X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=85ffad18c61efce1431c07aabba3a56c3cfef56c;hb=18ea0cefc370807e1d31fd7b462691f29f48c8fe;hp=3cdce3b259983866855721374fb1c9e0db608b80;hpb=89af8e9d32f550bdf00da9eab3288ad1e104d3b3;p=youtube-dl

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 3cdce3b25..85ffad18c 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -238,7 +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' % compat_str(err))
+				self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % u(err))
 				return
 
 		# Set language
@@ -247,7 +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' % compat_str(err))
+			self._downloader.to_stderr(u'WARNING: unable to set language: %s' % u(err))
 			return
 
 		# No authentication to be performed
@@ -270,7 +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' % compat_str(err))
+			self._downloader.to_stderr(u'WARNING: unable to log in: %s' % u(err))
 			return
 
 		# Confirm age
@@ -283,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err))
 			return
 
 	def _real_extract(self, url):
@@ -305,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
 			return
 
 		# Attempt to extract SWF player URL
@@ -327,7 +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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % u(err))
 				return
 		if 'token' not in video_info:
 			if 'reason' in video_info:
@@ -390,7 +390,7 @@ 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' % compat_str(err))
+					raise Trouble(u'WARNING: unable to download video subtitles: %s' % u(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:
@@ -407,7 +407,7 @@ class YoutubeIE(InfoExtractor):
 				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' % compat_str(err))
+					raise Trouble(u'WARNING: unable to download video subtitles: %s' % u(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'))
@@ -526,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % u(err))
 			return
 
 		# Confirm age
@@ -539,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to confirm age: %s' % u(err))
 			return
 
 	def _real_extract(self, url):
@@ -563,7 +563,7 @@ class MetacafeIE(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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err))
 			return
 
 		# Extract URL, uploader and title from webpage
@@ -656,7 +656,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % u(err))
 			return
 
 		# Extract URL, uploader and title from webpage
@@ -754,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 
 		# Extract URL, uploader, and title from webpage
@@ -793,7 +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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 				return
 			mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
 			if mobj is None:
@@ -849,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 
 		# Extract URL, uploader, and title from webpage
@@ -919,7 +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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 				return
 
 			mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
@@ -943,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 
 		# Extract uploader and title from webpage
@@ -1001,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 
 		# Extract media URL from playlist XML
@@ -1059,7 +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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 
 		# Now we begin extracting as much information as we can from what we
@@ -1140,6 +1140,143 @@ class VimeoIE(InfoExtractor):
 		}]
 
 
+class ArteTvIE(InfoExtractor):
+	"""arte.tv information extractor."""
+
+	_VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
+	_LIVE_URL = r'index-[0-9]+\.html$'
+
+	IE_NAME = u'arte.tv'
+
+	def __init__(self, downloader=None):
+		InfoExtractor.__init__(self, downloader)
+
+	def report_download_webpage(self, video_id):
+		"""Report webpage download."""
+		self._downloader.to_screen(u'[arte.tv] %s: Downloading webpage' % video_id)
+
+	def report_extraction(self, video_id):
+		"""Report information extraction."""
+		self._downloader.to_screen(u'[arte.tv] %s: Extracting information' % video_id)
+
+	def fetch_webpage(self, url):
+		self._downloader.increment_downloads()
+		request = urllib2.Request(url)
+		try:
+			self.report_download_webpage(url)
+			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))
+			return
+		except ValueError, err:
+			self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+			return
+		return webpage
+
+	def grep_webpage(self, url, regex, regexFlags, matchTuples):
+		page = self.fetch_webpage(url)
+		mobj = re.search(regex, page, regexFlags)
+		info = {}
+
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
+			return
+
+		for (i, key, err) in matchTuples:
+			if mobj.group(i) is None:
+				self._downloader.trouble(err)
+				return
+			else:
+				info[key] = mobj.group(i)
+
+		return info
+
+	def extractLiveStream(self, url):
+		video_lang = url.split('/')[-4]
+		info = self.grep_webpage(
+			url,
+			r'src="(.*?/videothek_js.*?\.js)',
+			0,
+			[
+				(1, 'url', u'ERROR: Invalid URL: %s' % url)
+			]
+		)
+		http_host = url.split('/')[2]
+		next_url = 'http://%s%s' % (http_host, urllib.unquote(info.get('url')))
+		info = self.grep_webpage(
+			next_url,
+			r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
+				'(http://.*?\.swf).*?' +
+				'(rtmp://.*?)\'',
+			re.DOTALL,
+			[
+				(1, 'path',   u'ERROR: could not extract video path: %s' % url),
+				(2, 'player', u'ERROR: could not extract video player: %s' % url),
+				(3, 'url',    u'ERROR: could not extract video url: %s' % url)
+			]
+		)
+		video_url = u'%s/%s' % (info.get('url'), info.get('path'))
+
+	def extractPlus7Stream(self, url):
+		video_lang = url.split('/')[-3]
+		info = self.grep_webpage(
+			url,
+			r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
+			0,
+			[
+				(1, 'url', u'ERROR: Invalid URL: %s' % url)
+			]
+		)
+		next_url = urllib.unquote(info.get('url'))
+		info = self.grep_webpage(
+			next_url,
+			r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
+			0,
+			[
+				(1, 'url', u'ERROR: Could not find <video> tag: %s' % url)
+			]
+		)
+		next_url = urllib.unquote(info.get('url'))
+
+		info = self.grep_webpage(
+			next_url,
+			r'<video id="(.*?)".*?>.*?' +
+				'<name>(.*?)</name>.*?' +
+				'<dateVideo>(.*?)</dateVideo>.*?' +
+				'<url quality="hd">(.*?)</url>',
+			re.DOTALL,
+			[
+				(1, 'id',    u'ERROR: could not extract video id: %s' % url),
+				(2, 'title', u'ERROR: could not extract video title: %s' % url),
+				(3, 'date',  u'ERROR: could not extract video date: %s' % url),
+				(4, 'url',   u'ERROR: could not extract video url: %s' % url)
+			]
+		)
+
+		return {
+			'id':           info.get('id'),
+			'url':          urllib.unquote(info.get('url')),
+			'uploader':     u'arte.tv',
+			'upload_date':  info.get('date'),
+			'title':        info.get('title'),
+			'ext':          u'mp4',
+			'format':       u'NA',
+			'player_url':   None,
+		}
+
+	def _real_extract(self, url):
+		video_id = url.split('/')[-1]
+		self.report_extraction(video_id)
+
+		if re.search(self._LIVE_URL, video_id) is not None:
+			self.extractLiveStream(url)
+			return
+		else:
+			info = self.extractPlus7Stream(url)
+
+		return [info]
+
+
 class GenericIE(InfoExtractor):
 	"""Generic last-resort information extractor."""
 
@@ -1225,7 +1362,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 		except ValueError, err:
 			# since this is the last-resort InfoExtractor, if
@@ -1319,7 +1456,7 @@ class YoutubeSearchIE(InfoExtractor):
 			return
 		else:
 			try:
-				n = long(prefix)
+				n = int(prefix)
 				if n <= 0:
 					self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
 					return
@@ -1346,7 +1483,7 @@ 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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to download API page: %s' % u(err))
 				return
 			api_response = json.loads(data)['data']
 
@@ -1397,7 +1534,7 @@ class GoogleSearchIE(InfoExtractor):
 			return
 		else:
 			try:
-				n = long(prefix)
+				n = int(prefix)
 				if n <= 0:
 					self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
 					return
@@ -1423,7 +1560,7 @@ 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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 				return
 
 			# Extract video identifiers
@@ -1479,7 +1616,7 @@ class YahooSearchIE(InfoExtractor):
 			return
 		else:
 			try:
-				n = long(prefix)
+				n = int(prefix)
 				if n <= 0:
 					self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
 					return
@@ -1506,7 +1643,7 @@ 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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 				return
 
 			# Extract video identifiers
@@ -1576,7 +1713,7 @@ 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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 				return
 
 			# Extract video identifiers
@@ -1633,7 +1770,7 @@ class YoutubeChannelIE(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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 				return
 
 			# Extract video identifiers
@@ -1696,7 +1833,7 @@ 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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 				return
 
 			# Extract video identifiers
@@ -1768,7 +1905,7 @@ class BlipTVUserIE(InfoExtractor):
 			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))
+			self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 			return
 
 
@@ -1856,7 +1993,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % u(err))
 			return
 
 		# Search for the real file URL
@@ -1973,7 +2110,7 @@ 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' % compat_str(err))
+				self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % u(err))
 				return
 
 		if useremail is None:
@@ -1993,7 +2130,7 @@ 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' % compat_str(err))
+			self._downloader.to_stderr(u'WARNING: unable to log in: %s' % u(err))
 			return
 
 	def _real_extract(self, url):
@@ -2010,7 +2147,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
 			return
 
 		# Start extracting information
@@ -2144,13 +2281,13 @@ class BlipTVIE(InfoExtractor):
 					'urlhandle': urlh
 				}
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % u(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' % compat_str(err))
+				self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % u(err))
 				return
 
 			try:
@@ -2218,7 +2355,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 
 		self.report_extraction(video_id)
@@ -2253,6 +2390,25 @@ class ComedyCentralIE(InfoExtractor):
 	_VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
 	IE_NAME = u'comedycentral'
 
+	_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
+
+	_video_extensions = {
+		'3500': 'mp4',
+		'2200': 'mp4',
+		'1700': 'mp4',
+		'1200': 'mp4',
+		'750': 'mp4',
+		'400': 'mp4',
+	}
+	_video_dimensions = {
+		'3500': '1280x720',
+		'2200': '960x540',
+		'1700': '768x432',
+		'1200': '640x360',
+		'750': '512x288',
+		'400': '384x216',
+	}
+
 	def report_extraction(self, episode_id):
 		self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
 
@@ -2265,6 +2421,13 @@ class ComedyCentralIE(InfoExtractor):
 	def report_player_url(self, episode_id):
 		self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
 
+
+	def _print_formats(self, formats):
+		print('Available formats:')
+		for x in formats:
+			print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???')))
+
+
 	def _real_extract(self, url):
 		mobj = re.match(self._VALID_URL, url)
 		if mobj is None:
@@ -2291,7 +2454,7 @@ class ComedyCentralIE(InfoExtractor):
 			htmlHandle = urllib2.urlopen(req)
 			html = htmlHandle.read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+			self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 			return
 		if dlNewest:
 			url = htmlHandle.geturl()
@@ -2305,17 +2468,26 @@ class ComedyCentralIE(InfoExtractor):
 			epTitle = mobj.group('episode')
 
 		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
+			# The Colbert Report embeds the information in a without
+			# a URL prefix; so extract the alternate reference
+			# and then add the URL prefix manually.
 
+			altMovieParams = re.findall('data-mgid="([^"]*episode.*?:.*?)"', html)
+			if len(altMovieParams) == 0:
+				self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
+				return
+			else:
+				mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
+		
 		playerUrl_raw = mMovieParams[0][0]
 		self.report_player_url(epTitle)
 		try:
 			urlHandle = urllib2.urlopen(playerUrl_raw)
 			playerUrl = urlHandle.geturl()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err))
+			self._downloader.trouble(u'ERROR: unable to find out player URL: ' + u(err))
 			return
 
 		uri = mMovieParams[0][1]
@@ -2324,7 +2496,7 @@ class ComedyCentralIE(InfoExtractor):
 		try:
 			indexXml = urllib2.urlopen(indexUrl).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
+			self._downloader.trouble(u'ERROR: unable to download episode index: ' + u(err))
 			return
 
 		results = []
@@ -2345,7 +2517,7 @@ class ComedyCentralIE(InfoExtractor):
 			try:
 				configXml = urllib2.urlopen(configReq).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % u(err))
 				return
 
 			cdoc = xml.etree.ElementTree.fromstring(configXml)
@@ -2357,20 +2529,30 @@ class ComedyCentralIE(InfoExtractor):
 			if len(turls) == 0:
 				self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
 				continue
+			
+			if self._downloader.params.get('listformats', None):
+				self._print_formats([i[0] for i in turls])
+				return
 
 			# For now, just pick the highest bitrate
 			format,video_url = turls[-1]
 
-			# Patch to download from alternative CDN, which does not 
-                        # break on current RTMPDump builds
-            
+			# Get the format arg from the arg stream
+			req_format = self._downloader.params.get('format', None)
+
+			# Select format if we can find one
+			for f,v in turls:
+				if f == req_format:
+					format, video_url = f, v
+					break
 
+			# Patch to download from alternative CDN, which does not
+			# break on current RTMPDump builds
 			broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/"
 			better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/"
-            
+
 			if video_url.startswith(broken_cdn):
-                            video_url = video_url.replace(broken_cdn, better_cdn)
-                    
+				video_url = video_url.replace(broken_cdn, better_cdn)
 
 			effTitle = showId + u'-' + epTitle
 			info = {
@@ -2418,7 +2600,7 @@ class EscapistIE(InfoExtractor):
 			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))
+			self._downloader.trouble(u'ERROR: unable to download webpage: ' + u(err))
 			return
 
 		descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
@@ -2434,7 +2616,7 @@ class EscapistIE(InfoExtractor):
 		try:
 			configJSON = urllib2.urlopen(configUrl).read()
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
+			self._downloader.trouble(u'ERROR: unable to download configuration: ' + u(err))
 			return
 
 		# Technically, it's JavaScript, not JSON
@@ -2443,7 +2625,7 @@ class EscapistIE(InfoExtractor):
 		try:
 			config = json.loads(configJSON)
 		except (ValueError,), err:
-			self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
+			self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + u(err))
 			return
 
 		playlist = config['playlist']
@@ -2491,7 +2673,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
 			return
 
 		m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
@@ -2510,7 +2692,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % u(err))
 			return
 
 		mdoc = xml.etree.ElementTree.fromstring(metaXml)
@@ -2556,7 +2738,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
 			return
 
 		self.report_extraction(video_id)
@@ -2642,7 +2824,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
 			return
 
 		self.report_extraction('%s/%s' % (uploader, slug_title))
@@ -2677,7 +2859,7 @@ class SoundcloudIE(InfoExtractor):
 			try:
 				upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
 			except Exception, e:
-				self._downloader.to_stderr(compat_str(e))
+				self._downloader.to_stderr(u(e))
 
 		# for soundcloud, a request to a cross domain is required for cookies
 		request = urllib2.Request('http://media.soundcloud.com/crossdomain.xml', std_headers)
@@ -2721,7 +2903,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
 			return
 
 		self.report_extraction(url)
@@ -2835,7 +3017,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % u(err))
 			return
 
 		# parse JSON
@@ -2912,7 +3094,7 @@ class StanfordOpenClassroomIE(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' % unicode(err))
+				self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % u(err))
 				return
 			mdoc = xml.etree.ElementTree.fromstring(metaXml)
 			try:
@@ -2935,7 +3117,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
 			try:
 				coursepage = urllib2.urlopen(url).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+				self._downloader.trouble(u'ERROR: unable to download course info page: ' + u(err))
 				return
 
 			m = re.search('<h1>([^<]+)</h1>', coursepage)
@@ -2972,7 +3154,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
 			try:
 				rootpage = urllib2.urlopen(rootURL).read()
 			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-				self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+				self._downloader.trouble(u'ERROR: unable to download course info page: ' + u(err))
 				return
 
 			info['title'] = info['id']
@@ -3019,7 +3201,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % u(err))
 			return
 
 		mobj = re.search(r'<meta name="mtv_vt" content="([^"]+)"/>', webpage)
@@ -3052,7 +3234,7 @@ 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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: unable to download video metadata: %s' % u(err))
 			return
 
 		mdoc = xml.etree.ElementTree.fromstring(metadataXml)
@@ -3139,7 +3321,7 @@ class YoukuIE(InfoExtractor):
 			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))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 
 		self.report_extraction(video_id)
@@ -3315,7 +3497,7 @@ class GooglePlusIE(InfoExtractor):
 		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))
+			self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % u(err))
 			return
 
 		# Extract update date
@@ -3357,7 +3539,7 @@ class GooglePlusIE(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' % compat_str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % u(err))
 			return
 		self.report_extract_vid_page(video_page)