aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2015-10-26 16:41:24 +0100
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2015-10-26 16:41:24 +0100
commitf78546272cf7c4b10c8003870728ab69bec982fc (patch)
tree35449b6fd8c220411a30403396ef705d149650a8 /youtube_dl/extractor
parent387db16a789fea25795433538d80513c18d0f699 (diff)
[compat] compat_etree_fromstring: also decode the text attribute
Deletes parse_xml from utils, because it also does it.
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/ard.py4
-rw-r--r--youtube_dl/extractor/generic.py4
2 files changed, 4 insertions, 4 deletions
diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py
index 6f465789b..73be6d204 100644
--- a/youtube_dl/extractor/ard.py
+++ b/youtube_dl/extractor/ard.py
@@ -14,8 +14,8 @@ from ..utils import (
parse_duration,
unified_strdate,
xpath_text,
- parse_xml,
)
+from ..compat import compat_etree_fromstring
class ARDMediathekIE(InfoExtractor):
@@ -161,7 +161,7 @@ class ARDMediathekIE(InfoExtractor):
raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
- doc = parse_xml(webpage)
+ doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index ca5fbafb2..1de96b268 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -9,6 +9,7 @@ import sys
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
+ compat_etree_fromstring,
compat_urllib_parse_unquote,
compat_urllib_request,
compat_urlparse,
@@ -21,7 +22,6 @@ from ..utils import (
HEADRequest,
is_html,
orderedSet,
- parse_xml,
smuggle_url,
unescapeHTML,
unified_strdate,
@@ -1237,7 +1237,7 @@ class GenericIE(InfoExtractor):
# Is it an RSS feed, a SMIL file or a XSPF playlist?
try:
- doc = parse_xml(webpage)
+ doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):