[imdb] Simplify

This commit is contained in:
Philipp Hagemeister 2014-11-04 23:26:23 +01:00
parent 12ea2f30cf
commit 11fba1751d

View file

@ -6,7 +6,6 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urlparse, compat_urlparse,
get_element_by_attribute,
) )
@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id) webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
descr = get_element_by_attribute('itemprop', 'description', webpage) descr = self._html_search_regex(
r'(?s)<span itemprop="description">(.*?)</span>',
webpage, 'description', fatal=False)
available_formats = re.findall( available_formats = re.findall(
r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage, r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
flags=re.MULTILINE) flags=re.MULTILINE)
@ -73,9 +73,7 @@ class ImdbListIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) list_id = self._match_id(url)
list_id = mobj.group('id')
webpage = self._download_webpage(url, list_id) webpage = self._download_webpage(url, list_id)
entries = [ entries = [
self.url_result('http://www.imdb.com' + m, 'Imdb') self.url_result('http://www.imdb.com' + m, 'Imdb')