New optoin --restrict-filenames

3 files changed, 46 insertions, 37 deletions

diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py
index 37a842cdd..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
@@ -349,7 +350,7 @@ class FileDownloader(object):
 	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:
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index bf4b55f48..1109e05cd 100644
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -272,6 +272,9 @@ def parseOpts():
 			help='number downloaded files starting from 00000', default=False)
 	filesystem.add_option('-o', '--output',
 			dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)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, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout.')
+	filesystem.add_option('--restrict-filenames',
+			action='store_true', dest='restrictfilenames',
+			help='Avoid some characters such as "&" and spaces in filenames', default=False)
 	filesystem.add_option('-a', '--batch-file',
 			dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
 	filesystem.add_option('-w', '--no-overwrites',
@@ -485,6 +488,7 @@ def _real_main():
 			or (opts.useid and u'%(id)s.%(ext)s')
 			or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
 			or u'%(id)s.%(ext)s'),
+		'restrictfilenames': opts.restrictfilenames,
 		'ignoreerrors': opts.ignoreerrors,
 		'ratelimit': opts.ratelimit,
 		'nooverwrites': opts.nooverwrites,
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 658fd2686..55f2fe02c 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -194,18 +194,22 @@ def timeconvert(timestr):
 	if timetuple is not None:
 		timestamp = email.utils.mktime_tz(timetuple)
 	return timestamp
-	
-def sanitize_filename(s):
-	"""Sanitizes a string so it could be used as part of a filename."""
+
+def sanitize_filename(s, restricted=False):
+	"""Sanitizes a string so it could be used as part of a filename.
+	If restricted is set, use a stricter subset of allowed characters.
+	"""
 	def replace_insane(char):
 		if char == '?' or ord(char) < 32 or ord(char) == 127:
 			return ''
 		elif char == '"':
-			return '\''
+			return '' if restricted else 'FOO\''
 		elif char == ':':
-			return ' -'
+			return '_-' if restricted else ' -'
 		elif char in '\\/|*<>':
 			return '-'
+		if restricted and (char in '&\'' or char.isspace()):
+			return '_'
 		return char
 
 	result = u''.join(map(replace_insane, s))