X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=35ba6cc5c9d59752621178f568473f49a7357156;hb=df4bad32454164552716da994f9a578178d918fd;hp=be6b0cb085e434985a1f7e65a017f62d24e5b7ff;hpb=0b8c922da91fb7238ea15434d6a4792da84015bf;p=youtube-dl

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index be6b0cb08..35ba6cc5c 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -13,6 +13,8 @@ import urllib
 import urllib2
 import email.utils
 import xml.etree.ElementTree
+import random
+import math
 from urlparse import parse_qs
 
 try:
@@ -39,7 +41,6 @@ class InfoExtractor(object):
 	url:		Final video URL.
 	uploader:	Nickname of the video uploader.
 	title:		Literal title.
-	stitle:		Simplified title.
 	ext:		Video filename extension.
 	format:		Video format.
 	player_url:	SWF Player URL (may be None).
@@ -96,7 +97,26 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
 	"""Information extractor for youtube.com."""
 
-	_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+	_VALID_URL = r"""^
+	                 (
+	                     (?:https?://)?                                       # http(s):// (optional)
+	                     (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
+	                     	tube\.majestyc\.net/)                             # the various hostnames, with wildcard subdomains
+	                     (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
+	                     (?!view_play_list|my_playlists|artist|playlist)      # ignore playlist URLs
+	                     (?:                                                  # the various things that can precede the ID:
+	                         (?:(?:v|embed|e)/)                               # v/ or embed/ or e/
+	                         |(?:                                             # or the v= param in all its forms
+	                             (?:watch(?:_popup)?(?:\.php)?)?              # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
+	                             (?:\?|\#!?)                                  # the params delimiter ? or # or #!
+	                             (?:.+&)?                                     # any other preceding param (like /?s=tuff&v=xxxx)
+	                             v=
+	                         )
+	                     )?                                                   # optional -> youtube.com/xxxx is OK
+	                 )?                                                       # all until now is optional -> you can pass the naked ID
+	                 ([0-9A-Za-z_-]+)                                         # here is it! the YouTube video ID
+	                 (?(1).+)?                                                # if we found the ID, everything can follow
+	                 $"""
 	_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
 	_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
 	_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@@ -135,6 +155,10 @@ class YoutubeIE(InfoExtractor):
 	}	
 	IE_NAME = u'youtube'
 
+	def suitable(self, url):
+		"""Receives a URL and returns True if suitable for this IE."""
+		return re.match(self._VALID_URL, url, re.VERBOSE) is not None
+
 	def report_lang(self):
 		"""Report attempt to set language."""
 		self._downloader.to_screen(u'[youtube] Setting language')
@@ -182,16 +206,16 @@ class YoutubeIE(InfoExtractor):
 			start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
 			end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
 			caption = unescapeHTML(caption)
-			caption = unescapeHTML(caption) # double cycle, inentional
-			srt += str(n) + '\n'
+			caption = unescapeHTML(caption) # double cycle, intentional
+			srt += str(n+1) + '\n'
 			srt += start + ' --> ' + end + '\n'
 			srt += caption + '\n\n'
 		return srt
 
 	def _print_formats(self, formats):
-		print 'Available formats:'
+		print('Available formats:')
 		for x in formats:
-			print '%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???'))
+			print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
 
 	def _real_initialize(self):
 		if self._downloader is None:
@@ -214,7 +238,7 @@ class YoutubeIE(InfoExtractor):
 				else:
 					raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
 			except (IOError, netrc.NetrcParseError), err:
-				self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+				self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
 				return
 
 		# Set language
@@ -223,7 +247,7 @@ class YoutubeIE(InfoExtractor):
 			self.report_lang()
 			urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+			self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_str(err))
 			return
 
 		# No authentication to be performed
@@ -246,7 +270,7 @@ class YoutubeIE(InfoExtractor):
 				self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
 				return
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+			self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
 			return
 
 		# Confirm age
@@ -259,7 +283,7 @@ class YoutubeIE(InfoExtractor):
 			self.report_age_confirmation()
 			age_results = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
 			return
 
 	def _real_extract(self, url):
@@ -269,7 +293,7 @@ class YoutubeIE(InfoExtractor):
 			url = 'http://www.youtube.com/' + urllib.unquote(mobj.group(1)).lstrip('/')
 
 		# Extract video id from URL
-		mobj = re.match(self._VALID_URL, url)
+		mobj = re.match(self._VALID_URL, url, re.VERBOSE)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
 			return
@@ -281,7 +305,7 @@ class YoutubeIE(InfoExtractor):
 		try:
 			video_webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
 			return
 
 		# Attempt to extract SWF player URL
@@ -303,7 +327,7 @@ class YoutubeIE(InfoExtractor):
 				if 'token' in video_info:
 					break
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
 				return
 		if 'token' not in video_info:
 			if 'reason' in video_info:
@@ -312,6 +336,11 @@ class YoutubeIE(InfoExtractor):
 				self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
 			return
 
+		# Check for "rental" videos
+		if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
+			self._downloader.trouble(u'ERROR: "rental" videos not supported')
+			return
+
 		# Start extracting information
 		self.report_information_extraction(video_id)
 
@@ -327,10 +356,6 @@ class YoutubeIE(InfoExtractor):
 			return
 		video_title = urllib.unquote_plus(video_info['title'][0])
 		video_title = video_title.decode('utf-8')
-		video_title = sanitize_title(video_title)
-
-		# simplified title
-		simple_title = simplify_title(video_title)
 
 		# thumbnail image
 		if 'thumbnail_url' not in video_info:
@@ -365,8 +390,9 @@ class YoutubeIE(InfoExtractor):
 				try:
 					srt_list = urllib2.urlopen(request).read()
 				except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-					raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
-				srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list)
+					raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err))
+				srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
+				srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
 				if not srt_lang_list:
 					raise Trouble(u'WARNING: video has no closed captions')
 				if self._downloader.params.get('subtitleslang', False):
@@ -374,18 +400,26 @@ class YoutubeIE(InfoExtractor):
 				elif 'en' in srt_lang_list:
 					srt_lang = 'en'
 				else:
-					srt_lang = srt_lang_list[0]
+					srt_lang = srt_lang_list.keys()[0]
 				if not srt_lang in srt_lang_list:
 					raise Trouble(u'WARNING: no closed captions found in the specified language')
-				request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id))
+				request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
 				try:
 					srt_xml = urllib2.urlopen(request).read()
 				except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-					raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
+					raise Trouble(u'WARNING: unable to download video subtitles: %s' % compat_str(err))
+				if not srt_xml:
+					raise Trouble(u'WARNING: unable to download video subtitles')
 				video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
 			except Trouble as trouble:
 				self._downloader.trouble(trouble[0])
 
+		if 'length_seconds' not in video_info:
+			self._downloader.trouble(u'WARNING: unable to extract video duration')
+			video_duration = ''
+		else:
+			video_duration = urllib.unquote_plus(video_info['length_seconds'][0])
+
 		# token
 		video_token = urllib.unquote_plus(video_info['token'][0])
 
@@ -399,7 +433,7 @@ class YoutubeIE(InfoExtractor):
 			url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
 			url_data = [parse_qs(uds) for uds in url_data_strs]
 			url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data)
-			url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
+			url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
 
 			format_limit = self._downloader.params.get('format_limit', None)
 			available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
@@ -447,13 +481,13 @@ class YoutubeIE(InfoExtractor):
 				'uploader':	video_uploader.decode('utf-8'),
 				'upload_date':	upload_date,
 				'title':	video_title,
-				'stitle':	simple_title,
 				'ext':		video_extension.decode('utf-8'),
 				'format':	(format_param is None and u'NA' or format_param.decode('utf-8')),
 				'thumbnail':	video_thumbnail.decode('utf-8'),
 				'description':	video_description,
 				'player_url':	player_url,
-				'subtitles':	video_subtitles
+				'subtitles':	video_subtitles,
+				'duration':		video_duration
 			})
 		return results
 
@@ -492,7 +526,7 @@ class MetacafeIE(InfoExtractor):
 			self.report_disclaimer()
 			disclaimer = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
 			return
 
 		# Confirm age
@@ -505,7 +539,7 @@ class MetacafeIE(InfoExtractor):
 			self.report_age_confirmation()
 			disclaimer = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
 			return
 
 	def _real_extract(self, url):
@@ -523,15 +557,13 @@ class MetacafeIE(InfoExtractor):
 			self._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
 			return
 
-		simple_title = mobj.group(2).decode('utf-8')
-
 		# Retrieve video webpage to extract further information
 		request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
 		try:
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract URL, uploader and title from webpage
@@ -570,9 +602,8 @@ class MetacafeIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: unable to extract title')
 			return
 		video_title = mobj.group(1).decode('utf-8')
-		video_title = sanitize_title(video_title)
 
-		mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
+		mobj = re.search(r'submitter=(.*?);', webpage)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
 			return
@@ -584,7 +615,6 @@ class MetacafeIE(InfoExtractor):
 			'uploader':	video_uploader.decode('utf-8'),
 			'upload_date':	u'NA',
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		video_extension.decode('utf-8'),
 			'format':	u'NA',
 			'player_url':	None,
@@ -594,7 +624,7 @@ class MetacafeIE(InfoExtractor):
 class DailymotionIE(InfoExtractor):
 	"""Information Extractor for Dailymotion"""
 
-	_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+	_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
 	IE_NAME = u'dailymotion'
 
 	def __init__(self, downloader=None):
@@ -615,9 +645,9 @@ class DailymotionIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
 			return
 
-		video_id = mobj.group(1)
+		video_id = mobj.group(1).split('_')[0].split('?')[0]
 
-		video_extension = 'flv'
+		video_extension = 'mp4'
 
 		# Retrieve video webpage to extract further information
 		request = urllib2.Request(url)
@@ -626,47 +656,64 @@ class DailymotionIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract URL, uploader and title from webpage
 		self.report_extraction(video_id)
-		mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]+?)\"\)', webpage)
+		mobj = re.search(r'\s*var flashvars = (.*)', webpage)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: unable to extract media URL')
 			return
-		sequence = urllib.unquote(mobj.group(1))
-		mobj = re.search(r',\"sdURL\"\:\"([^\"]+?)\",', sequence)
+		flashvars = urllib.unquote(mobj.group(1))
+
+		for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
+			if key in flashvars:
+				max_quality = key
+				self._downloader.to_screen(u'[dailymotion] Using %s' % key)
+				break
+		else:
+			self._downloader.trouble(u'ERROR: unable to extract video URL')
+			return
+
+		mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
 		if mobj is None:
-			self._downloader.trouble(u'ERROR: unable to extract media URL')
+			self._downloader.trouble(u'ERROR: unable to extract video URL')
 			return
-		mediaURL = urllib.unquote(mobj.group(1)).replace('\\', '')
 
-		# if needed add http://www.dailymotion.com/ if relative URL
+		video_url = urllib.unquote(mobj.group(1)).replace('\\/', '/')
 
-		video_url = mediaURL
+		# TODO: support choosing qualities
 
 		mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: unable to extract title')
 			return
 		video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
-		video_title = sanitize_title(video_title)
-		simple_title = simplify_title(video_title)
 
-		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
+		video_uploader = u'NA'
+		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
 		if mobj is None:
-			self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
-			return
-		video_uploader = mobj.group(1)
+			# lookin for official user
+			mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
+			if mobj_official is None:
+				self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+			else:
+				video_uploader = mobj_official.group(1)
+		else:
+			video_uploader = mobj.group(1)
+
+		video_upload_date = u'NA'
+		mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
+		if mobj is not None:
+			video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
 
 		return [{
 			'id':		video_id.decode('utf-8'),
 			'url':		video_url.decode('utf-8'),
 			'uploader':	video_uploader.decode('utf-8'),
-			'upload_date':	u'NA',
+			'upload_date':	video_upload_date,
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		video_extension.decode('utf-8'),
 			'format':	u'NA',
 			'player_url':	None,
@@ -707,7 +754,7 @@ class GoogleIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract URL, uploader, and title from webpage
@@ -730,8 +777,6 @@ class GoogleIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: unable to extract title')
 			return
 		video_title = mobj.group(1).decode('utf-8')
-		video_title = sanitize_title(video_title)
-		simple_title = simplify_title(video_title)
 
 		# Extract video description
 		mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
@@ -748,7 +793,7 @@ class GoogleIE(InfoExtractor):
 			try:
 				webpage = urllib2.urlopen(request).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 				return
 			mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
 			if mobj is None:
@@ -764,7 +809,6 @@ class GoogleIE(InfoExtractor):
 			'uploader':	u'NA',
 			'upload_date':	u'NA',
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		video_extension.decode('utf-8'),
 			'format':	u'NA',
 			'player_url':	None,
@@ -805,7 +849,7 @@ class PhotobucketIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract URL, uploader, and title from webpage
@@ -823,8 +867,6 @@ class PhotobucketIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: unable to extract title')
 			return
 		video_title = mobj.group(1).decode('utf-8')
-		video_title = sanitize_title(video_title)
-		simple_title = simplify_title(video_title)
 
 		video_uploader = mobj.group(2).decode('utf-8')
 
@@ -834,7 +876,6 @@ class PhotobucketIE(InfoExtractor):
 			'uploader':	video_uploader,
 			'upload_date':	u'NA',
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		video_extension.decode('utf-8'),
 			'format':	u'NA',
 			'player_url':	None,
@@ -878,7 +919,7 @@ class YahooIE(InfoExtractor):
 			try:
 				webpage = urllib2.urlopen(request).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 				return
 
 			mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
@@ -902,7 +943,7 @@ class YahooIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract uploader and title from webpage
@@ -912,7 +953,6 @@ class YahooIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: unable to extract video title')
 			return
 		video_title = mobj.group(1).decode('utf-8')
-		simple_title = simplify_title(video_title)
 
 		mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
 		if mobj is None:
@@ -961,7 +1001,7 @@ class YahooIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract media URL from playlist XML
@@ -978,7 +1018,6 @@ class YahooIE(InfoExtractor):
 			'uploader':	video_uploader,
 			'upload_date':	u'NA',
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		video_extension.decode('utf-8'),
 			'thumbnail':	video_thumbnail.decode('utf-8'),
 			'description':	video_description,
@@ -991,7 +1030,7 @@ class VimeoIE(InfoExtractor):
 	"""Information extractor for vimeo.com."""
 
 	# _VALID_URL matches Vimeo URLs
-	_VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
+	_VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
 	IE_NAME = u'vimeo'
 
 	def __init__(self, downloader=None):
@@ -1020,7 +1059,7 @@ class VimeoIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Now we begin extracting as much information as we can from what we
@@ -1038,7 +1077,6 @@ class VimeoIE(InfoExtractor):
 		
 		# Extract title
 		video_title = config["video"]["title"]
-		simple_title = simplify_title(video_title)
 
 		# Extract uploader
 		video_uploader = config["video"]["owner"]["name"]
@@ -1062,21 +1100,32 @@ class VimeoIE(InfoExtractor):
 		timestamp = config['request']['timestamp']
 
 		# Vimeo specific: extract video codec and quality information
+		# First consider quality, then codecs, then take everything
 		# TODO bind to format param
 		codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
-		for codec in codecs:
-			if codec[0] in config["video"]["files"]:
-				video_codec = codec[0]
-				video_extension = codec[1]
-				if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd'
-				else: quality = 'sd'
+		files = { 'hd': [], 'sd': [], 'other': []}
+		for codec_name, codec_extension in codecs:
+			if codec_name in config["video"]["files"]:
+				if 'hd' in config["video"]["files"][codec_name]:
+					files['hd'].append((codec_name, codec_extension, 'hd'))
+				elif 'sd' in config["video"]["files"][codec_name]:
+					files['sd'].append((codec_name, codec_extension, 'sd'))
+				else:
+					files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
+
+		for quality in ('hd', 'sd', 'other'):
+			if len(files[quality]) > 0:
+				video_quality = files[quality][0][2]
+				video_codec = files[quality][0][0]
+				video_extension = files[quality][0][1]
+				self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
 				break
 		else:
 			self._downloader.trouble(u'ERROR: no known codec found')
 			return
 
 		video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
-					%(video_id, sig, timestamp, quality, video_codec.upper())
+					%(video_id, sig, timestamp, video_quality, video_codec.upper())
 
 		return [{
 			'id':		video_id,
@@ -1084,7 +1133,6 @@ class VimeoIE(InfoExtractor):
 			'uploader':	video_uploader,
 			'upload_date':	video_upload_date,
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		video_extension,
 			'thumbnail':	video_thumbnail,
 			'description':	video_description,
@@ -1177,7 +1225,7 @@ class GenericIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 		except ValueError, err:
 			# since this is the last-resort InfoExtractor, if
@@ -1219,8 +1267,6 @@ class GenericIE(InfoExtractor):
 			self._downloader.trouble(u'ERROR: unable to extract title')
 			return
 		video_title = mobj.group(1).decode('utf-8')
-		video_title = sanitize_title(video_title)
-		simple_title = simplify_title(video_title)
 
 		# video uploader is domain name
 		mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
@@ -1235,7 +1281,6 @@ class GenericIE(InfoExtractor):
 			'uploader':	video_uploader,
 			'upload_date':	u'NA',
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		video_extension.decode('utf-8'),
 			'format':	u'NA',
 			'player_url':	None,
@@ -1253,7 +1298,7 @@ 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))
 
@@ -1301,7 +1346,7 @@ class YoutubeSearchIE(InfoExtractor):
 			try:
 				data = urllib2.urlopen(request).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download API page: %s' % str(err))
+				self._downloader.trouble(u'ERROR: unable to download API page: %s' % compat_str(err))
 				return
 			api_response = json.loads(data)['data']
 
@@ -1378,7 +1423,7 @@ class GoogleSearchIE(InfoExtractor):
 			try:
 				page = urllib2.urlopen(request).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
 				return
 
 			# Extract video identifiers
@@ -1461,7 +1506,7 @@ class YahooSearchIE(InfoExtractor):
 			try:
 				page = urllib2.urlopen(request).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
 				return
 
 			# Extract video identifiers
@@ -1487,10 +1532,10 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
 	"""Information Extractor for YouTube playlists."""
 
-	_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_-]+))?.*'
+	_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|EC)?|PL|EC)([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=(.+?)&amp;list=PL%s&'
-	_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
+	_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;([^&"]+&amp;)*list=.*?%s'
+	_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
 	IE_NAME = u'youtube:playlist'
 
 	def __init__(self, downloader=None):
@@ -1531,7 +1576,7 @@ class YoutubePlaylistIE(InfoExtractor):
 			try:
 				page = urllib2.urlopen(request).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
 				return
 
 			# Extract video identifiers
@@ -1557,6 +1602,56 @@ class YoutubePlaylistIE(InfoExtractor):
 		return
 
 
+class YoutubeChannelIE(InfoExtractor):
+	"""Information Extractor for YouTube channels."""
+
+	_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+	_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
+	_MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
+	IE_NAME = u'youtube:channel'
+
+	def report_download_page(self, channel_id, pagenum):
+		"""Report attempt to download channel page with given number."""
+		self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
+
+	def _real_extract(self, url):
+		# Extract channel id
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+			return
+
+		# Download channel pages
+		channel_id = mobj.group(1)
+		video_ids = []
+		pagenum = 1
+
+		while True:
+			self.report_download_page(channel_id, pagenum)
+			url = self._TEMPLATE_URL % (channel_id, pagenum)
+			request = urllib2.Request(url)
+			try:
+				page = urllib2.urlopen(request).read()
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+				return
+
+			# Extract video identifiers
+			ids_in_page = []
+			for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
+				if mobj.group(1) not in ids_in_page:
+					ids_in_page.append(mobj.group(1))
+			video_ids.extend(ids_in_page)
+
+			if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+				break
+			pagenum = pagenum + 1
+
+		for id in video_ids:
+			self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
+		return
+
+
 class YoutubeUserIE(InfoExtractor):
 	"""Information Extractor for YouTube users."""
 
@@ -1601,7 +1696,7 @@ class YoutubeUserIE(InfoExtractor):
 			try:
 				page = urllib2.urlopen(request).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
 				return
 
 			# Extract video identifiers
@@ -1640,6 +1735,98 @@ class YoutubeUserIE(InfoExtractor):
 			self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id])
 
 
+class BlipTVUserIE(InfoExtractor):
+	"""Information Extractor for blip.tv users."""
+
+	_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$'
+	_PAGE_SIZE = 12
+	IE_NAME = u'blip.tv:user'
+
+	def __init__(self, downloader=None):
+		InfoExtractor.__init__(self, downloader)
+
+	def report_download_page(self, username, pagenum):
+		"""Report attempt to download user page."""
+		self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' %
+				(self.IE_NAME, username, pagenum))
+
+	def _real_extract(self, url):
+		# Extract username
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+			return
+
+		username = mobj.group(1)
+
+		page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1'
+
+		request = urllib2.Request(url)
+
+		try:
+			page = urllib2.urlopen(request).read().decode('utf-8')
+			mobj = re.search(r'data-users-id="([^"]+)"', page)
+			page_base = page_base % mobj.group(1)
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
+			return
+
+
+		# Download video ids using BlipTV Ajax calls. Result size per
+		# query is limited (currently to 12 videos) so we need to query
+		# page by page until there are no video ids - it means we got
+		# all of them.
+
+		video_ids = []
+		pagenum = 1
+
+		while True:
+			self.report_download_page(username, pagenum)
+
+			request = urllib2.Request( page_base + "&page=" + str(pagenum) )
+
+			try:
+				page = urllib2.urlopen(request).read().decode('utf-8')
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+				return
+
+			# Extract video identifiers
+			ids_in_page = []
+
+			for mobj in re.finditer(r'href="/([^"]+)"', page):
+				if mobj.group(1) not in ids_in_page:
+					ids_in_page.append(unescapeHTML(mobj.group(1)))
+
+			video_ids.extend(ids_in_page)
+
+			# A little optimization - if current page is not
+			# "full", ie. does not contain PAGE_SIZE video ids then
+			# we can assume that this page is the last one - there
+			# are no more ids on further pages - no need to query
+			# again.
+
+			if len(ids_in_page) < self._PAGE_SIZE:
+				break
+
+			pagenum += 1
+
+		all_ids_count = len(video_ids)
+		playliststart = self._downloader.params.get('playliststart', 1) - 1
+		playlistend = self._downloader.params.get('playlistend', -1)
+
+		if playlistend == -1:
+			video_ids = video_ids[playliststart:]
+		else:
+			video_ids = video_ids[playliststart:playlistend]
+
+		self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" %
+				(self.IE_NAME, username, all_ids_count, len(video_ids)))
+
+		for video_id in video_ids:
+			self._downloader.download([u'http://blip.tv/'+video_id])
+
+
 class DepositFilesIE(InfoExtractor):
 	"""Information extractor for depositfiles.com"""
 
@@ -1669,7 +1856,7 @@ class DepositFilesIE(InfoExtractor):
 			self.report_download_webpage(file_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % compat_str(err))
 			return
 
 		# Search for the real file URL
@@ -1700,7 +1887,6 @@ class DepositFilesIE(InfoExtractor):
 			'uploader':	u'NA',
 			'upload_date':	u'NA',
 			'title':	file_title,
-			'stitle':	file_title,
 			'ext':		file_extension.decode('utf-8'),
 			'format':	u'NA',
 			'player_url':	None,
@@ -1787,7 +1973,7 @@ class FacebookIE(InfoExtractor):
 				else:
 					raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
 			except (IOError, netrc.NetrcParseError), err:
-				self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
+				self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
 				return
 
 		if useremail is None:
@@ -1807,7 +1993,7 @@ class FacebookIE(InfoExtractor):
 				self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
 				return
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
+			self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
 			return
 
 	def _real_extract(self, url):
@@ -1824,7 +2010,7 @@ class FacebookIE(InfoExtractor):
 			page = urllib2.urlopen(request)
 			video_webpage = page.read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
 			return
 
 		# Start extracting information
@@ -1845,9 +2031,6 @@ class FacebookIE(InfoExtractor):
 			return
 		video_title = video_info['title']
 		video_title = video_title.decode('utf-8')
-		video_title = sanitize_title(video_title)
-
-		simple_title = simplify_title(video_title)
 
 		# thumbnail image
 		if 'thumbnail' not in video_info:
@@ -1908,7 +2091,6 @@ class FacebookIE(InfoExtractor):
 				'uploader':	video_uploader.decode('utf-8'),
 				'upload_date':	upload_date,
 				'title':	video_title,
-				'stitle':	simple_title,
 				'ext':		video_extension.decode('utf-8'),
 				'format':	(format_param is None and u'NA' or format_param.decode('utf-8')),
 				'thumbnail':	video_thumbnail.decode('utf-8'),
@@ -1943,7 +2125,7 @@ class BlipTVIE(InfoExtractor):
 		else:
 			cchar = '?'
 		json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
-		request = urllib2.Request(json_url)
+		request = urllib2.Request(json_url.encode('utf-8'))
 		self.report_extraction(mobj.group(1))
 		info = None
 		try:
@@ -1958,18 +2140,17 @@ class BlipTVIE(InfoExtractor):
 					'id': title,
 					'url': url,
 					'title': title,
-					'stitle': simplify_title(title),
 					'ext': ext,
 					'urlhandle': urlh
 				}
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
 			return
 		if info is None: # Regular URL
 			try:
 				json_code = urlh.read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
+				self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % compat_str(err))
 				return
 
 			try:
@@ -1992,7 +2173,6 @@ class BlipTVIE(InfoExtractor):
 					'uploader': data['display_name'],
 					'upload_date': upload_date,
 					'title': data['title'],
-					'stitle': simplify_title(data['title']),
 					'ext': ext,
 					'format': data['media']['mimeType'],
 					'thumbnail': data['thumbnailUrl'],
@@ -2003,6 +2183,7 @@ class BlipTVIE(InfoExtractor):
 				self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
 				return
 
+		std_headers['User-Agent'] = 'iTunes/10.6.1'
 		return [info]
 
 
@@ -2037,7 +2218,7 @@ class MyVideoIE(InfoExtractor):
 			self.report_download_webpage(video_id)
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 
 		self.report_extraction(video_id)
@@ -2054,9 +2235,6 @@ class MyVideoIE(InfoExtractor):
 			return
 
 		video_title = mobj.group(1)
-		video_title = sanitize_title(video_title)
-
-		simple_title = simplify_title(video_title)
 
 		return [{
 			'id':		video_id,
@@ -2064,7 +2242,6 @@ class MyVideoIE(InfoExtractor):
 			'uploader':	u'NA',
 			'upload_date':  u'NA',
 			'title':	video_title,
-			'stitle':	simple_title,
 			'ext':		u'flv',
 			'format':	u'NA',
 			'player_url':	None,
@@ -2191,7 +2368,6 @@ class ComedyCentralIE(InfoExtractor):
 				'uploader': showId,
 				'upload_date': officialDate,
 				'title': effTitle,
-				'stitle': simplify_title(effTitle),
 				'ext': 'mp4',
 				'format': format,
 				'thumbnail': None,
@@ -2226,7 +2402,10 @@ class EscapistIE(InfoExtractor):
 
 		self.report_extraction(showName)
 		try:
-			webPage = 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
@@ -2265,7 +2444,6 @@ class EscapistIE(InfoExtractor):
 			'uploader': showName,
 			'upload_date': None,
 			'title': showName,
-			'stitle': simplify_title(showName),
 			'ext': 'flv',
 			'format': 'flv',
 			'thumbnail': imgUrl,
@@ -2302,7 +2480,7 @@ class CollegeHumorIE(InfoExtractor):
 		try:
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
 			return
 
 		m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
@@ -2321,7 +2499,7 @@ class CollegeHumorIE(InfoExtractor):
 		try:
 			metaXml = urllib2.urlopen(xmlUrl).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % compat_str(err))
 			return
 
 		mdoc = xml.etree.ElementTree.fromstring(metaXml)
@@ -2329,7 +2507,6 @@ class CollegeHumorIE(InfoExtractor):
 			videoNode = mdoc.findall('./video')[0]
 			info['description'] = videoNode.findall('./description')[0].text
 			info['title'] = videoNode.findall('./caption')[0].text
-			info['stitle'] = simplify_title(info['title'])
 			info['url'] = videoNode.findall('./file')[0].text
 			info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
 			info['ext'] = info['url'].rpartition('.')[2]
@@ -2368,7 +2545,7 @@ class XVideosIE(InfoExtractor):
 		try:
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
 			return
 
 		self.report_extraction(video_id)
@@ -2391,11 +2568,11 @@ class XVideosIE(InfoExtractor):
 
 
 		# Extract video thumbnail
-		mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
+		mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)', webpage)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
 			return
-		video_thumbnail = mobj.group(1).decode('utf-8')
+		video_thumbnail = mobj.group(0).decode('utf-8')
 
 		info = {
 			'id': video_id,
@@ -2403,7 +2580,6 @@ class XVideosIE(InfoExtractor):
 			'uploader': None,
 			'upload_date': None,
 			'title': video_title,
-			'stitle': simplify_title(video_title),
 			'ext': 'flv',
 			'format': 'flv',
 			'thumbnail': video_thumbnail,
@@ -2447,7 +2623,7 @@ class SoundcloudIE(InfoExtractor):
 		uploader = mobj.group(1).decode('utf-8')
 		# extract simple title (uploader + slug of song title)
 		slug_title =  mobj.group(2).decode('utf-8')
-		simple_title = uploader + '-' + slug_title
+		simple_title = uploader + u'-' + slug_title
 
 		self.report_webpage('%s/%s' % (uploader, slug_title))
 
@@ -2455,7 +2631,7 @@ class SoundcloudIE(InfoExtractor):
 		try:
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
 			return
 
 		self.report_extraction('%s/%s' % (uploader, slug_title))
@@ -2469,7 +2645,9 @@ class SoundcloudIE(InfoExtractor):
 		# extract unsimplified title
 		mobj = re.search('"title":"(.*?)",', webpage)
 		if mobj:
-			title = mobj.group(1)
+			title = mobj.group(1).decode('utf-8')
+		else:
+			title = simple_title
 
 		# construct media url (with uid/token)
 		mediaURL = "http://media.soundcloud.com/stream/%s?stream_token=%s"
@@ -2480,7 +2658,7 @@ class SoundcloudIE(InfoExtractor):
 		mobj = re.search('track-description-value"><p>(.*?)</p>', webpage)
 		if mobj:
 			description = mobj.group(1)
-		
+
 		# upload date
 		upload_date = None
 		mobj = re.search("pretty-date'>on ([\w]+ [\d]+, [\d]+ \d+:\d+)</abbr></h2>", webpage)
@@ -2488,7 +2666,7 @@ class SoundcloudIE(InfoExtractor):
 			try:
 				upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
 			except Exception, e:
-				print str(e)
+				self._downloader.to_stderr(compat_str(e))
 
 		# for soundcloud, a request to a cross domain is required for cookies
 		request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
@@ -2498,8 +2676,7 @@ class SoundcloudIE(InfoExtractor):
 			'url':		mediaURL,
 			'uploader':	uploader.decode('utf-8'),
 			'upload_date':  upload_date,
-			'title':	simple_title.decode('utf-8'),
-			'stitle':	simple_title.decode('utf-8'),
+			'title':	title,
 			'ext':		u'mp3',
 			'format':	u'NA',
 			'player_url':	None,
@@ -2533,7 +2710,7 @@ class InfoQIE(InfoExtractor):
 		try:
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
 			return
 
 		self.report_extraction(url)
@@ -2569,7 +2746,6 @@ class InfoQIE(InfoExtractor):
 			'uploader': None,
 			'upload_date': None,
 			'title': video_title,
-			'stitle': simplify_title(video_title),
 			'ext': extension,
 			'format': extension, # Extension is always(?) mp4, but seems to be flv
 			'thumbnail': None,
@@ -2620,15 +2796,15 @@ class MixcloudIE(InfoExtractor):
 		return None
 
 	def _print_formats(self, formats):
-		print 'Available formats:'
+		print('Available formats:')
 		for fmt in formats.keys():
 			for b in formats[fmt]:
 				try:
 					ext = formats[fmt][b][0]
-					print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
+					print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1]))
 				except TypeError: # we have no bitrate info
 					ext = formats[fmt][0]
-					print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
+					print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1]))
 					break
 
 	def _real_extract(self, url):
@@ -2648,7 +2824,7 @@ class MixcloudIE(InfoExtractor):
 			self.report_download_json(file_url)
 			jsonData = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % compat_str(err))
 			return
 
 		# parse JSON
@@ -2685,7 +2861,6 @@ class MixcloudIE(InfoExtractor):
 			'uploader':	uploader.decode('utf-8'),
 			'upload_date': u'NA',
 			'title': json_data['name'],
-			'stitle': simplify_title(json_data['name']),
 			'ext': file_url.split('.')[-1].decode('utf-8'),
 			'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
 			'thumbnail': json_data['thumbnail_url'],
@@ -2717,7 +2892,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
 			course = mobj.group('course')
 			video = mobj.group('video')
 			info = {
-				'id': simplify_title(course + '_' + video),
+				'id': course + '_' + video,
 			}
 
 			self.report_extraction(info['id'])
@@ -2735,14 +2910,13 @@ class StanfordOpenClassroomIE(InfoExtractor):
 			except IndexError:
 				self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
 				return
-			info['stitle'] = simplify_title(info['title'])
 			info['ext'] = info['url'].rpartition('.')[2]
 			info['format'] = info['ext']
 			return [info]
 		elif mobj.group('course'): # A course page
 			course = mobj.group('course')
 			info = {
-				'id': simplify_title(course),
+				'id': course,
 				'type': 'playlist',
 			}
 
@@ -2758,7 +2932,6 @@ class StanfordOpenClassroomIE(InfoExtractor):
 				info['title'] = unescapeHTML(m.group(1))
 			else:
 				info['title'] = info['id']
-			info['stitle'] = simplify_title(info['title'])
 
 			m = re.search('<description>([^<]+)</description>', coursepage)
 			if m:
@@ -2792,7 +2965,6 @@ class StanfordOpenClassroomIE(InfoExtractor):
 				return
 
 			info['title'] = info['id']
-			info['stitle'] = simplify_title(info['title'])
 
 			links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
 			info['list'] = [
@@ -2836,7 +3008,7 @@ class MTVIE(InfoExtractor):
 		try:
 			webpage = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
 			return
 
 		mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
@@ -2869,7 +3041,7 @@ class MTVIE(InfoExtractor):
 		try:
 			metadataXml = urllib2.urlopen(request).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % compat_str(err))
 			return
 
 		mdoc = xml.etree.ElementTree.fromstring(metadataXml)
@@ -2891,9 +3063,319 @@ class MTVIE(InfoExtractor):
 			'url': video_url,
 			'uploader': performer,
 			'title': video_title,
-			'stitle': simplify_title(video_title),
 			'ext': ext,
 			'format': format,
 		}
 
 		return [info]
+
+
+class YoukuIE(InfoExtractor):
+
+	_VALID_URL =  r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
+	IE_NAME = u'Youku'
+
+	def __init__(self, downloader=None):
+		InfoExtractor.__init__(self, downloader)
+
+	def report_download_webpage(self, file_id):
+		"""Report webpage download."""
+		self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id)
+
+	def report_extraction(self, file_id):
+		"""Report information extraction."""
+		self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id)
+
+	def _gen_sid(self):
+		nowTime = int(time.time() * 1000)
+		random1 = random.randint(1000,1998)
+		random2 = random.randint(1000,9999)
+
+		return "%d%d%d" %(nowTime,random1,random2)
+
+	def _get_file_ID_mix_string(self, seed):
+		mixed = []
+		source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
+		seed = float(seed)
+		for i in range(len(source)):
+			seed  =  (seed * 211 + 30031 ) % 65536
+			index  =  math.floor(seed / 65536 * len(source) )
+			mixed.append(source[int(index)])
+			source.remove(source[int(index)])
+		#return ''.join(mixed)
+		return mixed
+
+	def _get_file_id(self, fileId, seed):
+		mixed = self._get_file_ID_mix_string(seed)
+		ids = fileId.split('*')
+		realId = []
+		for ch in ids:
+			if ch:
+				realId.append(mixed[int(ch)])
+		return ''.join(realId)
+
+	def _real_extract(self, url):
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+			return
+		video_id = mobj.group('ID')
+
+		info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
+
+		request = urllib2.Request(info_url, None, std_headers)
+		try:
+			self.report_download_webpage(video_id)
+			jsondata = urllib2.urlopen(request).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error) as err:
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+			return
+
+		self.report_extraction(video_id)
+		try:
+			config = json.loads(jsondata)
+
+			video_title =  config['data'][0]['title']
+			seed = config['data'][0]['seed']
+
+			format = self._downloader.params.get('format', None)
+			supported_format = config['data'][0]['streamfileids'].keys()
+
+			if format is None or format == 'best':
+				if 'hd2' in supported_format:
+					format = 'hd2'
+				else:
+					format = 'flv'
+				ext = u'flv'
+			elif format == 'worst':
+				format = 'mp4'
+				ext = u'mp4'
+			else:
+				format = 'flv'
+				ext = u'flv'
+
+
+			fileid = config['data'][0]['streamfileids'][format]
+			seg_number = len(config['data'][0]['segs'][format])
+
+			keys=[]
+			for i in xrange(seg_number):
+				keys.append(config['data'][0]['segs'][format][i]['k'])
+
+			#TODO check error
+			#youku only could be viewed from mainland china
+		except:
+			self._downloader.trouble(u'ERROR: unable to extract info section')
+			return
+
+		files_info=[]
+		sid = self._gen_sid()
+		fileid = self._get_file_id(fileid, seed)
+
+		#column 8,9 of fileid represent the segment number
+		#fileid[7:9] should be changed
+		for index, key in enumerate(keys):
+
+			temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
+			download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
+
+			info = {
+				'id': '%s_part%02d' % (video_id, index),
+				'url': download_url,
+				'uploader': None,
+				'title': video_title,
+				'ext': ext,
+				'format': u'NA'
+			}
+			files_info.append(info)
+
+		return files_info
+
+
+class XNXXIE(InfoExtractor):
+	"""Information extractor for xnxx.com"""
+
+	_VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)'
+	IE_NAME = u'xnxx'
+	VIDEO_URL_RE = r'flv_url=(.*?)&amp;'
+	VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
+	VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
+
+	def report_webpage(self, video_id):
+		"""Report information extraction"""
+		self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
+
+	def report_extraction(self, video_id):
+		"""Report information extraction"""
+		self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+	def _real_extract(self, url):
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+			return
+		video_id = mobj.group(1).decode('utf-8')
+
+		self.report_webpage(video_id)
+
+		# Get webpage content
+		try:
+			webpage = urllib2.urlopen(url).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
+			return
+
+		result = re.search(self.VIDEO_URL_RE, webpage)
+		if result is None:
+			self._downloader.trouble(u'ERROR: unable to extract video url')
+			return
+		video_url = urllib.unquote(result.group(1).decode('utf-8'))
+
+		result = re.search(self.VIDEO_TITLE_RE, webpage)
+		if result is None:
+			self._downloader.trouble(u'ERROR: unable to extract video title')
+			return
+		video_title = result.group(1).decode('utf-8')
+
+		result = re.search(self.VIDEO_THUMB_RE, webpage)
+		if result is None:
+			self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
+			return
+		video_thumbnail = result.group(1).decode('utf-8')
+
+		info = {'id': video_id,
+				'url': video_url,
+				'uploader': None,
+				'upload_date': None,
+				'title': video_title,
+				'ext': 'flv',
+				'format': 'flv',
+				'thumbnail': video_thumbnail,
+				'description': None,
+				'player_url': None}
+
+		return [info]
+
+
+class GooglePlusIE(InfoExtractor):
+	"""Information extractor for plus.google.com."""
+
+	_VALID_URL = r'(?:https://)?plus\.google\.com/(?:\w+/)*?(\d+)/posts/(\w+)'
+	IE_NAME = u'plus.google'
+
+	def __init__(self, downloader=None):
+		InfoExtractor.__init__(self, downloader)
+
+	def report_extract_entry(self, url):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Downloading entry: %s' % url.decode('utf-8'))
+
+	def report_date(self, upload_date):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Entry date: %s' % upload_date)
+
+	def report_uploader(self, uploader):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Uploader: %s' % uploader.decode('utf-8'))
+
+	def report_title(self, video_title):
+		"""Report downloading extry"""
+		self._downloader.to_screen(u'[plus.google] Title: %s' % video_title.decode('utf-8'))
+
+	def report_extract_vid_page(self, video_page):
+		"""Report information extraction."""
+		self._downloader.to_screen(u'[plus.google] Extracting video page: %s' % video_page.decode('utf-8'))
+
+	def _real_extract(self, url):
+		# Extract id from URL
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+			return
+
+		post_url = mobj.group(0)
+		video_id = mobj.group(2)
+
+		video_extension = 'flv'
+
+		# Step 1, Retrieve post webpage to extract further information
+		self.report_extract_entry(post_url)
+		request = urllib2.Request(post_url)
+		try:
+			webpage = urllib2.urlopen(request).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err))
+			return
+
+		# Extract update date
+		upload_date = u'NA'
+		pattern = 'title="Timestamp">(.*?)</a>'
+		mobj = re.search(pattern, webpage)
+		if mobj:
+			upload_date = mobj.group(1)
+			# Convert timestring to a format suitable for filename
+			upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
+			upload_date = upload_date.strftime('%Y%m%d')
+		self.report_date(upload_date)
+
+		# Extract uploader
+		uploader = u'NA'
+		pattern = r'rel\="author".*?>(.*?)</a>'
+		mobj = re.search(pattern, webpage)
+		if mobj:
+			uploader = mobj.group(1)
+		self.report_uploader(uploader)
+
+		# Extract title
+		# Get the first line for title
+		video_title = u'NA'
+		pattern = r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]'
+		mobj = re.search(pattern, webpage)
+		if mobj:
+			video_title = mobj.group(1)
+		self.report_title(video_title)
+
+		# Step 2, Stimulate clicking the image box to launch video
+		pattern = '"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]'
+		mobj = re.search(pattern, webpage)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: unable to extract video page URL')
+
+		video_page = mobj.group(1)
+		request = urllib2.Request(video_page)
+		try:
+			webpage = urllib2.urlopen(request).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
+			return
+		self.report_extract_vid_page(video_page)
+
+
+		# Extract video links on video page
+		"""Extract video links of all sizes"""
+		pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
+		mobj = re.findall(pattern, webpage)
+		if len(mobj) == 0:
+			self._downloader.trouble(u'ERROR: unable to extract video links')
+
+		# Sort in resolution
+		links = sorted(mobj)
+
+		# Choose the lowest of the sort, i.e. highest resolution
+		video_url = links[-1]
+		# Only get the url. The resolution part in the tuple has no use anymore
+		video_url = video_url[-1]
+		# Treat escaped \u0026 style hex
+		video_url = unicode(video_url, "unicode_escape")
+
+
+		return [{
+			'id':		video_id.decode('utf-8'),
+			'url':		video_url,
+			'uploader':	uploader.decode('utf-8'),
+			'upload_date':	upload_date.decode('utf-8'),
+			'title':	video_title.decode('utf-8'),
+			'ext':		video_extension.decode('utf-8'),
+			'format':	u'NA',
+			'player_url':	None,
+		}]