X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=blobdiff_plain;f=youtube_dl%2Futils.py;h=40d6823a0f8ddbbf42a54bf4b0aea9e344825600;hp=7faa046c8cf6f9a464f8de65cfd0c637664329ba;hb=1a9c655e3b1569f315d4193e877cba0b4a863c63;hpb=bae611f216ac7b1f1a24a506da6dffc518d09d5b

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 7faa046c8..40d6823a0 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -19,13 +19,18 @@ except ImportError:
 	import StringIO
 
 std_headers = {
-	'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:5.0.1) Gecko/20100101 Firefox/5.0.1',
+	'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
 	'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
 	'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
 	'Accept-Encoding': 'gzip, deflate',
 	'Accept-Language': 'en-us,en;q=0.5',
 }
 
+try:
+    compat_str = unicode # Python 2
+except NameError:
+    compat_str = str
+
 def preferredencoding():
 	"""Get preferred encoding.
 
@@ -81,7 +86,6 @@ class IDParser(HTMLParser.HTMLParser):
 		HTMLParser.HTMLParser.__init__(self)
 
 	def error(self, message):
-		print >> sys.stderr, self.getpos()
 		if self.error_count > 10 or self.started:
 			raise HTMLParser.HTMLParseError(message, self.getpos())
 		self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
@@ -188,14 +192,36 @@ 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 in u' .\\/|?*<>:"' or ord(char) < 32:
+		if char == '?' or ord(char) < 32 or ord(char) == 127:
+			return ''
+		elif char == '"':
+			return '' if restricted else '\''
+		elif char == ':':
+			return '_-' if restricted else ' -'
+		elif char in '\\/|*<>':
+			return '_'
+		if restricted and (char in '!&\'' or char.isspace()):
+			return '_'
+		if restricted and ord(char) > 127:
 			return '_'
 		return char
-	return u''.join(map(replace_insane, s)).strip('_')
+
+	result = u''.join(map(replace_insane, s))
+	while '__' in result:
+		result = result.replace('__', '_')
+	result = result.strip('_')
+	# Common case of "Foreign band name - English song title"
+	if restricted and result.startswith('-_'):
+		result = result[2:]
+	if not result:
+		result = '_'
+	return result
 
 def orderedSet(iterable):
 	""" Remove all duplicates from the input iterable """
@@ -221,7 +247,7 @@ def encodeFilename(s):
 
 	assert type(s) == type(u'')
 
-	if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
+	if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
 		# Pass u'' directly to use Unicode APIs on Windows 2000 and up
 		# (Detecting Windows NT 4 is tricky because 'major >= 4' would
 		# match Windows 9x series as well. Besides, NT 4 is obsolete.)
@@ -288,7 +314,7 @@ class ContentTooShortError(Exception):
 
 class Trouble(Exception):
 	"""Trouble helper exception
-	
+
 	This is an exception to be handled with
 	FileDownloader.trouble
 	"""