Workaround for regex engine limitation

This commit is contained in:
AGSPhoenix 2014-04-04 15:25:28 -04:00
parent bb799e811b
commit 6d0d573eca
1 changed files with 6 additions and 4 deletions

View File

@ -9,7 +9,7 @@ from ..utils import (
class TeamcocoIE(InfoExtractor): class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>\d*)?/?(?P<url_title>.*)' _VALID_URL = r'http://teamcoco\.com/video/([^/]*)?/?(.*)'
_TESTS = [ _TESTS = [
{ {
'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant', 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
@ -35,11 +35,13 @@ class TeamcocoIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
raise ExtractorError('Invalid URL: %s' % url) raise ExtractorError('Invalid URL: %s' % url)
url_title = mobj.group('url_title') url_title = mobj.group(2)
if url_title == '':
url_title = mobj.group(1)
webpage = self._download_webpage(url, url_title) webpage = self._download_webpage(url, url_title)
video_id = mobj.group("video_id") video_id = mobj.group(1)
if video_id == '': if mobj.group(2) == '':
video_id = self._html_search_regex( video_id = self._html_search_regex(
r'<article class="video" data-id="(\d+?)"', r'<article class="video" data-id="(\d+?)"',
webpage, 'video id') webpage, 'video id')