Update changelog.

[youtubedl] / youtube_dl / utils.py

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 5be7cf99200c57639af17b1dc89f9a861658f331..4d3cbac74aaebdbe0b314690b7dea07e2e2371e2 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -41,6 +41,7 @@ from .compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,

+    shlex_quote,

 )
 
 
 )
 
 


@@ -55,6 +56,7 @@ std_headers = {
     'Accept-Language': 'en-us,en;q=0.5',
 }
 
     'Accept-Language': 'en-us,en;q=0.5',
 }
 

+

 def preferredencoding():
     """Get preferred encoding.
 
 def preferredencoding():
     """Get preferred encoding.
 


@@ -129,7 +131,7 @@ if sys.version_info >= (2, 7):
         """ Find the xpath xpath[@key=val] """
         assert re.match(r'^[a-zA-Z-]+$', key)
         assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val)
         """ Find the xpath xpath[@key=val] """
         assert re.match(r'^[a-zA-Z-]+$', key)
         assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val)

-        expr = xpath + u"[@%s='%s']" % (key, val)
+        expr = xpath + "[@%s='%s']" % (key, val)

         return node.find(expr)
 else:
     def find_xpath_attr(node, xpath, key, val):
         return node.find(expr)
 else:
     def find_xpath_attr(node, xpath, key, val):


@@ -145,6 +147,8 @@ else:
 
 # On python2.6 the xml.etree.ElementTree.Element methods don't support
 # the namespace parameter
 
 # On python2.6 the xml.etree.ElementTree.Element methods don't support
 # the namespace parameter

+
+

 def xpath_with_ns(path, ns_map):
     components = [c.split(':') for c in path.split('/')]
     replaced = []
 def xpath_with_ns(path, ns_map):
     components = [c.split(':') for c in path.split('/')]
     replaced = []


@@ -236,9 +240,9 @@ def sanitize_open(filename, open_mode):
 
         # In case of error, try to remove win32 forbidden chars
         alt_filename = os.path.join(
 
         # In case of error, try to remove win32 forbidden chars
         alt_filename = os.path.join(

-                        re.sub('[/<>:"\\|\\\\?\\*]', '#', path_part)
-                        for path_part in os.path.split(filename)
-                       )
+            re.sub('[/<>:"\\|\\\\?\\*]', '#', path_part)
+            for path_part in os.path.split(filename)
+        )

         if alt_filename == filename:
             raise
         else:
         if alt_filename == filename:
             raise
         else:


@@ -255,6 +259,7 @@ def timeconvert(timestr):
         timestamp = email.utils.mktime_tz(timetuple)
     return timestamp
 
         timestamp = email.utils.mktime_tz(timetuple)
     return timestamp
 

+

 def sanitize_filename(s, restricted=False, is_id=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 sanitize_filename(s, restricted=False, is_id=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.


@@ -287,6 +292,7 @@ def sanitize_filename(s, restricted=False, is_id=False):
             result = '_'
     return result
 
             result = '_'
     return result
 

+

 def orderedSet(iterable):
     """ Remove all duplicates from the input iterable """
     res = []
 def orderedSet(iterable):
     """ Remove all duplicates from the input iterable """
     res = []


@@ -371,6 +377,7 @@ def decodeOption(optval):
     assert isinstance(optval, compat_str)
     return optval
 
     assert isinstance(optval, compat_str)
     return optval
 

+

 def formatSeconds(secs):
     if secs > 3600:
         return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
 def formatSeconds(secs):
     if secs > 3600:
         return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)


@@ -423,6 +430,7 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
 
 class ExtractorError(Exception):
     """Error during info extraction."""
 
 class ExtractorError(Exception):
     """Error during info extraction."""

+

     def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
         """ tb, if given, is the original traceback (so that it can be printed out).
         If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
     def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
         """ tb, if given, is the original traceback (so that it can be printed out).
         If expected is set, this is a normal error message and most likely not a bug in youtube-dl.


@@ -467,6 +475,7 @@ class DownloadError(Exception):
     configured to continue on errors. They will contain the appropriate
     error message.
     """
     configured to continue on errors. They will contain the appropriate
     error message.
     """

+

     def __init__(self, msg, exc_info=None):
         """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
         super(DownloadError, self).__init__(msg)
     def __init__(self, msg, exc_info=None):
         """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
         super(DownloadError, self).__init__(msg)


@@ -488,9 +497,11 @@ class PostProcessingError(Exception):
     This exception may be raised by PostProcessor's .run() method to
     indicate an error in the postprocessing task.
     """
     This exception may be raised by PostProcessor's .run() method to
     indicate an error in the postprocessing task.
     """

+

     def __init__(self, msg):
         self.msg = msg
 
     def __init__(self, msg):
         self.msg = msg
 

+

 class MaxDownloadsReached(Exception):
     """ --max-downloads limit has been reached. """
     pass
 class MaxDownloadsReached(Exception):
     """ --max-downloads limit has been reached. """
     pass


@@ -520,6 +531,7 @@ class ContentTooShortError(Exception):
         self.downloaded = downloaded
         self.expected = expected
 
         self.downloaded = downloaded
         self.expected = expected
 

+

 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 
 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 


@@ -639,7 +651,7 @@ def unified_strdate(date_str):
         return None
 
     upload_date = None
         return None
 
     upload_date = None

-    #Replace commas
+    # Replace commas

     date_str = date_str.replace(',', ' ')
     # %z (UTC offset) is only supported in python>=3.2
     date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
     date_str = date_str.replace(',', ' ')
     # %z (UTC offset) is only supported in python>=3.2
     date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)


@@ -680,6 +692,7 @@ def unified_strdate(date_str):
             upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
     return upload_date
 
             upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
     return upload_date
 

+

 def determine_ext(url, default_ext='unknown_video'):
     if url is None:
         return default_ext
 def determine_ext(url, default_ext='unknown_video'):
     if url is None:
         return default_ext


@@ -689,9 +702,11 @@ def determine_ext(url, default_ext='unknown_video'):
     else:
         return default_ext
 
     else:
         return default_ext
 

+

 def subtitles_filename(filename, sub_lang, sub_format):
     return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format
 
 def subtitles_filename(filename, sub_lang, sub_format):
     return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format
 

+

 def date_from_str(date_str):
     """
     Return a datetime object from a string in the format YYYYMMDD or
 def date_from_str(date_str):
     """
     Return a datetime object from a string in the format YYYYMMDD or


@@ -706,7 +721,7 @@ def date_from_str(date_str):
         if sign == '-':
             time = -time
         unit = match.group('unit')
         if sign == '-':
             time = -time
         unit = match.group('unit')

-        #A bad aproximation?
+        # A bad aproximation?

         if unit == 'month':
             unit = 'day'
             time *= 30
         if unit == 'month':
             unit = 'day'
             time *= 30


@@ -717,7 +732,8 @@ def date_from_str(date_str):
         delta = datetime.timedelta(**{unit: time})
         return today + delta
     return datetime.datetime.strptime(date_str, "%Y%m%d").date()
         delta = datetime.timedelta(**{unit: time})
         return today + delta
     return datetime.datetime.strptime(date_str, "%Y%m%d").date()

-    
+
+

 def hyphenate_date(date_str):
     """
     Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
 def hyphenate_date(date_str):
     """
     Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""


@@ -727,8 +743,10 @@ def hyphenate_date(date_str):
     else:
         return date_str
 
     else:
         return date_str
 

+

 class DateRange(object):
     """Represents a time interval between two dates"""
 class DateRange(object):
     """Represents a time interval between two dates"""

+

     def __init__(self, start=None, end=None):
         """start and end must be strings in the format accepted by date"""
         if start is not None:
     def __init__(self, start=None, end=None):
         """start and end must be strings in the format accepted by date"""
         if start is not None:


@@ -741,17 +759,20 @@ class DateRange(object):
             self.end = datetime.datetime.max.date()
         if self.start > self.end:
             raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
             self.end = datetime.datetime.max.date()
         if self.start > self.end:
             raise ValueError('Date range: "%s" , the start date must be before the end date' % self)

+

     @classmethod
     def day(cls, day):
         """Returns a range that only contains the given day"""
     @classmethod
     def day(cls, day):
         """Returns a range that only contains the given day"""

-        return cls(day,day)
+        return cls(day, day)
+

     def __contains__(self, date):
         """Check if the date is in the range"""
         if not isinstance(date, datetime.date):
             date = date_from_str(date)
         return self.start <= date <= self.end
     def __contains__(self, date):
         """Check if the date is in the range"""
         if not isinstance(date, datetime.date):
             date = date_from_str(date)
         return self.start <= date <= self.end

+

     def __str__(self):
     def __str__(self):

-        return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())
+        return '%s - %s' % (self.start.isoformat(), self.end.isoformat())

 
 
 def platform_name():
 
 
 def platform_name():


@@ -1025,6 +1046,57 @@ def format_bytes(bytes):
     return '%.2f%s' % (converted, suffix)
 
 
     return '%.2f%s' % (converted, suffix)
 
 

+def parse_filesize(s):
+    if s is None:
+        return None
+
+    # The lower-case forms are of course incorrect and inofficial,
+    # but we support those too
+    _UNIT_TABLE = {
+        'B': 1,
+        'b': 1,
+        'KiB': 1024,
+        'KB': 1000,
+        'kB': 1024,
+        'Kb': 1000,
+        'MiB': 1024 ** 2,
+        'MB': 1000 ** 2,
+        'mB': 1024 ** 2,
+        'Mb': 1000 ** 2,
+        'GiB': 1024 ** 3,
+        'GB': 1000 ** 3,
+        'gB': 1024 ** 3,
+        'Gb': 1000 ** 3,
+        'TiB': 1024 ** 4,
+        'TB': 1000 ** 4,
+        'tB': 1024 ** 4,
+        'Tb': 1000 ** 4,
+        'PiB': 1024 ** 5,
+        'PB': 1000 ** 5,
+        'pB': 1024 ** 5,
+        'Pb': 1000 ** 5,
+        'EiB': 1024 ** 6,
+        'EB': 1000 ** 6,
+        'eB': 1024 ** 6,
+        'Eb': 1000 ** 6,
+        'ZiB': 1024 ** 7,
+        'ZB': 1000 ** 7,
+        'zB': 1024 ** 7,
+        'Zb': 1000 ** 7,
+        'YiB': 1024 ** 8,
+        'YB': 1000 ** 8,
+        'yB': 1024 ** 8,
+        'Yb': 1000 ** 8,
+    }
+
+    units_re = '|'.join(re.escape(u) for u in _UNIT_TABLE)
+    m = re.match(r'(?P<num>[0-9]+(?:\.[0-9]*)?)\s*(?P<unit>%s)' % units_re, s)
+    if not m:
+        return None
+
+    return int(float(m.group('num')) * _UNIT_TABLE[m.group('unit')])
+
+

 def get_term_width():
     columns = compat_getenv('COLUMNS', None)
     if columns:
 def get_term_width():
     columns = compat_getenv('COLUMNS', None)
     if columns:


@@ -1149,7 +1221,7 @@ def parse_duration(s):
 
 
 def prepend_extension(filename, ext):
 
 
 def prepend_extension(filename, ext):

-    name, real_ext = os.path.splitext(filename) 
+    name, real_ext = os.path.splitext(filename)

     return '{0}.{1}{2}'.format(name, ext, real_ext)
 
 
     return '{0}.{1}{2}'.format(name, ext, real_ext)
 
 


@@ -1433,3 +1505,8 @@ def ytdl_is_updateable():
     from zipimport import zipimporter
 
     return isinstance(globals().get('__loader__'), zipimporter) or hasattr(sys, 'frozen')
     from zipimport import zipimporter
 
     return isinstance(globals().get('__loader__'), zipimporter) or hasattr(sys, 'frozen')

+
+
+def args_to_str(args):
+    # Get a short string representation for a subprocess command
+    return ' '.join(shlex_quote(a) for a in args)