aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/collegehumor.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-24 14:59:19 +0100
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-24 14:59:19 +0100
commit267ed0c5d3547c68f1d34203c2ae4b0d826a29d9 (patch)
treedc86b8beea51b1e445280992ec2db99ed128b016 /youtube_dl/extractor/collegehumor.py
parentf459d17018812dc896324f8208cdfe2ada04ea50 (diff)
downloadyoutube-dl-267ed0c5d3547c68f1d34203c2ae4b0d826a29d9.tar.xz
[collegehumor] Encode the xml before calling xml.etree.ElementTree.fromstring (fixes #1822)
Uses a new helper method in InfoExtractor: _download_xml
Diffstat (limited to 'youtube_dl/extractor/collegehumor.py')
-rw-r--r--youtube_dl/extractor/collegehumor.py7
1 files changed, 2 insertions, 5 deletions
diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py
index 0c29acfb1..b27c1dfc5 100644
--- a/youtube_dl/extractor/collegehumor.py
+++ b/youtube_dl/extractor/collegehumor.py
@@ -1,5 +1,4 @@
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
@@ -46,11 +45,10 @@ class CollegeHumorIE(InfoExtractor):
self.report_extraction(video_id)
xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
- metaXml = self._download_webpage(xmlUrl, video_id,
+ mdoc = self._download_xml(xmlUrl, video_id,
u'Downloading info XML',
u'Unable to download video info XML')
- mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
videoNode = mdoc.findall('./video')[0]
youtubeIdNode = videoNode.find('./youtubeID')
@@ -65,11 +63,10 @@ class CollegeHumorIE(InfoExtractor):
if next_url.endswith(u'manifest.f4m'):
manifest_url = next_url + '?hdcore=2.10.3'
- manifestXml = self._download_webpage(manifest_url, video_id,
+ adoc = self._download_xml(manifest_url, video_id,
u'Downloading XML manifest',
u'Unable to download video info XML')
- adoc = xml.etree.ElementTree.fromstring(manifestXml)
try:
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError: