diff options
Diffstat (limited to 'youtube_dl/FileDownloader.py')
| -rw-r--r-- | youtube_dl/FileDownloader.py | 105 | 
1 files changed, 56 insertions, 49 deletions
| diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index ed5a79f13..4c79be432 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -44,37 +44,38 @@ class FileDownloader(object):  	Available options: -	username:         Username for authentication purposes. -	password:         Password for authentication purposes. -	usenetrc:         Use netrc for authentication instead. -	quiet:            Do not print messages to stdout. -	forceurl:         Force printing final URL. -	forcetitle:       Force printing title. -	forcethumbnail:   Force printing thumbnail URL. -	forcedescription: Force printing description. -	forcefilename:    Force printing final filename. -	simulate:         Do not download the video files. -	format:           Video format code. -	format_limit:     Highest quality format to try. -	outtmpl:          Template for output names. -	ignoreerrors:     Do not stop on download errors. -	ratelimit:        Download speed limit, in bytes/sec. -	nooverwrites:     Prevent overwriting files. -	retries:          Number of times to retry for HTTP error 5xx -	continuedl:       Try to continue downloads if possible. -	noprogress:       Do not print the progress bar. -	playliststart:    Playlist item to start at. -	playlistend:      Playlist item to end at. -	matchtitle:       Download only matching titles. -	rejecttitle:      Reject downloads for matching titles. -	logtostderr:      Log messages to stderr instead of stdout. -	consoletitle:     Display progress in console window's titlebar. -	nopart:           Do not use temporary .part files. -	updatetime:       Use the Last-modified header to set output file timestamps. -	writedescription: Write the video description to a .description file -	writeinfojson:    Write the video description to a .info.json file -	writesubtitles:   Write the video subtitles to a .srt file -	subtitleslang:    Language of the subtitles to download +	username:          Username for authentication purposes. +	password:          Password for authentication purposes. +	usenetrc:          Use netrc for authentication instead. +	quiet:             Do not print messages to stdout. +	forceurl:          Force printing final URL. +	forcetitle:        Force printing title. +	forcethumbnail:    Force printing thumbnail URL. +	forcedescription:  Force printing description. +	forcefilename:     Force printing final filename. +	simulate:          Do not download the video files. +	format:            Video format code. +	format_limit:      Highest quality format to try. +	outtmpl:           Template for output names. +	restrictfilenames: Do not allow "&" and spaces in file names +	ignoreerrors:      Do not stop on download errors. +	ratelimit:         Download speed limit, in bytes/sec. +	nooverwrites:      Prevent overwriting files. +	retries:           Number of times to retry for HTTP error 5xx +	continuedl:        Try to continue downloads if possible. +	noprogress:        Do not print the progress bar. +	playliststart:     Playlist item to start at. +	playlistend:       Playlist item to end at. +	matchtitle:        Download only matching titles. +	rejecttitle:       Reject downloads for matching titles. +	logtostderr:       Log messages to stderr instead of stdout. +	consoletitle:      Display progress in console window's titlebar. +	nopart:            Do not use temporary .part files. +	updatetime:        Use the Last-modified header to set output file timestamps. +	writedescription:  Write the video description to a .description file +	writeinfojson:     Write the video description to a .info.json file +	writesubtitles:    Write the video subtitles to a .srt file +	subtitleslang:     Language of the subtitles to download  	"""  	params = None @@ -139,23 +140,23 @@ 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 long(new_max) +			return int(new_max)  		rate = bytes / elapsed_time  		if rate > new_max: -			return long(new_max) +			return int(new_max)  		if rate < new_min: -			return long(new_min) -		return long(rate) +			return int(new_min) +		return int(rate)  	@staticmethod  	def parse_bytes(bytestr): -		"""Parse a string indicating a byte quantity into a long integer.""" +		"""Parse a string indicating a byte quantity into an integer."""  		matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)  		if matchobj is None:  			return None  		number = float(matchobj.group(1))  		multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) -		return long(round(number * multiplier)) +		return int(round(number * multiplier))  	def add_info_extractor(self, ie):  		"""Add an InfoExtractor object to the end of the list.""" @@ -180,7 +181,8 @@ class FileDownloader(object):  	def to_stderr(self, message):  		"""Print message to stderr.""" -		print >>sys.stderr, message.encode(preferredencoding()) +		assert type(message) == type(u'') +		sys.stderr.write((message + u'\n').encode(preferredencoding()))  	def to_cons_title(self, message):  		"""Set console/terminal window title to message.""" @@ -322,6 +324,7 @@ class FileDownloader(object):  			template_dict = dict(info_dict)  			template_dict['epoch'] = unicode(long(time.time()))  			template_dict['autonumber'] = unicode('%05d' % self._num_downloads) +			template_dict['title'] = template_dict['stitle'] # Keep both for backwards compatibility  			filename = self.params['outtmpl'] % template_dict  			return filename  		except (ValueError, KeyError), err: @@ -333,17 +336,21 @@ class FileDownloader(object):  		title = info_dict['title']  		matchtitle = self.params.get('matchtitle', False) -		if matchtitle and not re.search(matchtitle, title, re.IGNORECASE): -			return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' +		if matchtitle: +			matchtitle = matchtitle.decode('utf8') +			if not re.search(matchtitle, title, re.IGNORECASE): +				return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'  		rejecttitle = self.params.get('rejecttitle', False) -		if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE): -			return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' +		if rejecttitle: +			rejecttitle = rejecttitle.decode('utf8') +			if re.search(rejecttitle, title, re.IGNORECASE): +				return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'  		return None  	def process_info(self, info_dict):  		"""Process a single dictionary returned by an InfoExtractor.""" -		info_dict['stitle'] = sanitize_filename(info_dict['title']) +		info_dict['stitle'] = sanitize_filename(info_dict['title'], self.params.get('restrictfilenames'))  		reason = self._match_entry(info_dict)  		if reason is not None: @@ -359,17 +366,17 @@ class FileDownloader(object):  		# Forced printings  		if self.params.get('forcetitle', False): -			print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace') +			print(info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace'))  		if self.params.get('forceurl', False): -			print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace') +			print(info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace'))  		if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: -			print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace') +			print(info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace'))  		if self.params.get('forcedescription', False) and 'description' in info_dict: -			print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace') +			print(info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace'))  		if self.params.get('forcefilename', False) and filename is not None: -			print filename.encode(preferredencoding(), 'xmlcharrefreplace') +			print(filename.encode(preferredencoding(), 'xmlcharrefreplace'))  		if self.params.get('forceformat', False): -			print info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace') +			print(info_dict['format'].encode(preferredencoding(), 'xmlcharrefreplace'))  		# Do nothing else if in simulate mode  		if self.params.get('simulate', False): | 
