X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2FInfoExtractors.py;h=f0d3e0c63e91766631121dd3c1ef06fc98e41d2a;hb=96731798dbdd5a8878ac5cf29b69c6c7c821311b;hp=9df521d0233d806a83e3f5abf648f2e3a22b690f;hpb=fe4d68e1967cc39cc00a06c3e2e722d51b8e1419;p=youtube-dl

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 9df521d02..f0d3e0c63 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -29,37 +29,48 @@ class InfoExtractor(object):
 	"""Information Extractor class.
 
 	Information extractors are the classes that, given a URL, extract
-	information from the video (or videos) the URL refers to. This
-	information includes the real video URL, the video title and simplified
-	title, author and others. The information is stored in a dictionary
-	which is then passed to the FileDownloader. The FileDownloader
-	processes this information possibly downloading the video to the file
-	system, among other possible outcomes. The dictionaries must include
-	the following fields:
-
-	id:		Video identifier.
-	url:		Final video URL.
-	uploader:	Nickname of the video uploader.
-	title:		Literal title.
-	ext:		Video filename extension.
-	format:		Video format.
-	player_url:	SWF Player URL (may be None).
-
-	The following fields are optional. Their primary purpose is to allow
-	youtube-dl to serve as the backend for a video search function, such
-	as the one in youtube2mp3.  They are only used when their respective
-	forced printing functions are called:
-
-	thumbnail:	Full URL to a video thumbnail image.
-	description:	One-line video description.
+	information about the video (or videos) the URL refers to. This
+	information includes the real video URL, the video title, author and
+	others. The information is stored in a dictionary which is then 
+	passed to the FileDownloader. The FileDownloader processes this
+	information possibly downloading the video to the file system, among
+	other possible outcomes.
+
+	The dictionaries must include the following fields:
+
+	id:             Video identifier.
+	url:            Final video URL.
+	uploader:       Nickname of the video uploader, unescaped.
+	upload_date:    Video upload date (YYYYMMDD).
+	title:          Video title, unescaped.
+	ext:            Video filename extension.
+
+	The following fields are optional:
+
+	format:         The video format, defaults to ext (used for --get-format)
+	thumbnail:      Full URL to a video thumbnail image.
+	description:    One-line video description.
+	player_url:     SWF Player URL (used for rtmpdump).
+	subtitles:      The .srt file contents.
+	urlhandle:		[internal] The urlHandle to be used to download the file,
+	                like returned by urllib2.urlopen
+
+	The fields should all be Unicode strings.
 
 	Subclasses of this one should re-define the _real_initialize() and
 	_real_extract() methods and define a _VALID_URL regexp.
 	Probably, they should also be added to the list of extractors.
+
+	_real_extract() must return a *list* of information dictionaries as
+	described above.
+
+	Finally, the _WORKING attribute should be set to False for broken IEs
+	in order to warn the users and skip the tests.
 	"""
 
 	_ready = False
 	_downloader = None
+	_WORKING = True
 
 	def __init__(self, downloader=None):
 		"""Constructor. Receives an optional downloader."""
@@ -70,6 +81,10 @@ class InfoExtractor(object):
 		"""Receives a URL and returns True if suitable for this IE."""
 		return re.match(self._VALID_URL, url) is not None
 
+	def working(self):
+		"""Getter method for _WORKING."""
+		return self._WORKING
+
 	def initialize(self):
 		"""Initializes an instance (authentication, etc)."""
 		if not self._ready:
@@ -213,9 +228,9 @@ class YoutubeIE(InfoExtractor):
 		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:
@@ -238,7 +253,7 @@ 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
@@ -247,7 +262,7 @@ 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
@@ -270,7 +285,7 @@ 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
@@ -283,7 +298,7 @@ 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):
@@ -305,7 +320,7 @@ 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
@@ -327,7 +342,7 @@ 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:
@@ -365,7 +380,7 @@ class YoutubeIE(InfoExtractor):
 			video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
 
 		# upload date
-		upload_date = u'NA'
+		upload_date = None
 		mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
 		if mobj is not None:
 			upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
@@ -390,7 +405,7 @@ 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' % str(err))
+					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:
@@ -407,7 +422,7 @@ 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' % 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'))
@@ -475,6 +490,9 @@ class YoutubeIE(InfoExtractor):
 			# Extension
 			video_extension = self._video_extensions.get(format_param, 'flv')
 
+			video_format = '{} - {}'.format(format_param.decode('utf-8') if format_param else video_extension.decode('utf-8'),
+				                            self._video_dimensions.get(format_param, '???'))
+
 			results.append({
 				'id':		video_id.decode('utf-8'),
 				'url':		video_real_url.decode('utf-8'),
@@ -482,7 +500,7 @@ class YoutubeIE(InfoExtractor):
 				'upload_date':	upload_date,
 				'title':	video_title,
 				'ext':		video_extension.decode('utf-8'),
-				'format':	(format_param is None and u'NA' or format_param.decode('utf-8')),
+				'format':	video_format,
 				'thumbnail':	video_thumbnail.decode('utf-8'),
 				'description':	video_description,
 				'player_url':	player_url,
@@ -526,7 +544,7 @@ 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
@@ -539,7 +557,7 @@ 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):
@@ -563,7 +581,7 @@ 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' % str(err))
+			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract URL, uploader and title from webpage
@@ -603,7 +621,7 @@ class MetacafeIE(InfoExtractor):
 			return
 		video_title = mobj.group(1).decode('utf-8')
 
-		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
@@ -613,11 +631,9 @@ class MetacafeIE(InfoExtractor):
 			'id':		video_id.decode('utf-8'),
 			'url':		video_url.decode('utf-8'),
 			'uploader':	video_uploader.decode('utf-8'),
-			'upload_date':	u'NA',
+			'upload_date':	None,
 			'title':	video_title,
 			'ext':		video_extension.decode('utf-8'),
-			'format':	u'NA',
-			'player_url':	None,
 		}]
 
 
@@ -656,7 +672,7 @@ 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' % str(err))
+			self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_str(err))
 			return
 
 		# Extract URL, uploader and title from webpage
@@ -691,14 +707,19 @@ class DailymotionIE(InfoExtractor):
 			return
 		video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
 
-		video_uploader = u'NA'
+		video_uploader = None
 		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
 		if mobj is None:
-			self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+			# 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'
+		video_upload_date = None
 		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)
@@ -710,8 +731,6 @@ class DailymotionIE(InfoExtractor):
 			'upload_date':	video_upload_date,
 			'title':	video_title,
 			'ext':		video_extension.decode('utf-8'),
-			'format':	u'NA',
-			'player_url':	None,
 		}]
 
 
@@ -749,7 +768,7 @@ 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
@@ -788,7 +807,7 @@ 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:
@@ -801,12 +820,10 @@ class GoogleIE(InfoExtractor):
 		return [{
 			'id':		video_id.decode('utf-8'),
 			'url':		video_url.decode('utf-8'),
-			'uploader':	u'NA',
-			'upload_date':	u'NA',
+			'uploader':	None,
+			'upload_date':	None,
 			'title':	video_title,
 			'ext':		video_extension.decode('utf-8'),
-			'format':	u'NA',
-			'player_url':	None,
 		}]
 
 
@@ -844,7 +861,7 @@ 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
@@ -869,11 +886,9 @@ class PhotobucketIE(InfoExtractor):
 			'id':		video_id.decode('utf-8'),
 			'url':		video_url.decode('utf-8'),
 			'uploader':	video_uploader,
-			'upload_date':	u'NA',
+			'upload_date':	None,
 			'title':	video_title,
 			'ext':		video_extension.decode('utf-8'),
-			'format':	u'NA',
-			'player_url':	None,
 		}]
 
 
@@ -914,7 +929,7 @@ 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)
@@ -938,7 +953,7 @@ 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
@@ -996,7 +1011,7 @@ 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
@@ -1011,13 +1026,11 @@ class YahooIE(InfoExtractor):
 			'id':		video_id.decode('utf-8'),
 			'url':		video_url,
 			'uploader':	video_uploader,
-			'upload_date':	u'NA',
+			'upload_date':	None,
 			'title':	video_title,
 			'ext':		video_extension.decode('utf-8'),
 			'thumbnail':	video_thumbnail.decode('utf-8'),
 			'description':	video_description,
-			'thumbnail':	video_thumbnail,
-			'player_url':	None,
 		}]
 
 
@@ -1025,7 +1038,7 @@ 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):
@@ -1054,7 +1067,7 @@ 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
@@ -1085,7 +1098,7 @@ class VimeoIE(InfoExtractor):
 		else: video_description = ''
 
 		# Extract upload date
-		video_upload_date = u'NA'
+		video_upload_date = None
 		mobj = re.search(r'<span id="clip-date" style="display:none">[^:]*: (.*?)( \([^\(]*\))?</span>', webpage)
 		if mobj is not None:
 			video_upload_date = mobj.group(1)
@@ -1095,21 +1108,32 @@ 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,
@@ -1120,10 +1144,146 @@ class VimeoIE(InfoExtractor):
 			'ext':		video_extension,
 			'thumbnail':	video_thumbnail,
 			'description':	video_description,
-			'player_url':	None,
 		}]
 
 
+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' % compat_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."""
 
@@ -1209,7 +1369,7 @@ 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
@@ -1263,11 +1423,9 @@ class GenericIE(InfoExtractor):
 			'id':		video_id.decode('utf-8'),
 			'url':		video_url.decode('utf-8'),
 			'uploader':	video_uploader,
-			'upload_date':	u'NA',
+			'upload_date':	None,
 			'title':	video_title,
 			'ext':		video_extension.decode('utf-8'),
-			'format':	u'NA',
-			'player_url':	None,
 		}]
 
 
@@ -1303,7 +1461,7 @@ 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
@@ -1330,7 +1488,7 @@ 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']
 
@@ -1381,7 +1539,7 @@ 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
@@ -1407,7 +1565,7 @@ 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
@@ -1463,7 +1621,7 @@ 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
@@ -1490,7 +1648,7 @@ 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
@@ -1560,7 +1718,7 @@ 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
@@ -1617,7 +1775,7 @@ 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' % str(err))
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
 				return
 
 			# Extract video identifiers
@@ -1680,7 +1838,7 @@ 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
@@ -1752,7 +1910,7 @@ 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' % str(err))
+			self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
 			return
 
 
@@ -1840,7 +1998,7 @@ 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
@@ -1868,18 +2026,17 @@ class DepositFilesIE(InfoExtractor):
 		return [{
 			'id':		file_id.decode('utf-8'),
 			'url':		file_url.decode('utf-8'),
-			'uploader':	u'NA',
-			'upload_date':	u'NA',
+			'uploader':	None,
+			'upload_date':	None,
 			'title':	file_title,
 			'ext':		file_extension.decode('utf-8'),
-			'format':	u'NA',
-			'player_url':	None,
 		}]
 
 
 class FacebookIE(InfoExtractor):
 	"""Information Extractor for Facebook"""
 
+	_WORKING = False
 	_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
 	_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
 	_NETRC_MACHINE = 'facebook'
@@ -1957,7 +2114,7 @@ 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:
@@ -1977,7 +2134,7 @@ 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):
@@ -1994,7 +2151,7 @@ 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
@@ -2024,7 +2181,7 @@ class FacebookIE(InfoExtractor):
 			video_thumbnail = video_info['thumbnail']
 
 		# upload date
-		upload_date = u'NA'
+		upload_date = None
 		if 'upload_date' in video_info:
 			upload_time = video_info['upload_date']
 			timetuple = email.utils.parsedate_tz(upload_time)
@@ -2079,7 +2236,6 @@ class FacebookIE(InfoExtractor):
 				'format':	(format_param is None and u'NA' or format_param.decode('utf-8')),
 				'thumbnail':	video_thumbnail.decode('utf-8'),
 				'description':	video_description.decode('utf-8'),
-				'player_url':	None,
 			})
 		return results
 
@@ -2123,18 +2279,20 @@ class BlipTVIE(InfoExtractor):
 				info = {
 					'id': title,
 					'url': url,
+					'uploader': None,
+					'upload_date': None,
 					'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:
@@ -2202,7 +2360,7 @@ 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)
@@ -2223,12 +2381,10 @@ class MyVideoIE(InfoExtractor):
 		return [{
 			'id':		video_id,
 			'url':		video_url,
-			'uploader':	u'NA',
-			'upload_date':  u'NA',
+			'uploader':	None,
+			'upload_date':  None,
 			'title':	video_title,
 			'ext':		u'flv',
-			'format':	u'NA',
-			'player_url':	None,
 		}]
 
 class ComedyCentralIE(InfoExtractor):
@@ -2237,6 +2393,25 @@ 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)
 
@@ -2249,6 +2424,13 @@ 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:
@@ -2275,7 +2457,7 @@ 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' % compat_str(err))
 			return
 		if dlNewest:
 			url = htmlHandle.geturl()
@@ -2289,17 +2471,26 @@ 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: ' + compat_str(err))
 			return
 
 		uri = mMovieParams[0][1]
@@ -2308,7 +2499,7 @@ 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: ' + compat_str(err))
 			return
 
 		results = []
@@ -2329,7 +2520,7 @@ 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' % compat_str(err))
 				return
 
 			cdoc = xml.etree.ElementTree.fromstring(configXml)
@@ -2341,10 +2532,31 @@ 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]
 
+			# 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)
+
 			effTitle = showId + u'-' + epTitle
 			info = {
 				'id': shortMediaId,
@@ -2356,7 +2568,7 @@ class ComedyCentralIE(InfoExtractor):
 				'format': format,
 				'thumbnail': None,
 				'description': officialTitle,
-				'player_url': playerUrl
+				'player_url': None #playerUrl
 			}
 
 			results.append(info)
@@ -2391,7 +2603,7 @@ 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: ' + compat_str(err))
 			return
 
 		descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
@@ -2407,7 +2619,7 @@ 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: ' + compat_str(err))
 			return
 
 		# Technically, it's JavaScript, not JSON
@@ -2416,7 +2628,7 @@ 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: ' + compat_str(err))
 			return
 
 		playlist = config['playlist']
@@ -2429,7 +2641,6 @@ class EscapistIE(InfoExtractor):
 			'upload_date': None,
 			'title': showName,
 			'ext': 'flv',
-			'format': 'flv',
 			'thumbnail': imgUrl,
 			'description': description,
 			'player_url': playerUrl,
@@ -2464,7 +2675,7 @@ 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)
@@ -2476,6 +2687,8 @@ class CollegeHumorIE(InfoExtractor):
 		info = {
 			'id': video_id,
 			'internal_id': internal_video_id,
+			'uploader': None,
+			'upload_date': None,
 		}
 
 		self.report_extraction(video_id)
@@ -2483,7 +2696,7 @@ 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)
@@ -2494,7 +2707,6 @@ class CollegeHumorIE(InfoExtractor):
 			info['url'] = videoNode.findall('./file')[0].text
 			info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
 			info['ext'] = info['url'].rpartition('.')[2]
-			info['format'] = info['ext']
 		except IndexError:
 			self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
 			return
@@ -2529,7 +2741,7 @@ 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)
@@ -2565,10 +2777,8 @@ class XVideosIE(InfoExtractor):
 			'upload_date': None,
 			'title': video_title,
 			'ext': 'flv',
-			'format': 'flv',
 			'thumbnail': video_thumbnail,
 			'description': None,
-			'player_url': None,
 		}
 
 		return [info]
@@ -2615,7 +2825,7 @@ 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))
@@ -2642,7 +2852,7 @@ 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)
@@ -2650,7 +2860,7 @@ 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(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)
@@ -2662,8 +2872,6 @@ class SoundcloudIE(InfoExtractor):
 			'upload_date':  upload_date,
 			'title':	title,
 			'ext':		u'mp3',
-			'format':	u'NA',
-			'player_url':	None,
 			'description': description.decode('utf-8')
 		}]
 
@@ -2694,7 +2902,7 @@ 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)
@@ -2730,11 +2938,9 @@ class InfoQIE(InfoExtractor):
 			'uploader': None,
 			'upload_date': None,
 			'title': video_title,
-			'ext': extension,
-			'format': extension, # Extension is always(?) mp4, but seems to be flv
+			'ext': extension, # Extension is always(?) mp4, but seems to be flv
 			'thumbnail': None,
 			'description': video_description,
-			'player_url': None,
 		}
 
 		return [info]
@@ -2780,15 +2986,15 @@ 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):
@@ -2808,7 +3014,7 @@ 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
@@ -2843,7 +3049,7 @@ class MixcloudIE(InfoExtractor):
 			'id': file_id.decode('utf-8'),
 			'url': file_url.decode('utf-8'),
 			'uploader':	uploader.decode('utf-8'),
-			'upload_date': u'NA',
+			'upload_date': None,
 			'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')),
@@ -2877,6 +3083,8 @@ class StanfordOpenClassroomIE(InfoExtractor):
 			video = mobj.group('video')
 			info = {
 				'id': course + '_' + video,
+				'uploader': None,
+				'upload_date': None,
 			}
 
 			self.report_extraction(info['id'])
@@ -2885,7 +3093,7 @@ 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' % compat_str(err))
 				return
 			mdoc = xml.etree.ElementTree.fromstring(metaXml)
 			try:
@@ -2895,20 +3103,21 @@ class StanfordOpenClassroomIE(InfoExtractor):
 				self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
 				return
 			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': course,
 				'type': 'playlist',
+				'uploader': None,
+				'upload_date': None,
 			}
 
 			self.report_download_webpage(info['id'])
 			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: ' + compat_str(err))
 				return
 
 			m = re.search('<h1>([^<]+)</h1>', coursepage)
@@ -2938,6 +3147,8 @@ class StanfordOpenClassroomIE(InfoExtractor):
 			info = {
 				'id': 'Stanford OpenClassroom',
 				'type': 'playlist',
+				'uploader': None,
+				'upload_date': None,
 			}
 
 			self.report_download_webpage(info['id'])
@@ -2945,7 +3156,7 @@ 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: ' + compat_str(err))
 				return
 
 			info['title'] = info['id']
@@ -2992,7 +3203,7 @@ 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)
@@ -3025,7 +3236,7 @@ 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)
@@ -3046,6 +3257,7 @@ class MTVIE(InfoExtractor):
 			'id': video_id,
 			'url': video_url,
 			'uploader': performer,
+			'upload_date': None,
 			'title': video_title,
 			'ext': ext,
 			'format': format,
@@ -3112,7 +3324,7 @@ 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' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 
 		self.report_extraction(video_id)
@@ -3167,9 +3379,9 @@ class YoukuIE(InfoExtractor):
 				'id': '%s_part%02d' % (video_id, index),
 				'url': download_url,
 				'uploader': None,
+				'upload_date': None,
 				'title': video_title,
 				'ext': ext,
-				'format': u'NA'
 			}
 			files_info.append(info)
 
@@ -3227,18 +3439,16 @@ class XNXXIE(InfoExtractor):
 			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]
+		return [{
+			'id': video_id,
+			'url': video_url,
+			'uploader': None,
+			'upload_date': None,
+			'title': video_title,
+			'ext': 'flv',
+			'thumbnail': video_thumbnail,
+			'description': None,
+		}]
 
 
 class GooglePlusIE(InfoExtractor):
@@ -3288,11 +3498,11 @@ 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' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve entry webpage: %s' % compat_str(err))
 			return
 
 		# Extract update date
-		upload_date = u'NA'
+		upload_date = None
 		pattern = 'title="Timestamp">(.*?)</a>'
 		mobj = re.search(pattern, webpage)
 		if mobj:
@@ -3303,7 +3513,7 @@ class GooglePlusIE(InfoExtractor):
 		self.report_date(upload_date)
 
 		# Extract uploader
-		uploader = u'NA'
+		uploader = None
 		pattern = r'rel\="author".*?>(.*?)</a>'
 		mobj = re.search(pattern, webpage)
 		if mobj:
@@ -3330,7 +3540,7 @@ 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' % str(err))
+			self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_str(err))
 			return
 		self.report_extract_vid_page(video_page)
 
@@ -3360,6 +3570,4 @@ class GooglePlusIE(InfoExtractor):
 			'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,
 		}]