Release 2011.09.27

add support for vorbis to  --extract-audio

LATEST_VERSION

@@ -1 +1 @@
-2011.09.18
+2011.09.27

README.md

@@ -33,13 +33,17 @@ which means you can modify it, redistribute it or use it however you like.
     -t, --title              use title in file name
     -l, --literal            use literal title in file name
     -A, --auto-number        number downloaded files starting from 00000
-    -o, --output TEMPLATE    output filename template
+    -o, --output TEMPLATE    output filename template. Use %(stitle)s to get the
+                             title, %(uploader)s for the uploader name,
+                             %(autonumber)s to get an automatically incremented
+                             number, %(ext)s for the filename extension, and %%
+                             for a literal percent
     -a, --batch-file FILE    file containing URLs to download ('-' for stdin)
     -w, --no-overwrites      do not overwrite files
     -c, --continue           resume partially downloaded files
     --no-continue            do not resume partially downloaded files (restart
                              from beginning)
-    --cookies FILE           file to dump cookie jar to
+    --cookies FILE           file to read cookies from and dump cookie jar in
     --no-part                do not use .part files
     --no-mtime               do not use the Last-modified header to set the file
                              modification time
@@ -73,7 +77,7 @@ which means you can modify it, redistribute it or use it however you like.
 ### Post-processing Options:
     --extract-audio          convert video files to audio-only files (requires
                              ffmpeg and ffprobe)
-    --audio-format FORMAT    "best", "aac" or "mp3"; best by default
+    --audio-format FORMAT    "best", "aac", "vorbis" or "mp3"; best by default
     --audio-quality QUALITY  ffmpeg audio bitrate specification, 128k by default
     -k, --keep-video         keeps the video file on disk after the post-
                              processing; the video is erased by default

youtube-dl

@@ -15,7 +15,7 @@ __author__  = (
 	)
 
 __license__ = 'Public Domain'
-__version__ = '2011.09.18'
+__version__ = '2011.09.27'
 
 UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
 
@@ -766,7 +766,8 @@ class FileDownloader(object):
 			try:
 				infof = open(infofn, 'wb')
 				try:
-					json.dump(info_dict, infof)
+					json_info_dict = dict((k,v) for k,v in info_dict.iteritems() if not k in ('urlhandle',))
+					json.dump(json_info_dict, infof)
 				finally:
 					infof.close()
 			except (OSError, IOError):
@@ -905,6 +906,8 @@ class FileDownloader(object):
 		while count <= retries:
 			# Establish connection
 			try:
+				if count == 0 and 'urlhandle' in info_dict:
+					data = info_dict['urlhandle']
 				data = urllib2.urlopen(request)
 				break
 			except (urllib2.HTTPError, ), err:
@@ -982,10 +985,13 @@ class FileDownloader(object):
 			block_size = self.best_block_size(after - before, len(data_block))
 
 			# Progress message
-			percent_str = self.calc_percent(byte_counter, data_len)
-			eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
 			speed_str = self.calc_speed(start, time.time(), byte_counter - resume_len)
-			self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+			if data_len is None:
+				self.report_progress('Unknown %', data_len_str, speed_str, 'Unknown ETA')
+			else:
+				percent_str = self.calc_percent(byte_counter, data_len)
+				eta_str = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
+				self.report_progress(percent_str, data_len_str, speed_str, eta_str)
 
 			# Apply rate limit
 			self.slow_down(start, byte_counter - resume_len)
@@ -1079,13 +1085,13 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
 	"""Information extractor for youtube.com."""
 
-	_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+	_VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
 	_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'
 	_NETRC_MACHINE = 'youtube'
 	# Listed in order of quality
-	_available_formats = ['38', '37', '45', '22', '43', '35', '34', '18', '6', '5', '17', '13']
+	_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
 	_video_extensions = {
 		'13': '3gp',
 		'17': 'mp4',
@@ -1094,6 +1100,7 @@ class YoutubeIE(InfoExtractor):
 		'37': 'mp4',
 		'38': 'video', # You actually don't know if this will be MOV, AVI or whatever
 		'43': 'webm',
+		'44': 'webm',
 		'45': 'webm',
 	}
 	IE_NAME = u'youtube'
@@ -2428,7 +2435,7 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
 	"""Information Extractor for YouTube playlists."""
 
-	_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+	_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)([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 = r'/watch\?v=(.+?)&'
 	_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
@@ -2502,7 +2509,7 @@ class YoutubePlaylistIE(InfoExtractor):
 class YoutubeUserIE(InfoExtractor):
 	"""Information Extractor for YouTube users."""
 
-	_VALID_URL = r'(?:(?:(?:http://)?(?:\w+\.)?youtube.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
+	_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
 	_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
 	_GDATA_PAGE_SIZE = 50
 	_GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
@@ -2590,7 +2597,7 @@ class YoutubeUserIE(InfoExtractor):
 class DepositFilesIE(InfoExtractor):
 	"""Information extractor for depositfiles.com"""
 
-	_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles.com/(?:../(?#locale))?files/(.+)'
+	_VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
 	IE_NAME = u'DepositFiles'
 
 	def __init__(self, downloader=None):
@@ -2667,7 +2674,7 @@ class DepositFilesIE(InfoExtractor):
 class FacebookIE(InfoExtractor):
 	"""Information Extractor for Facebook"""
 
-	_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook.com/video/video.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+	_VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.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'
 	_available_formats = ['highqual', 'lowqual']
@@ -2891,7 +2898,11 @@ class BlipTVIE(InfoExtractor):
 
 	def report_extraction(self, file_id):
 		"""Report information extraction."""
-		self._downloader.to_screen(u'[blip.tv] %s: Extracting information' % file_id)
+		self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+	def report_direct_download(self, title):
+		"""Report information extraction."""
+		self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
 
 	def _simplify_title(self, title):
 		res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
@@ -2911,43 +2922,64 @@ class BlipTVIE(InfoExtractor):
 		json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
 		request = urllib2.Request(json_url)
 		self.report_extraction(mobj.group(1))
+		info = None
 		try:
-			json_code = urllib2.urlopen(request).read()
+			urlh = urllib2.urlopen(request)
+			if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
+				basename = url.split('/')[-1]
+				title,ext = os.path.splitext(basename)
+				ext = ext.replace('.', '')
+				self.report_direct_download(title)
+				info = {
+					'id': title,
+					'url': url,
+					'title': title,
+					'stitle': self._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))
 			return
-		try:
+		if info is None: # Regular URL
-			json_data = json.loads(json_code)
+			try:
-			if 'Post' in json_data:
+				json_code = urlh.read()
-				data = json_data['Post']
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
-			else:
+				self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
-				data = json_data
+				return
 
-			upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+			try:
-			video_url = data['media']['url']
+				json_data = json.loads(json_code)
-			umobj = re.match(self._URL_EXT, video_url)
+				if 'Post' in json_data:
-			if umobj is None:
+					data = json_data['Post']
-				raise ValueError('Can not determine filename extension')
+				else:
-			ext = umobj.group(1)
+					data = json_data
+	
+				upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
+				video_url = data['media']['url']
+				umobj = re.match(self._URL_EXT, video_url)
+				if umobj is None:
+					raise ValueError('Can not determine filename extension')
+				ext = umobj.group(1)
+	
+				info = {
+					'id': data['item_id'],
+					'url': video_url,
+					'uploader': data['display_name'],
+					'upload_date': upload_date,
+					'title': data['title'],
+					'stitle': self._simplify_title(data['title']),
+					'ext': ext,
+					'format': data['media']['mimeType'],
+					'thumbnail': data['thumbnailUrl'],
+					'description': data['description'],
+					'player_url': data['embedUrl']
+				}
+			except (ValueError,KeyError), err:
+				self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
+				return
 
-			self._downloader.increment_downloads()
+		self._downloader.increment_downloads()
-
-			info = {
-				'id': data['item_id'],
-				'url': video_url,
-				'uploader': data['display_name'],
-				'upload_date': upload_date,
-				'title': data['title'],
-				'stitle': self._simplify_title(data['title']),
-				'ext': ext,
-				'format': data['media']['mimeType'],
-				'thumbnail': data['thumbnailUrl'],
-				'description': data['description'],
-				'player_url': data['embedUrl']
-			}
-		except (ValueError,KeyError), err:
-			self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
-			return
 
 		try:
 			self._downloader.process_info(info)
@@ -3013,7 +3045,6 @@ class MyVideoIE(InfoExtractor):
 		video_title = sanitize_title(video_title)
 
 		try:
-			print(video_url)
 			self._downloader.process_info({
 				'id':		video_id,
 				'url':		video_url,
@@ -3172,7 +3203,7 @@ class ComedyCentralIE(InfoExtractor):
 class EscapistIE(InfoExtractor):
 	"""Information extractor for The Escapist """
 
-	_VALID_URL = r'^(https?://)?(www\.)escapistmagazine.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?].*$'
+	_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
 	IE_NAME = u'escapist'
 
 	def report_extraction(self, showName):
@@ -3347,12 +3378,14 @@ class FFmpegExtractAudioPP(PostProcessor):
 
 		more_opts = []
 		if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
-			if filecodec == 'aac' or filecodec == 'mp3':
+			if filecodec in ['aac', 'mp3', 'vorbis']:
 				# Lossless if possible
 				acodec = 'copy'
 				extension = filecodec
 				if filecodec == 'aac':
 					more_opts = ['-f', 'adts']
+				if filecodec == 'vorbis':
+					extension = 'ogg'
 			else:
 				# MP3 otherwise.
 				acodec = 'libmp3lame'
@@ -3362,13 +3395,15 @@ class FFmpegExtractAudioPP(PostProcessor):
 					more_opts += ['-ab', self._preferredquality]
 		else:
 			# We convert the audio (lossy)
-			acodec = {'mp3': 'libmp3lame', 'aac': 'aac'}[self._preferredcodec]
+			acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
 			extension = self._preferredcodec
 			more_opts = []
 			if self._preferredquality is not None:
 				more_opts += ['-ab', self._preferredquality]
 			if self._preferredcodec == 'aac':
 				more_opts += ['-f', 'adts']
+			if self._preferredcodec == 'vorbis':
+				extension = 'ogg'
 
 		(prefix, ext) = os.path.splitext(path)
 		new_path = prefix + '.' + extension
@@ -3409,6 +3444,11 @@ def updateSelf(downloader, filename):
 		try:
 			urlh = urllib.urlopen(UPDATE_URL)
 			newcontent = urlh.read()
+			
+			vmatch = re.search("__version__ = '([^']+)'", newcontent)
+			if vmatch is not None and vmatch.group(1) == __version__:
+				downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')')
+				return
 		finally:
 			urlh.close()
 	except (IOError, OSError), err:
@@ -3423,7 +3463,7 @@ def updateSelf(downloader, filename):
 	except (IOError, OSError), err:
 		sys.exit('ERROR: unable to overwrite current version')
 
-	downloader.to_screen('Updated youtube-dl. Restart to use the new version.')
+	downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')
 
 def parseOpts():
 	# Deferred imports
@@ -3563,7 +3603,7 @@ def parseOpts():
 			action='store_true', dest='autonumber',
 			help='number downloaded files starting from 00000', default=False)
 	filesystem.add_option('-o', '--output',
-			dest='outtmpl', metavar='TEMPLATE', help='output filename template')
+			dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, and %% for a literal percent')
 	filesystem.add_option('-a', '--batch-file',
 			dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
 	filesystem.add_option('-w', '--no-overwrites',
@@ -3574,7 +3614,7 @@ def parseOpts():
 			action='store_false', dest='continue_dl',
 			help='do not resume partially downloaded files (restart from beginning)')
 	filesystem.add_option('--cookies',
-			dest='cookiefile', metavar='FILE', help='file to dump cookie jar to')
+			dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
 	filesystem.add_option('--no-part',
 			action='store_true', dest='nopart', help='do not use .part files', default=False)
 	filesystem.add_option('--no-mtime',
@@ -3591,7 +3631,7 @@ def parseOpts():
 	postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
 			help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
 	postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
-			help='"best", "aac" or "mp3"; best by default')
+			help='"best", "aac", "vorbis" or "mp3"; best by default')
 	postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
 			help='ffmpeg audio bitrate specification, 128k by default')
 	postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
@@ -3618,12 +3658,12 @@ def gen_extractors():
 	google_ie = GoogleIE()
 	yahoo_ie = YahooIE()
 	return [
-		youtube_ie,
-		MetacafeIE(youtube_ie),
-		DailymotionIE(),
 		YoutubePlaylistIE(youtube_ie),
 		YoutubeUserIE(youtube_ie),
 		YoutubeSearchIE(youtube_ie),
+		youtube_ie,
+		MetacafeIE(youtube_ie),
+		DailymotionIE(),
 		google_ie,
 		GoogleSearchIE(google_ie),
 		PhotobucketIE(),
@@ -3725,7 +3765,7 @@ def main():
 	except (TypeError, ValueError), err:
 		parser.error(u'invalid playlist end number specified')
 	if opts.extractaudio:
-		if opts.audioformat not in ['best', 'aac', 'mp3']:
+		if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
 			parser.error(u'invalid audio format specified')
 
 	# File downloader