Merge pull request #1 from rg3/master

t1
This commit is contained in:
siddht1 2015-11-17 21:09:36 +05:30
commit 07e4fea6e6
4 changed files with 11 additions and 13 deletions

View File

@ -210,8 +210,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unescapeHTML('%20;'), '%20;')
self.assertEqual(unescapeHTML('/'), '/')
self.assertEqual(unescapeHTML('/'), '/')
self.assertEqual(
unescapeHTML('é'), 'é')
self.assertEqual(unescapeHTML('é'), 'é')
self.assertEqual(unescapeHTML('�'), '�')
def test_daterange(self):
_20century = DateRange("19000101", "20000101")

View File

@ -40,7 +40,7 @@ class NetEaseMusicBaseIE(InfoExtractor):
if not details:
continue
formats.append({
'url': 'http://m1.music.126.net/%s/%s.%s' %
'url': 'http://m5.music.126.net/%s/%s.%s' %
(cls._encrypt(details['dfsId']), details['dfsId'],
details['extension']),
'ext': details.get('extension'),

View File

@ -6,7 +6,7 @@ import re
import time
from .common import InfoExtractor
from ..compat import compat_urllib_request, compat_urlparse
from ..compat import compat_urllib_request
from ..utils import (
ExtractorError,
float_or_none,
@ -107,15 +107,9 @@ class RTVEALaCartaIE(InfoExtractor):
png = self._download_webpage(png_request, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
if not video_url.endswith('.f4m'):
auth_url = video_url.replace(
video_url = video_url.replace(
'resources/', 'auth/resources/'
).replace('.net.rtve', '.multimedia.cdn.rtve')
video_path = self._download_webpage(
auth_url, video_id, 'Getting video url')
# Use mvod1.akcdn instead of flash.akamaihd.multimedia.cdn to get
# the right Content-Length header and the mp4 format
video_url = compat_urlparse.urljoin(
'http://mvod1.akcdn.rtve.es/', video_path)
subtitles = None
if info.get('sbtFile') is not None:

View File

@ -396,10 +396,14 @@ def _htmlentity_transform(entity):
numstr = '0%s' % numstr
else:
base = 10
return compat_chr(int(numstr, base))
# See https://github.com/rg3/youtube-dl/issues/7518
try:
return compat_chr(int(numstr, base))
except ValueError:
pass
# Unknown entity in name, return its literal representation
return ('&%s;' % entity)
return '&%s;' % entity
def unescapeHTML(s):