X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=499d9b1aed8c3d4177539179f515d8abdcf981d8;hb=3210735c499e6a7d0b4df4b8120e17bd7ba8927b;hp=0b5d76bdbd89f393340afdec9e0a79b86df615c8;hpb=65dc7d027278d93b4a760dcbf6d19067fb8ff85d;p=youtube-dl.git

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 0b5d76bdb..499d9b1ae 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -1232,7 +1232,7 @@ class YoutubeSearchIE(InfoExtractor):
 		InfoExtractor.__init__(self, downloader)
 
 	def report_download_page(self, query, pagenum):
-		"""Report attempt to download playlist page with given number."""
+		"""Report attempt to download search page with given number."""
 		query = query.decode(preferredencoding())
 		self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
 
@@ -1468,8 +1468,8 @@ class YoutubePlaylistIE(InfoExtractor):
 
 	_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
 	_TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
-	_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&list=PL%s&'
-	_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+	_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;list=(PL)?%s&'
+	_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
 	IE_NAME = u'youtube:playlist'
 
 	def __init__(self, downloader=None):
@@ -2193,12 +2193,14 @@ class EscapistIE(InfoExtractor):
 
 		self.report_extraction(showName)
 		try:
-			webPageBytes = urllib2.urlopen(url).read()
+			webPage = urllib2.urlopen(url)
+			webPageBytes = webPage.read()
+			m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
+			webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
 			self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
 			return
 
-		webPage = webPageBytes.decode('utf-8')
 		descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
 		description = unescapeHTML(descMatch.group(1))
 		imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)