X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=40d6823a0f8ddbbf42a54bf4b0aea9e344825600;hb=1a9c655e3b1569f315d4193e877cba0b4a863c63;hp=0f903c64a0d8c71517378143ecad1caf07cb5893;hpb=9beb5af82ecfbb35ee534692e73fb38f4399698a;p=youtube-dl

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 0f903c64a..40d6823a0 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -11,40 +11,39 @@ import sys
 import zlib
 import urllib2
 import email.utils
+import json
 
 try:
 	import cStringIO as StringIO
 except ImportError:
 	import StringIO
-		
-try:
-	import json
-except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
-	import trivialjson as json
 
 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.
 
 	Returns the best encoding scheme for the system, based on
 	locale.getpreferredencoding() and some further tweaks.
 	"""
-	def yield_preferredencoding():
-		try:
-			pref = locale.getpreferredencoding()
-			u'TEST'.encode(pref)
-		except:
-			pref = 'UTF-8'
-		while True:
-			yield pref
-	return yield_preferredencoding().next()
+	try:
+		pref = locale.getpreferredencoding()
+		u'TEST'.encode(pref)
+	except:
+		pref = 'UTF-8'
+
+	return pref
 
 
 def htmlentity_transform(matchobj):
@@ -87,7 +86,6 @@ class IDParser(HTMLParser.HTMLParser):
 		HTMLParser.HTMLParser.__init__(self)
 
 	def error(self, message):
-		print 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
@@ -160,12 +158,6 @@ def clean_html(html):
 	return html
 
 
-def sanitize_title(utitle):
-	"""Sanitizes a video title so it could be used as part of a filename."""
-	utitle = unescapeHTML(utitle)
-	return utitle.replace(unicode(os.sep), u'%')
-
-
 def sanitize_open(filename, open_mode):
 	"""Try to open the given filename, and slightly tweak it if this fails.
 
@@ -201,9 +193,35 @@ def timeconvert(timestr):
 		timestamp = email.utils.mktime_tz(timetuple)
 	return timestamp
 
-def simplify_title(title):
-	expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
-	return expr.sub(u'_', title).strip(u'_')
+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 '' 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
+
+	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 """
@@ -229,7 +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.)
@@ -294,6 +312,13 @@ class ContentTooShortError(Exception):
 		self.expected = expected
 
 
+class Trouble(Exception):
+	"""Trouble helper exception
+
+	This is an exception to be handled with
+	FileDownloader.trouble
+	"""
+
 class YoutubeDLHandler(urllib2.HTTPHandler):
 	"""Handler for HTTP requests and responses.