X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..2e86127b07f6a63b7ce457331d600d9486b22b44:/youtube_dl/utils.py diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 2864e51..4d3cbac 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1,6 +1,8 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import unicode_literals + import calendar import codecs import contextlib @@ -8,7 +10,6 @@ import ctypes import datetime import email.utils import errno -import getpass import gzip import itertools import io @@ -29,254 +30,19 @@ import traceback import xml.etree.ElementTree import zlib -try: - import urllib.request as compat_urllib_request -except ImportError: # Python 2 - import urllib2 as compat_urllib_request - -try: - import urllib.error as compat_urllib_error -except ImportError: # Python 2 - import urllib2 as compat_urllib_error - -try: - import urllib.parse as compat_urllib_parse -except ImportError: # Python 2 - import urllib as compat_urllib_parse - -try: - from urllib.parse import urlparse as compat_urllib_parse_urlparse -except ImportError: # Python 2 - from urlparse import urlparse as compat_urllib_parse_urlparse - -try: - import urllib.parse as compat_urlparse -except ImportError: # Python 2 - import urlparse as compat_urlparse - -try: - import http.cookiejar as compat_cookiejar -except ImportError: # Python 2 - import cookielib as compat_cookiejar - -try: - import html.entities as compat_html_entities -except ImportError: # Python 2 - import htmlentitydefs as compat_html_entities - -try: - import html.parser as compat_html_parser -except ImportError: # Python 2 - import HTMLParser as compat_html_parser - -try: - import http.client as compat_http_client -except ImportError: # Python 2 - import httplib as compat_http_client - -try: - from urllib.error import HTTPError as compat_HTTPError -except ImportError: # Python 2 - from urllib2 import HTTPError as compat_HTTPError - -try: - from urllib.request import urlretrieve as compat_urlretrieve -except ImportError: # Python 2 - from urllib import urlretrieve as compat_urlretrieve - - -try: - from subprocess import DEVNULL - compat_subprocess_get_DEVNULL = lambda: DEVNULL -except ImportError: - compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w') - -try: - from urllib.parse import unquote as compat_urllib_parse_unquote -except ImportError: - def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): - if string == '': - return string - res = string.split('%') - if len(res) == 1: - return string - if encoding is None: - encoding = 'utf-8' - if errors is None: - errors = 'replace' - # pct_sequence: contiguous sequence of percent-encoded bytes, decoded - pct_sequence = b'' - string = res[0] - for item in res[1:]: - try: - if not item: - raise ValueError - pct_sequence += item[:2].decode('hex') - rest = item[2:] - if not rest: - # This segment was just a single percent-encoded character. - # May be part of a sequence of code units, so delay decoding. - # (Stored in pct_sequence). - continue - except ValueError: - rest = '%' + item - # Encountered non-percent-encoded characters. Flush the current - # pct_sequence. - string += pct_sequence.decode(encoding, errors) + rest - pct_sequence = b'' - if pct_sequence: - # Flush the final pct_sequence - string += pct_sequence.decode(encoding, errors) - return string - - -try: - from urllib.parse import parse_qs as compat_parse_qs -except ImportError: # Python 2 - # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib. - # Python 2's version is apparently totally broken - - def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False, - encoding='utf-8', errors='replace'): - qs, _coerce_result = qs, unicode - pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')] - r = [] - for name_value in pairs: - if not name_value and not strict_parsing: - continue - nv = name_value.split('=', 1) - if len(nv) != 2: - if strict_parsing: - raise ValueError("bad query field: %r" % (name_value,)) - # Handle case of a control-name with no equal sign - if keep_blank_values: - nv.append('') - else: - continue - if len(nv[1]) or keep_blank_values: - name = nv[0].replace('+', ' ') - name = compat_urllib_parse_unquote( - name, encoding=encoding, errors=errors) - name = _coerce_result(name) - value = nv[1].replace('+', ' ') - value = compat_urllib_parse_unquote( - value, encoding=encoding, errors=errors) - value = _coerce_result(value) - r.append((name, value)) - return r - - def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False, - encoding='utf-8', errors='replace'): - parsed_result = {} - pairs = _parse_qsl(qs, keep_blank_values, strict_parsing, - encoding=encoding, errors=errors) - for name, value in pairs: - if name in parsed_result: - parsed_result[name].append(value) - else: - parsed_result[name] = [value] - return parsed_result - -try: - compat_str = unicode # Python 2 -except NameError: - compat_str = str - -try: - compat_chr = unichr # Python 2 -except NameError: - compat_chr = chr - -try: - from xml.etree.ElementTree import ParseError as compat_xml_parse_error -except ImportError: # Python 2.6 - from xml.parsers.expat import ExpatError as compat_xml_parse_error - -try: - from shlex import quote as shlex_quote -except ImportError: # Python < 3.3 - def shlex_quote(s): - return "'" + s.replace("'", "'\"'\"'") + "'" - - -def compat_ord(c): - if type(c) is int: return c - else: return ord(c) - - -if sys.version_info >= (3, 0): - compat_getenv = os.getenv - compat_expanduser = os.path.expanduser -else: - # Environment variables should be decoded with filesystem encoding. - # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918) - - def compat_getenv(key, default=None): - env = os.getenv(key, default) - if env: - env = env.decode(get_filesystem_encoding()) - return env - - # HACK: The default implementations of os.path.expanduser from cpython do not decode - # environment variables with filesystem encoding. We will work around this by - # providing adjusted implementations. - # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib - # for different platforms with correct environment variables decoding. - - if os.name == 'posix': - def compat_expanduser(path): - """Expand ~ and ~user constructions. If user or $HOME is unknown, - do nothing.""" - if not path.startswith('~'): - return path - i = path.find('/', 1) - if i < 0: - i = len(path) - if i == 1: - if 'HOME' not in os.environ: - import pwd - userhome = pwd.getpwuid(os.getuid()).pw_dir - else: - userhome = compat_getenv('HOME') - else: - import pwd - try: - pwent = pwd.getpwnam(path[1:i]) - except KeyError: - return path - userhome = pwent.pw_dir - userhome = userhome.rstrip('/') - return (userhome + path[i:]) or '/' - elif os.name == 'nt' or os.name == 'ce': - def compat_expanduser(path): - """Expand ~ and ~user constructs. - - If user or $HOME is unknown, do nothing.""" - if path[:1] != '~': - return path - i, n = 1, len(path) - while i < n and path[i] not in '/\\': - i = i + 1 - - if 'HOME' in os.environ: - userhome = compat_getenv('HOME') - elif 'USERPROFILE' in os.environ: - userhome = compat_getenv('USERPROFILE') - elif not 'HOMEPATH' in os.environ: - return path - else: - try: - drive = compat_getenv('HOMEDRIVE') - except KeyError: - drive = '' - userhome = os.path.join(drive, compat_getenv('HOMEPATH')) - - if i != 1: #~user - userhome = os.path.join(os.path.dirname(userhome), path[1:i]) - - return userhome + path[i:] - else: - compat_expanduser = os.path.expanduser +from .compat import ( + compat_chr, + compat_getenv, + compat_html_entities, + compat_parse_qs, + compat_str, + compat_urllib_error, + compat_urllib_parse, + compat_urllib_parse_urlparse, + compat_urllib_request, + compat_urlparse, + shlex_quote, +) # This is not clearly defined otherwise @@ -290,6 +56,7 @@ std_headers = { 'Accept-Language': 'en-us,en;q=0.5', } + def preferredencoding(): """Get preferred encoding. @@ -298,28 +65,33 @@ def preferredencoding(): """ try: pref = locale.getpreferredencoding() - u'TEST'.encode(pref) + 'TEST'.encode(pref) except: pref = 'UTF-8' return pref -if sys.version_info < (3,0): - def compat_print(s): - print(s.encode(preferredencoding(), 'xmlcharrefreplace')) -else: - def compat_print(s): - assert type(s) == type(u'') - print(s) - def write_json_file(obj, fn): - """ Encode obj as JSON and write it to fn, atomically """ + """ Encode obj as JSON and write it to fn, atomically if possible """ + + fn = encodeFilename(fn) + if sys.version_info < (3, 0) and sys.platform != 'win32': + encoding = get_filesystem_encoding() + # os.path.basename returns a bytes object, but NamedTemporaryFile + # will fail if the filename contains non ascii characters unless we + # use a unicode object + path_basename = lambda f: os.path.basename(fn).decode(encoding) + # the same for os.path.dirname + path_dirname = lambda f: os.path.dirname(fn).decode(encoding) + else: + path_basename = os.path.basename + path_dirname = os.path.dirname args = { 'suffix': '.tmp', - 'prefix': os.path.basename(fn) + '.', - 'dir': os.path.dirname(fn), + 'prefix': path_basename(fn) + '.', + 'dir': path_dirname(fn), 'delete': False, } @@ -338,6 +110,13 @@ def write_json_file(obj, fn): try: with tf: json.dump(obj, tf) + if sys.platform == 'win32': + # Need to remove existing file on Windows, else os.rename raises + # WindowsError or FileExistsError. + try: + os.unlink(fn) + except OSError: + pass os.rename(tf.name, fn) except: try: @@ -352,7 +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) - 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): @@ -368,6 +147,8 @@ else: # 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 = [] @@ -394,127 +175,32 @@ def xpath_text(node, xpath, name=None, fatal=False): return n.text -compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix -class BaseHTMLParser(compat_html_parser.HTMLParser): - def __init(self): - compat_html_parser.HTMLParser.__init__(self) - self.html = None - - def loads(self, html): - self.html = html - self.feed(html) - self.close() - -class AttrParser(BaseHTMLParser): - """Modified HTMLParser that isolates a tag with the specified attribute""" - def __init__(self, attribute, value): - self.attribute = attribute - self.value = value - self.result = None - self.started = False - self.depth = {} - self.watch_startpos = False - self.error_count = 0 - BaseHTMLParser.__init__(self) - - def error(self, message): - if self.error_count > 10 or self.started: - raise compat_html_parser.HTMLParseError(message, self.getpos()) - self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line - self.error_count += 1 - self.goahead(1) - - def handle_starttag(self, tag, attrs): - attrs = dict(attrs) - if self.started: - self.find_startpos(None) - if self.attribute in attrs and attrs[self.attribute] == self.value: - self.result = [tag] - self.started = True - self.watch_startpos = True - if self.started: - if not tag in self.depth: self.depth[tag] = 0 - self.depth[tag] += 1 - - def handle_endtag(self, tag): - if self.started: - if tag in self.depth: self.depth[tag] -= 1 - if self.depth[self.result[0]] == 0: - self.started = False - self.result.append(self.getpos()) - - def find_startpos(self, x): - """Needed to put the start position of the result (self.result[1]) - after the opening tag with the requested id""" - if self.watch_startpos: - self.watch_startpos = False - self.result.append(self.getpos()) - handle_entityref = handle_charref = handle_data = handle_comment = \ - handle_decl = handle_pi = unknown_decl = find_startpos - - def get_result(self): - if self.result is None: - return None - if len(self.result) != 3: - return None - lines = self.html.split('\n') - lines = lines[self.result[1][0]-1:self.result[2][0]] - lines[0] = lines[0][self.result[1][1]:] - if len(lines) == 1: - lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] - lines[-1] = lines[-1][:self.result[2][1]] - return '\n'.join(lines).strip() -# Hack for https://github.com/rg3/youtube-dl/issues/662 -if sys.version_info < (2, 7, 3): - AttrParser.parse_endtag = (lambda self, i: - i + len("") - if self.rawdata[i:].startswith("") - else compat_html_parser.HTMLParser.parse_endtag(self, i)) - def get_element_by_id(id, html): """Return the content of the tag with the specified ID in the passed HTML document""" return get_element_by_attribute("id", id, html) + def get_element_by_attribute(attribute, value, html): """Return the content of the tag with the specified attribute in the passed HTML document""" - parser = AttrParser(attribute, value) - try: - parser.loads(html) - except compat_html_parser.HTMLParseError: - pass - return parser.get_result() -class MetaParser(BaseHTMLParser): - """ - Modified HTMLParser that isolates a meta tag with the specified name - attribute. - """ - def __init__(self, name): - BaseHTMLParser.__init__(self) - self.name = name - self.content = None - self.result = None - - def handle_starttag(self, tag, attrs): - if tag != 'meta': - return - attrs = dict(attrs) - if attrs.get('name') == self.name: - self.result = attrs.get('content') + m = re.search(r'''(?xs) + <([a-zA-Z0-9:._-]+) + (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*? + \s+%s=['"]?%s['"]? + (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*? + \s*> + (?P.*?) + + ''' % (re.escape(attribute), re.escape(value)), html) - def get_result(self): - return self.result + if not m: + return None + res = m.group('content') -def get_meta_content(name, html): - """ - Return the content attribute from the meta tag with the given name attribute. - """ - parser = MetaParser(name) - try: - parser.loads(html) - except compat_html_parser.HTMLParseError: - pass - return parser.get_result() + if res.startswith('"') or res.startswith("'"): + res = res[1:-1] + + return unescapeHTML(res) def clean_html(html): @@ -541,7 +227,7 @@ def sanitize_open(filename, open_mode): It returns the tuple (stream, definitive_file_name). """ try: - if filename == u'-': + if filename == '-': if sys.platform == 'win32': import msvcrt msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) @@ -554,9 +240,9 @@ def sanitize_open(filename, open_mode): # In case of error, try to remove win32 forbidden chars alt_filename = os.path.join( - re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', 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: @@ -573,6 +259,7 @@ def timeconvert(timestr): 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. @@ -593,7 +280,7 @@ def sanitize_filename(s, restricted=False, is_id=False): return '_' return char - result = u''.join(map(replace_insane, s)) + result = ''.join(map(replace_insane, s)) if not is_id: while '__' in result: result = result.replace('__', '_') @@ -605,6 +292,7 @@ def sanitize_filename(s, restricted=False, is_id=False): result = '_' return result + def orderedSet(iterable): """ Remove all duplicates from the input iterable """ res = [] @@ -623,15 +311,15 @@ def _htmlentity_transform(entity): mobj = re.match(r'#(x?[0-9]+)', entity) if mobj is not None: numstr = mobj.group(1) - if numstr.startswith(u'x'): + if numstr.startswith('x'): base = 16 - numstr = u'0%s' % numstr + numstr = '0%s' % numstr else: base = 10 return compat_chr(int(numstr, base)) # Unknown entity in name, return its literal representation - return (u'&%s;' % entity) + return ('&%s;' % entity) def unescapeHTML(s): @@ -655,7 +343,7 @@ def encodeFilename(s, for_subprocess=False): return s if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: - # Pass u'' directly to use Unicode APIs on Windows 2000 and up + # Pass '' 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.) if not for_subprocess: @@ -689,6 +377,7 @@ def decodeOption(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) @@ -738,8 +427,10 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs): pass # Python < 3.4 return compat_urllib_request.HTTPSHandler(context=context, **kwargs) + 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. @@ -750,9 +441,15 @@ class ExtractorError(Exception): if video_id is not None: msg = video_id + ': ' + msg if cause: - msg += u' (caused by %r)' % cause + msg += ' (caused by %r)' % cause if not expected: - msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output. Make sure you are using the latest version; type youtube-dl -U to update.' + if ytdl_is_updateable(): + update_cmd = 'type youtube-dl -U to update' + else: + update_cmd = 'see https://yt-dl.org/update on how to update' + msg += '; please report this issue on https://yt-dl.org/bug .' + msg += ' Make sure you are using the latest version; %s.' % update_cmd + msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.' super(ExtractorError, self).__init__(msg) self.traceback = tb @@ -763,7 +460,7 @@ class ExtractorError(Exception): def format_traceback(self): if self.traceback is None: return None - return u''.join(traceback.format_tb(self.traceback)) + return ''.join(traceback.format_tb(self.traceback)) class RegexNotFoundError(ExtractorError): @@ -778,6 +475,7 @@ class DownloadError(Exception): 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) @@ -799,9 +497,11 @@ class PostProcessingError(Exception): 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 + class MaxDownloadsReached(Exception): """ --max-downloads limit has been reached. """ pass @@ -831,6 +531,7 @@ class ContentTooShortError(Exception): self.downloaded = downloaded self.expected = expected + class YoutubeDLHandler(compat_urllib_request.HTTPHandler): """Handler for HTTP requests and responses. @@ -950,7 +651,7 @@ def unified_strdate(date_str): 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) @@ -991,17 +692,20 @@ def unified_strdate(date_str): upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d') return upload_date -def determine_ext(url, default_ext=u'unknown_video'): + +def determine_ext(url, default_ext='unknown_video'): if url is None: return default_ext - guess = url.partition(u'?')[0].rpartition(u'.')[2] + guess = url.partition('?')[0].rpartition('.')[2] if re.match(r'^[A-Za-z0-9]+$', guess): return guess else: return default_ext + def subtitles_filename(filename, sub_lang, sub_format): - return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format + return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format + def date_from_str(date_str): """ @@ -1017,7 +721,7 @@ def date_from_str(date_str): if sign == '-': time = -time unit = match.group('unit') - #A bad aproximation? + # A bad aproximation? if unit == 'month': unit = 'day' time *= 30 @@ -1028,7 +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() - + + def hyphenate_date(date_str): """ Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format""" @@ -1038,8 +743,10 @@ def hyphenate_date(date_str): else: return date_str + 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: @@ -1052,17 +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) + @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 __str__(self): - return '%s - %s' % ( self.start.isoformat(), self.end.isoformat()) + return '%s - %s' % (self.start.isoformat(), self.end.isoformat()) def platform_name(): @@ -1181,10 +891,7 @@ def bytes_to_intlist(bs): def intlist_to_bytes(xs): if not xs: return b'' - if isinstance(chr(0), bytes): # Python 2 - return ''.join([chr(x) for x in xs]) - else: - return bytes(xs) + return struct_pack('%dB' % len(xs), *xs) # Cross-platform file locking @@ -1296,7 +1003,7 @@ def shell_quote(args): # We may get a filename encoded with 'encodeFilename' a = a.decode(encoding) quoted_args.append(pipes.quote(a)) - return u' '.join(quoted_args) + return ' '.join(quoted_args) def takewhile_inclusive(pred, seq): @@ -1312,31 +1019,82 @@ def smuggle_url(url, data): """ Pass additional data in a URL for internal use. """ sdata = compat_urllib_parse.urlencode( - {u'__youtubedl_smuggle': json.dumps(data)}) - return url + u'#' + sdata + {'__youtubedl_smuggle': json.dumps(data)}) + return url + '#' + sdata def unsmuggle_url(smug_url, default=None): if not '#__youtubedl_smuggle' in smug_url: return smug_url, default - url, _, sdata = smug_url.rpartition(u'#') - jsond = compat_parse_qs(sdata)[u'__youtubedl_smuggle'][0] + url, _, sdata = smug_url.rpartition('#') + jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0] data = json.loads(jsond) return url, data def format_bytes(bytes): if bytes is None: - return u'N/A' + return 'N/A' if type(bytes) is str: bytes = float(bytes) if bytes == 0.0: exponent = 0 else: exponent = int(math.log(bytes, 1024.0)) - suffix = [u'B', u'KiB', u'MiB', u'GiB', u'TiB', u'PiB', u'EiB', u'ZiB', u'YiB'][exponent] + suffix = ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB'][exponent] converted = float(bytes) / float(1024 ** exponent) - return u'%.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[0-9]+(?:\.[0-9]*)?)\s*(?P%s)' % units_re, s) + if not m: + return None + + return int(float(m.group('num')) * _UNIT_TABLE[m.group('unit')]) def get_term_width(): @@ -1359,8 +1117,8 @@ def month_by_name(name): """ Return the number of a month by (locale-independently) English name """ ENGLISH_NAMES = [ - u'January', u'February', u'March', u'April', u'May', u'June', - u'July', u'August', u'September', u'October', u'November', u'December'] + 'January', 'February', 'March', 'April', 'May', 'June', + 'July', 'August', 'September', 'October', 'November', 'December'] try: return ENGLISH_NAMES.index(name) + 1 except ValueError: @@ -1371,7 +1129,7 @@ def fix_xml_ampersands(xml_str): """Replace all the '&' by '&' in XML""" return re.sub( r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)', - u'&', + '&', xml_str) @@ -1404,7 +1162,7 @@ def remove_end(s, end): def url_basename(url): path = compat_urlparse.urlparse(url).path - return path.strip(u'/').split(u'/')[-1] + return path.strip('/').split('/')[-1] class HEADRequest(compat_urllib_request.Request): @@ -1429,7 +1187,7 @@ def str_to_int(int_str): """ A more relaxed version of int_or_none """ if int_str is None: return None - int_str = re.sub(r'[,\.\+]', u'', int_str) + int_str = re.sub(r'[,\.\+]', '', int_str) return int(int_str) @@ -1444,7 +1202,12 @@ def parse_duration(s): s = s.strip() m = re.match( - r'(?i)(?:(?:(?P[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P[0-9]+)(?P\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s) + r'''(?ix)T? + (?: + (?:(?P[0-9]+)\s*(?:[:h]|hours?)\s*)? + (?P[0-9]+)\s*(?:[:m]|mins?|minutes?)\s* + )? + (?P[0-9]+)(?P\.[0-9]+)?\s*(?:s|secs?|seconds?)?$''', s) if not m: return None res = int(m.group('secs')) @@ -1458,8 +1221,8 @@ def parse_duration(s): def prepend_extension(filename, ext): - name, real_ext = os.path.splitext(filename) - return u'{0}.{1}{2}'.format(name, ext, real_ext) + name, real_ext = os.path.splitext(filename) + return '{0}.{1}{2}'.format(name, ext, real_ext) def check_executable(exe, args=[]): @@ -1472,6 +1235,25 @@ def check_executable(exe, args=[]): return exe +def get_exe_version(exe, args=['--version'], + version_re=r'version\s+([0-9._-a-zA-Z]+)', + unrecognized='present'): + """ Returns the version of the specified executable, + or False if the executable is not present """ + try: + out, err = subprocess.Popen( + [exe] + args, + stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate() + except OSError: + return False + firstline = out.partition(b'\n')[0].decode('ascii', 'ignore') + m = re.search(version_re, firstline) + if m: + return m.group(1) + else: + return unrecognized + + class PagedList(object): def __len__(self): # This is only useful for tests @@ -1562,7 +1344,7 @@ def escape_rfc3986(s): """Escape non-ASCII characters as suggested by RFC 3986""" if sys.version_info < (3, 0) and isinstance(s, unicode): s = s.encode('utf-8') - return compat_urllib_parse.quote(s, "%/;:@&=+$,!~*'()?#[]") + return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]") def escape_url(url): @@ -1576,7 +1358,7 @@ def escape_url(url): ).geturl() try: - struct.pack(u'!I', 0) + struct.pack('!I', 0) except TypeError: # In Python 2.6 (and some 2.7 versions), struct requires a bytes argument def struct_pack(spec, *args): @@ -1597,7 +1379,7 @@ def read_batch_urls(batch_fd): def fixup(url): if not isinstance(url, compat_str): url = url.decode('utf-8', 'replace') - BOM_UTF8 = u'\xef\xbb\xbf' + BOM_UTF8 = '\xef\xbb\xbf' if url.startswith(BOM_UTF8): url = url[len(BOM_UTF8):] url = url.strip() @@ -1636,15 +1418,6 @@ def parse_xml(s): return tree -if sys.version_info < (3, 0) and sys.platform == 'win32': - def compat_getpass(prompt, *args, **kwargs): - if isinstance(prompt, compat_str): - prompt = prompt.encode(preferredencoding()) - return getpass.getpass(prompt, *args, **kwargs) -else: - compat_getpass = getpass.getpass - - US_RATINGS = { 'G': 0, 'PG': 10, @@ -1662,7 +1435,8 @@ def parse_age_limit(s): def strip_jsonp(code): - return re.sub(r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?\s*$', r'\1', code) + return re.sub( + r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?(?://[^\n]*)*$', r'\1', code) def js_to_json(code): @@ -1702,18 +1476,6 @@ def qualities(quality_ids): DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)s' -try: - subprocess_check_output = subprocess.check_output -except AttributeError: - def subprocess_check_output(*args, **kwargs): - assert 'input' not in kwargs - p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs) - output, _ = p.communicate() - ret = p.poll() - if ret: - raise subprocess.CalledProcessError(ret, p.args, output=output) - return output - def limit_length(s, length): """ Add ellipses to overly long strings """ @@ -1736,3 +1498,15 @@ def is_outdated_version(version, limit, assume_new=True): return version_tuple(version) < version_tuple(limit) except ValueError: return not assume_new + + +def ytdl_is_updateable(): + """ Returns if youtube-dl can be updated with -U """ + 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)