sm4:video:embed', webpage, 'sm4 embed', default='')
mgid = self._search_regex(
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid')
r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=default)
return mgid
def _real_extract(self, url):

View file

@ -1,5 +1,7 @@
from __future__ import unicode_literals
import re
from .mtv import MTVServicesInfoExtractor
@ -16,6 +18,15 @@ class SpikeIE(MTVServicesInfoExtractor):
'timestamp': 1388120400,
'upload_date': '20131227',
},
}, {
'url': 'http://www.spike.com/full-episodes/j830qm/lip-sync-battle-joel-mchale-vs-jim-rash-season-2-ep-209',
'md5': 'b25c6f16418aefb9ad5a6cae2559321f',
'info_dict': {
'id': '37ace3a8-1df6-48be-85b8-38df8229e241',
'ext': 'mp4',
'title': 'Lip Sync Battle|April 28, 2016|2|209|Joel McHale Vs. Jim Rash|Act 1',
'description': 'md5:a739ca8f978a7802f67f8016d27ce114',
},
}, {
'url': 'http://www.spike.com/video-clips/lhtu8m/',
'only_matching': True,
@ -32,3 +43,12 @@ class SpikeIE(MTVServicesInfoExtractor):
_FEED_URL = 'http://www.spike.com/feeds/mrss/'
_MOBILE_TEMPLATE = 'http://m.spike.com/videos/video.rbml?id=%s'
_CUSTOM_URL_REGEX = re.compile(r'spikenetworkapp://([^/]+/[-a-fA-F0-9]+)')
def _extract_mgid(self, webpage):
mgid = super(SpikeIE, self)._extract_mgid(webpage, default=None)
if mgid is None:
url_parts = self._search_regex(self._CUSTOM_URL_REGEX, webpage, 'episode_id')
video_type, episode_id = url_parts.split('/', 1)
mgid = 'mgid:arc:{0}:spike.com:{1}'.format(video_type, episode_id)
return mgid