diff options
Diffstat (limited to 'youtube-dl')
| -rwxr-xr-x | youtube-dl | 19 |
1 files changed, 13 insertions, 6 deletions
diff --git a/youtube-dl b/youtube-dl index 2522e0233..818a3a73a 100755 --- a/youtube-dl +++ b/youtube-dl @@ -1,7 +1,7 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- -__author__ = ( +__authors__ = ( 'Ricardo Garcia Gonzalez', 'Danny Colligan', 'Benjamin Johnson', @@ -18,7 +18,7 @@ __author__ = ( ) __license__ = 'Public Domain' -__version__ = '2011.12.18' +__version__ = '2012.01.05' UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' @@ -290,6 +290,15 @@ def _orderedSet(iterable): res.append(el) return res +def _unescapeHTML(s): + """ + @param s a string (of type unicode) + """ + assert type(s) == type(u'') + + htmlParser = HTMLParser.HTMLParser() + return htmlParser.unescape(s) + class DownloadError(Exception): """Download Error exception. @@ -1590,8 +1599,6 @@ class DailymotionIE(InfoExtractor): self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id) def _real_extract(self, url): - htmlParser = HTMLParser.HTMLParser() - # Extract id and simplified title from URL mobj = re.match(self._VALID_URL, url) if mobj is None: @@ -1635,7 +1642,7 @@ class DailymotionIE(InfoExtractor): if mobj is None: self._downloader.trouble(u'ERROR: unable to extract title') return - video_title = htmlParser.unescape(mobj.group('title')).decode('utf-8') + video_title = _unescapeHTML(mobj.group('title').decode('utf-8')) video_title = sanitize_title(video_title) simple_title = _simplify_title(video_title) @@ -3151,7 +3158,7 @@ class ComedyCentralIE(InfoExtractor): return epTitle = mobj.group('episode') - mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html) + mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html) if len(mMovieParams) == 0: self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) return |