aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/utils.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/utils.py')
-rw-r--r--youtube_dl/utils.py40
1 files changed, 33 insertions, 7 deletions
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 922e17ecc..4ace22c2f 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.
@@ -83,7 +88,6 @@ 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
@@ -190,14 +194,36 @@ 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 """