[extractor/generic] Use compat_urllib_parse_unquote

This commit is contained in:
Sergey M․ 2015-07-17 23:39:32 +06:00
parent 1f80e360fc
commit f7e6f7fa23

View file

@ -8,7 +8,6 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from .youtube import YoutubeIE from .youtube import YoutubeIE
from ..compat import ( from ..compat import (
compat_urllib_parse,
compat_urllib_parse_unquote, compat_urllib_parse_unquote,
compat_urllib_request, compat_urllib_request,
compat_urlparse, compat_urlparse,
@ -1369,7 +1368,7 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url')) return self.url_result(mobj.group('url'))
mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage) mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
if mobj is not None: if mobj is not None:
return self.url_result(compat_urllib_parse.unquote(mobj.group('url'))) return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
# Look for funnyordie embed # Look for funnyordie embed
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage) matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
@ -1682,7 +1681,7 @@ class GenericIE(InfoExtractor):
entries = [] entries = []
for video_url in found: for video_url in found:
video_url = compat_urlparse.urljoin(url, video_url) video_url = compat_urlparse.urljoin(url, video_url)
video_id = compat_urllib_parse.unquote(os.path.basename(video_url)) video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
# Sometimes, jwplayer extraction will result in a YouTube URL # Sometimes, jwplayer extraction will result in a YouTube URL
if YoutubeIE.suitable(video_url): if YoutubeIE.suitable(video_url):