Bump version number

interrupted downloads will properly resume and append to the previously downloaded data, instead of overwriting the file.

There's some error checking - if the length of the file to be download matches the length of the previously downloaded data, we report that this file has already been downloaded and do nothing.

If there is some other HTTP 416 'Requested range not satisfiable' error, we simply re-download the whole file (reverting to the original functionality)

All other HTTP errors are simply raised.

Resuming does not override -w (--nooverwrite), since it is not clear what should happen if file on disk is larger than file to be downloaded.

Thus, -c does nothing if -w is present.

.hgignore

@@ -1,2 +0,0 @@
-syntax: glob
-.*.swp

LATEST_VERSION

@@ -0,0 +1 @@
+2009.05.30

youtube-dl

@@ -52,6 +52,29 @@ class PostProcessingError(Exception):
 	"""
 	pass
 
+class UnavailableFormatError(Exception):
+	"""Unavailable Format exception.
+
+	This exception will be thrown when a video is requested
+	in a format that is not available for that video.
+	"""
+	pass
+
+class ContentTooShortError(Exception):
+	"""Content Too Short exception.
+
+	This exception may be raised by FileDownloader objects when a file they
+	download is too small for what the server announced first, indicating
+	the connection was probably interrupted.
+	"""
+	# Both in bytes
+	downloaded = None
+	expected = None
+
+	def __init__(self, downloaded, expected):
+		self.downloaded = downloaded
+		self.expected = expected
+
 class FileDownloader(object):
 	"""File Downloader class.
 
@@ -91,6 +114,7 @@ class FileDownloader(object):
 	ignoreerrors:	Do not stop on download errors.
 	ratelimit:	Download speed limit, in bytes/sec.
 	nooverwrites:	Prevent overwriting files.
+	continuedl:	Try to continue downloads if possible.
 	"""
 
 	params = None
@@ -159,13 +183,13 @@ class FileDownloader(object):
 		new_min = max(bytes / 2.0, 1.0)
 		new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
 		if elapsed_time < 0.001:
-			return int(new_max)
+			return long(new_max)
 		rate = bytes / elapsed_time
 		if rate > new_max:
-			return int(new_max)
+			return long(new_max)
 		if rate < new_min:
-			return int(new_min)
-		return int(rate)
+			return long(new_min)
+		return long(rate)
 
 	@staticmethod
 	def parse_bytes(bytestr):
@@ -177,6 +201,14 @@ class FileDownloader(object):
 		multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
 		return long(round(number * multiplier))
 
+	@staticmethod
+	def verify_url(url):
+		"""Verify a URL is valid and data could be downloaded."""
+		request = urllib2.Request(url, None, std_headers)
+		data = urllib2.urlopen(request)
+		data.read(1)
+		data.close()
+
 	def add_info_extractor(self, ie):
 		"""Add an InfoExtractor object to the end of the list."""
 		self._ies.append(ie)
@@ -235,6 +267,18 @@ class FileDownloader(object):
 		"""Report download progress."""
 		self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
 				(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+
+	def report_resuming_byte(self, resume_len):
+		"""Report attemtp to resume at given byte."""
+		self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+	
+	def report_file_already_downloaded(self, file_name):
+		"""Report file has already been fully downloaded."""
+		self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+	
+	def report_unable_to_resume(self):
+		"""Report it was impossible to resume download."""
+		self.to_stdout(u'[download] Unable to resume')
 	
 	def report_finish(self):
 		"""Report download finished."""
@@ -242,51 +286,64 @@ class FileDownloader(object):
 
 	def process_info(self, info_dict):
 		"""Process a single dictionary returned by an InfoExtractor."""
-		# Forced printings
-		if self.params.get('forcetitle', False):
-			print info_dict['title'].encode(locale.getpreferredencoding())
-		if self.params.get('forceurl', False):
-			print info_dict['url'].encode(locale.getpreferredencoding())
-			
 		# Do nothing else if in simulate mode
 		if self.params.get('simulate', False):
-			return
+			try:
+				self.verify_url(info_dict['url'])
+			except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
+				raise UnavailableFormatError
 
+			# Forced printings
+			if self.params.get('forcetitle', False):
+				print info_dict['title'].encode(locale.getpreferredencoding())
+			if self.params.get('forceurl', False):
+				print info_dict['url'].encode(locale.getpreferredencoding())
+
+			return
+			
 		try:
-			filename = self.params['outtmpl'] % info_dict
+			template_dict = dict(info_dict)
+			template_dict['epoch'] = unicode(long(time.time()))
+			filename = self.params['outtmpl'] % template_dict
 			self.report_destination(filename)
 		except (ValueError, KeyError), err:
 			self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
 		if self.params['nooverwrites'] and os.path.exists(filename):
 			self.to_stderr('WARNING: file exists: %s; skipping' % filename)
 			return
+
 		try:
 			self.pmkdir(filename)
 		except (OSError, IOError), err:
 			self.trouble('ERROR: unable to create directories: %s' % str(err))
 			return
+
 		try:
-			outstream = open(filename, 'wb')
+			outstream = open(filename, 'ab')
 		except (OSError, IOError), err:
 			self.trouble('ERROR: unable to open for writing: %s' % str(err))
 			return
+
 		try:
 			self._do_download(outstream, info_dict['url'])
 			outstream.close()
 		except (OSError, IOError), err:
-			self.trouble('ERROR: unable to write video data: %s' % str(err))
-			return
+			outstream.close()
+			os.remove(filename)
+			raise UnavailableFormatError
 		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
 			self.trouble('ERROR: unable to download video data: %s' % str(err))
 			return
+		except (ContentTooShortError, ), err:
+			self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+			return
+
 		try:
 			self.post_process(filename, info_dict)
 		except (PostProcessingError), err:
 			self.trouble('ERROR: postprocessing: %s' % str(err))
 			return
 
-		return
-
 	def download(self, url_list):
 		"""Download a given list of URLs."""
 		if len(url_list) > 1 and self.fixed_template():
@@ -323,8 +380,32 @@ class FileDownloader(object):
 				break
 	
 	def _do_download(self, stream, url):
+		basic_request = urllib2.Request(url, None, std_headers)
 		request = urllib2.Request(url, None, std_headers)
-		data = urllib2.urlopen(request)
+
+		# Resume transfer if filesize is non-zero
+		resume_len = stream.tell()
+		if self.params['continuedl'] and resume_len != 0:
+			self.report_resuming_byte(resume_len)
+			request.add_header('Range','bytes=%d-' % resume_len)
+		else:
+			stream.close()
+			stream = open(stream.name,'wb')
+		try:
+			data = urllib2.urlopen(request)
+		except urllib2.HTTPError, e:
+			if not e.code == 416: #  416 is 'Requested range not satisfiable'
+				raise
+			data = urllib2.urlopen(basic_request)
+			content_length = data.info()['Content-Length']
+			if content_length is not None and long(content_length) == resume_len:
+				self.report_file_already_downloaded(stream.name)
+				return
+			else:
+				self.report_unable_to_resume()
+				stream.close()
+				stream = open(stream.name,'wb')
+
 		data_len = data.info().get('Content-length', None)
 		data_len_str = self.format_bytes(data_len)
 		byte_counter = 0
@@ -353,7 +434,7 @@ class FileDownloader(object):
 
 		self.report_finish()
 		if data_len is not None and str(byte_counter) != data_len:
-			raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
+			raise ContentTooShortError(byte_counter, long(data_len))
 
 class InfoExtractor(object):
 	"""Information Extractor class.
@@ -424,6 +505,13 @@ class YoutubeIE(InfoExtractor):
 	_LOGIN_URL = 'http://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'
+	_available_formats = ['22', '35', '18', '17', '13'] # listed in order of priority for -b flag
+	_video_extensions = {
+		'13': '3gp',
+		'17': 'mp4',
+		'18': 'mp4',
+		'22': 'mp4',
+	}
 
 	@staticmethod
 	def suitable(url):
@@ -476,6 +564,10 @@ class YoutubeIE(InfoExtractor):
 		"""Report extracted video URL."""
 		self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
 	
+	def report_unavailable_format(self, video_id, format):
+		"""Report extracted video URL."""
+		self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
+	
 	def _real_initialize(self):
 		if self._downloader is None:
 			return
@@ -554,70 +646,91 @@ class YoutubeIE(InfoExtractor):
 		video_id = mobj.group(2)
 
 		# Downloader parameters
+		best_quality = False
 		format_param = None
+		quality_index = 0
 		if self._downloader is not None:
 			params = self._downloader.params
 			format_param = params.get('format', None)
+			if format_param == '0':
+				format_param = self._available_formats[quality_index]
+				best_quality = True
 
-		# Extension
-		video_extension = {
-			'17': '3gp',
-			'18': 'mp4',
-			'22': 'mp4',
-		}.get(format_param, 'flv')
+		while True:
+			# Extension
+			video_extension = self._video_extensions.get(format_param, 'flv')
 
-		# Normalize URL, including format
-		normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
-		if format_param is not None:
-			normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
-		request = urllib2.Request(normalized_url, None, std_headers)
-		try:
-			self.report_webpage_download(video_id)
-			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))
-			return
-		self.report_information_extraction(video_id)
-		
-		# "t" param
-		mobj = re.search(r', "t": "([^"]+)"', video_webpage)
-		if mobj is None:
-			self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
-			return
-		video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
-		if format_param is not None:
-			video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
-		self.report_video_url(video_id, video_real_url)
+			# Normalize URL, including format
+			normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
+			if format_param is not None:
+				normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
+			request = urllib2.Request(normalized_url, None, std_headers)
+			try:
+				self.report_webpage_download(video_id)
+				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))
+				return
+			self.report_information_extraction(video_id)
+			
+			# "t" param
+			mobj = re.search(r', "t": "([^"]+)"', video_webpage)
+			if mobj is None:
+				self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
+				return
+			video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
+			if format_param is not None:
+				video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
+			self.report_video_url(video_id, video_real_url)
 
-		# uploader
-		mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
-		if mobj is None:
-			self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
-			return
-		video_uploader = mobj.group(1)
+			# uploader
+			mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
+			if mobj is None:
+				self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+				return
+			video_uploader = mobj.group(1)
 
-		# title
-		mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
-		if mobj is None:
-			self._downloader.trouble(u'ERROR: unable to extract video title')
-			return
-		video_title = mobj.group(1).decode('utf-8')
-		video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
-		video_title = video_title.replace(os.sep, u'%')
+			# title
+			mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
+			if mobj is None:
+				self._downloader.trouble(u'ERROR: unable to extract video title')
+				return
+			video_title = mobj.group(1).decode('utf-8')
+			video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
+			video_title = video_title.replace(os.sep, u'%')
 
-		# simplified title
-		simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
-		simple_title = simple_title.strip(ur'_')
+			# simplified title
+			simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+			simple_title = simple_title.strip(ur'_')
+
+			try:
+				# Process video information
+				self._downloader.process_info({
+					'id':		video_id.decode('utf-8'),
+					'url':		video_real_url.decode('utf-8'),
+					'uploader':	video_uploader.decode('utf-8'),
+					'title':	video_title,
+					'stitle':	simple_title,
+					'ext':		video_extension.decode('utf-8'),
+				})
+
+				return
+
+			except UnavailableFormatError, err:
+				if best_quality:
+					if quality_index == len(self._available_formats) - 1:
+						# I don't ever expect this to happen
+						self._downloader.trouble(u'ERROR: no known formats available for video')
+						return
+					else:
+						self.report_unavailable_format(video_id, format_param)
+						quality_index += 1
+						format_param = self._available_formats[quality_index]
+						continue
+				else: 
+					self._downloader.trouble('ERROR: format not available for video')
+					return
 
-		# Process video information
-		self._downloader.process_info({
-			'id':		video_id.decode('utf-8'),
-			'url':		video_real_url.decode('utf-8'),
-			'uploader':	video_uploader.decode('utf-8'),
-			'title':	video_title,
-			'stitle':	simple_title,
-			'ext':		video_extension.decode('utf-8'),
-			})
 
 class MetacafeIE(InfoExtractor):
 	"""Information Extractor for metacafe.com."""
@@ -729,15 +842,18 @@ class MetacafeIE(InfoExtractor):
 			return
 		video_uploader = mobj.group(1)
 
-		# Process video information
-		self._downloader.process_info({
-			'id':		video_id.decode('utf-8'),
-			'url':		video_url.decode('utf-8'),
-			'uploader':	video_uploader.decode('utf-8'),
-			'title':	video_title,
-			'stitle':	simple_title,
-			'ext':		video_extension.decode('utf-8'),
+		try:
+			# Process video information
+			self._downloader.process_info({
+				'id':		video_id.decode('utf-8'),
+				'url':		video_url.decode('utf-8'),
+				'uploader':	video_uploader.decode('utf-8'),
+				'title':	video_title,
+				'stitle':	simple_title,
+				'ext':		video_extension.decode('utf-8'),
 			})
+		except UnavailableFormatError:
+			self._downloader.trouble(u'ERROR: format not available for video')
 
 
 class YoutubeSearchIE(InfoExtractor):
@@ -780,7 +896,7 @@ class YoutubeSearchIE(InfoExtractor):
 			return
 		else:
 			try:
-				n = int(prefix)
+				n = long(prefix)
 				if n <= 0:
 					self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
 					return
@@ -789,7 +905,7 @@ class YoutubeSearchIE(InfoExtractor):
 					n = self._max_youtube_results
 				self._download_n_results(query, n)
 				return
-			except ValueError: # parsing prefix as int fails
+			except ValueError: # parsing prefix as integer fails
 				self._download_n_results(query, 1)
 				return
 
@@ -919,7 +1035,7 @@ class PostProcessor(object):
 		"""Run the PostProcessor.
 
 		The "information" argument is a dictionary like the ones
-		returned by InfoExtractors. The only difference is that this
+		composed by InfoExtractors. The only difference is that this
 		one has an extra field called "filepath" that points to the
 		downloaded file.
 
@@ -949,76 +1065,96 @@ if __name__ == '__main__':
 
 		# Parse command line
 		parser = optparse.OptionParser(
-				usage='Usage: %prog [options] url...',
-				version='2009.04.25',
-				conflict_handler='resolve',
-				)
+			usage='Usage: %prog [options] url...',
+			version='2009.05.30',
+			conflict_handler='resolve',
+		)
+
 		parser.add_option('-h', '--help',
 				action='help', help='print this help text and exit')
 		parser.add_option('-v', '--version',
 				action='version', help='print program version and exit')
-		parser.add_option('-u', '--username',
-				dest='username', metavar='UN', help='account username')
-		parser.add_option('-p', '--password',
-				dest='password', metavar='PW', help='account password')
-		parser.add_option('-o', '--output',
-				dest='outtmpl', metavar='TPL', help='output filename template')
-		parser.add_option('-q', '--quiet',
-				action='store_true', dest='quiet', help='activates quiet mode', default=False)
-		parser.add_option('-s', '--simulate',
-				action='store_true', dest='simulate', help='do not download video', default=False)
-		parser.add_option('-t', '--title',
-				action='store_true', dest='usetitle', help='use title in file name', default=False)
-		parser.add_option('-l', '--literal',
-				action='store_true', dest='useliteral', help='use literal title in file name', default=False)
-		parser.add_option('-n', '--netrc',
-				action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
-		parser.add_option('-g', '--get-url',
-				action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
-		parser.add_option('-e', '--get-title',
-				action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
-		parser.add_option('-f', '--format',
-				dest='format', metavar='FMT', help='video format code')
-		parser.add_option('-m', '--mobile-version',
-				action='store_const', dest='format', help='alias for -f 17', const='17')
-		parser.add_option('-d', '--high-def',
-				action='store_const', dest='format', help='alias for -f 22', const='22')
 		parser.add_option('-i', '--ignore-errors',
 				action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
 		parser.add_option('-r', '--rate-limit',
 				dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
-		parser.add_option('-a', '--batch-file',
+
+		authentication = optparse.OptionGroup(parser, 'Authentication Options')
+		authentication.add_option('-u', '--username',
+				dest='username', metavar='UN', help='account username')
+		authentication.add_option('-p', '--password',
+				dest='password', metavar='PW', help='account password')
+		authentication.add_option('-n', '--netrc',
+				action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
+		parser.add_option_group(authentication)
+
+		video_format = optparse.OptionGroup(parser, 'Video Format Options')
+		video_format.add_option('-f', '--format',
+				action='store', dest='format', metavar='FMT', help='video format code')
+		video_format.add_option('-b', '--best-quality',
+				action='store_const', dest='format', help='download the best quality video possible', const='0')
+		video_format.add_option('-m', '--mobile-version',
+				action='store_const', dest='format', help='alias for -f 17', const='17')
+		video_format.add_option('-d', '--high-def',
+				action='store_const', dest='format', help='alias for -f 22', const='22')
+		parser.add_option_group(video_format)
+
+		verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+		verbosity.add_option('-q', '--quiet',
+				action='store_true', dest='quiet', help='activates quiet mode', default=False)
+		verbosity.add_option('-s', '--simulate',
+				action='store_true', dest='simulate', help='do not download video', default=False)
+		verbosity.add_option('-g', '--get-url',
+				action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
+		verbosity.add_option('-e', '--get-title',
+				action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
+		parser.add_option_group(verbosity)
+
+		filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
+		filesystem.add_option('-t', '--title',
+				action='store_true', dest='usetitle', help='use title in file name', default=False)
+		filesystem.add_option('-l', '--literal',
+				action='store_true', dest='useliteral', help='use literal title in file name', default=False)
+		filesystem.add_option('-o', '--output',
+				dest='outtmpl', metavar='TPL', help='output filename template')
+		filesystem.add_option('-a', '--batch-file',
 				dest='batchfile', metavar='F', help='file containing URLs to download')
-		parser.add_option('-w', '--no-overwrites',
+		filesystem.add_option('-w', '--no-overwrites',
 				action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+		filesystem.add_option('-c', '--continue',
+				action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
+		parser.add_option_group(filesystem)
+
 		(opts, args) = parser.parse_args()
 
 		# Batch file verification
 		batchurls = []
 		if opts.batchfile is not None:
 			try:
-				batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+				batchurls = open(opts.batchfile, 'r').readlines()
+				batchurls = [x.strip() for x in batchurls]
+				batchurls = [x for x in batchurls if len(x) > 0]
 			except IOError:
 				sys.exit(u'ERROR: batch file could not be read')
 		all_urls = batchurls + args
 
 		# Conflicting, missing and erroneous options
 		if len(all_urls) < 1:
-			sys.exit(u'ERROR: you must provide at least one URL')
+			parser.error(u'you must provide at least one URL')
 		if opts.usenetrc and (opts.username is not None or opts.password is not None):
-			sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
+			parser.error(u'using .netrc conflicts with giving username/password')
 		if opts.password is not None and opts.username is None:
-			sys.exit(u'ERROR: account username missing')
+			parser.error(u'account username missing')
 		if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
-			sys.exit(u'ERROR: using output template conflicts with using title or literal title')
+			parser.error(u'using output template conflicts with using title or literal title')
 		if opts.usetitle and opts.useliteral:
-			sys.exit(u'ERROR: using title conflicts with using literal title')
+			parser.error(u'using title conflicts with using literal title')
 		if opts.username is not None and opts.password is None:
 			opts.password = getpass.getpass(u'Type account password and press return:')
 		if opts.ratelimit is not None:
 			numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
 			if numeric_limit is None:
-				sys.exit(u'ERROR: invalid rate limit specified')
+				parser.error(u'invalid rate limit specified')
 			opts.ratelimit = numeric_limit
 
 		# Information extractors
@@ -1044,6 +1180,7 @@ if __name__ == '__main__':
 			'ignoreerrors': opts.ignoreerrors,
 			'ratelimit': opts.ratelimit,
 			'nooverwrites': opts.nooverwrites,
+			'continuedl': opts.continue_dl,
 			})
 		fd.add_info_extractor(youtube_search_ie)
 		fd.add_info_extractor(youtube_pl_ie)