+ r'\\U[0-9a-fA-F]{8}',
+ lambda m: unicode_escape(m.group(0))[0],
+ s)
+
+
+def lowercase_escape(s):
+ unicode_escape = codecs.getdecoder('unicode_escape')
+ return re.sub(
+ r'\\u[0-9a-fA-F]{4}',
+ lambda m: unicode_escape(m.group(0))[0],
+ s)
+
+
+def escape_rfc3986(s):
+ """Escape non-ASCII characters as suggested by RFC 3986"""
+ if sys.version_info < (3, 0) and isinstance(s, compat_str):
+ s = s.encode('utf-8')
+ return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
+
+
+def escape_url(url):
+ """Escape URL as suggested by RFC 3986"""
+ url_parsed = compat_urllib_parse_urlparse(url)
+ return url_parsed._replace(
+ netloc=url_parsed.netloc.encode('idna').decode('ascii'),
+ path=escape_rfc3986(url_parsed.path),
+ params=escape_rfc3986(url_parsed.params),
+ query=escape_rfc3986(url_parsed.query),
+ fragment=escape_rfc3986(url_parsed.fragment)
+ ).geturl()
+
+
+def read_batch_urls(batch_fd):
+ def fixup(url):
+ if not isinstance(url, compat_str):
+ url = url.decode('utf-8', 'replace')
+ BOM_UTF8 = '\xef\xbb\xbf'
+ if url.startswith(BOM_UTF8):
+ url = url[len(BOM_UTF8):]
+ url = url.strip()
+ if url.startswith(('#', ';', ']')):
+ return False
+ return url
+
+ with contextlib.closing(batch_fd) as fd:
+ return [url for url in map(fixup, fd) if url]
+
+
+def urlencode_postdata(*args, **kargs):
+ return compat_urllib_parse_urlencode(*args, **kargs).encode('ascii')
+
+
+def update_url_query(url, query):
+ if not query:
+ return url
+ parsed_url = compat_urlparse.urlparse(url)
+ qs = compat_parse_qs(parsed_url.query)
+ qs.update(query)
+ return compat_urlparse.urlunparse(parsed_url._replace(
+ query=compat_urllib_parse_urlencode(qs, True)))
+
+
+def update_Request(req, url=None, data=None, headers={}, query={}):
+ req_headers = req.headers.copy()
+ req_headers.update(headers)
+ req_data = data or req.data
+ req_url = update_url_query(url or req.get_full_url(), query)
+ req_get_method = req.get_method()
+ if req_get_method == 'HEAD':
+ req_type = HEADRequest
+ elif req_get_method == 'PUT':
+ req_type = PUTRequest
+ else:
+ req_type = compat_urllib_request.Request
+ new_req = req_type(
+ req_url, data=req_data, headers=req_headers,
+ origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
+ if hasattr(req, 'timeout'):
+ new_req.timeout = req.timeout
+ return new_req
+
+
+def _multipart_encode_impl(data, boundary):
+ content_type = 'multipart/form-data; boundary=%s' % boundary
+
+ out = b''
+ for k, v in data.items():
+ out += b'--' + boundary.encode('ascii') + b'\r\n'
+ if isinstance(k, compat_str):
+ k = k.encode('utf-8')
+ if isinstance(v, compat_str):
+ v = v.encode('utf-8')
+ # RFC 2047 requires non-ASCII field names to be encoded, while RFC 7578
+ # suggests sending UTF-8 directly. Firefox sends UTF-8, too
+ content = b'Content-Disposition: form-data; name="' + k + b'"\r\n\r\n' + v + b'\r\n'
+ if boundary.encode('ascii') in content:
+ raise ValueError('Boundary overlaps with data')
+ out += content
+
+ out += b'--' + boundary.encode('ascii') + b'--\r\n'
+
+ return out, content_type
+
+
+def multipart_encode(data, boundary=None):
+ '''
+ Encode a dict to RFC 7578-compliant form-data
+
+ data:
+ A dict where keys and values can be either Unicode or bytes-like
+ objects.
+ boundary:
+ If specified a Unicode object, it's used as the boundary. Otherwise
+ a random boundary is generated.
+
+ Reference: https://tools.ietf.org/html/rfc7578
+ '''
+ has_specified_boundary = boundary is not None
+
+ while True:
+ if boundary is None:
+ boundary = '---------------' + str(random.randrange(0x0fffffff, 0xffffffff))
+
+ try:
+ out, content_type = _multipart_encode_impl(data, boundary)
+ break
+ except ValueError:
+ if has_specified_boundary:
+ raise
+ boundary = None
+
+ return out, content_type
+
+
+def dict_get(d, key_or_keys, default=None, skip_false_values=True):
+ if isinstance(key_or_keys, (list, tuple)):
+ for key in key_or_keys:
+ if key not in d or d[key] is None or skip_false_values and not d[key]:
+ continue
+ return d[key]
+ return default
+ return d.get(key_or_keys, default)
+
+
+def try_get(src, getter, expected_type=None):
+ if not isinstance(getter, (list, tuple)):
+ getter = [getter]
+ for get in getter:
+ try:
+ v = get(src)
+ except (AttributeError, KeyError, TypeError, IndexError):
+ pass
+ else:
+ if expected_type is None or isinstance(v, expected_type):
+ return v
+
+
+def merge_dicts(*dicts):
+ merged = {}
+ for a_dict in dicts:
+ for k, v in a_dict.items():
+ if v is None:
+ continue
+ if (k not in merged or
+ (isinstance(v, compat_str) and v and
+ isinstance(merged[k], compat_str) and
+ not merged[k])):
+ merged[k] = v
+ return merged
+
+
+def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
+ return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
+
+
+US_RATINGS = {
+ 'G': 0,
+ 'PG': 10,
+ 'PG-13': 13,
+ 'R': 16,
+ 'NC': 18,
+}
+
+
+TV_PARENTAL_GUIDELINES = {
+ 'TV-Y': 0,
+ 'TV-Y7': 7,
+ 'TV-G': 0,
+ 'TV-PG': 0,
+ 'TV-14': 14,
+ 'TV-MA': 17,
+}
+
+
+def parse_age_limit(s):
+ if type(s) == int:
+ return s if 0 <= s <= 21 else None
+ if not isinstance(s, compat_basestring):
+ return None
+ m = re.match(r'^(?P<age>\d{1,2})\+?$', s)
+ if m:
+ return int(m.group('age'))
+ if s in US_RATINGS:
+ return US_RATINGS[s]
+ m = re.match(r'^TV[_-]?(%s)$' % '|'.join(k[3:] for k in TV_PARENTAL_GUIDELINES), s)
+ if m:
+ return TV_PARENTAL_GUIDELINES['TV-' + m.group(1)]
+ return None
+
+
+def strip_jsonp(code):
+ return re.sub(
+ r'''(?sx)^
+ (?:window\.)?(?P<func_name>[a-zA-Z0-9_.$]+)
+ (?:\s*&&\s*(?P=func_name))?
+ \s*\(\s*(?P<callback_data>.*)\);?
+ \s*?(?://[^\n]*)*$''',
+ r'\g<callback_data>', code)
+
+
+def js_to_json(code):
+ COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*'
+ SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE)
+ INTEGER_TABLE = (
+ (r'(?s)^(0[xX][0-9a-fA-F]+){skip}:?$'.format(skip=SKIP_RE), 16),
+ (r'(?s)^(0+[0-7]+){skip}:?$'.format(skip=SKIP_RE), 8),
+ )
+
+ def fix_kv(m):
+ v = m.group(0)
+ if v in ('true', 'false', 'null'):
+ return v
+ elif v.startswith('/*') or v.startswith('//') or v == ',':
+ return ""
+
+ if v[0] in ("'", '"'):
+ v = re.sub(r'(?s)\\.|"', lambda m: {
+ '"': '\\"',
+ "\\'": "'",
+ '\\\n': '',
+ '\\x': '\\u00',
+ }.get(m.group(0), m.group(0)), v[1:-1])
+
+ for regex, base in INTEGER_TABLE:
+ im = re.match(regex, v)
+ if im:
+ i = int(im.group(1), base)
+ return '"%d":' % i if v.endswith(':') else '%d' % i
+
+ return '"%s"' % v
+
+ return re.sub(r'''(?sx)
+ "(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
+ '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
+ {comment}|,(?={skip}[\]}}])|
+ (?:(?<![0-9])[eE]|[a-df-zA-DF-Z_])[.a-zA-Z_0-9]*|
+ \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
+ [0-9]+(?={skip}:)
+ '''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code)
+
+
+def qualities(quality_ids):
+ """ Get a numeric quality value out of a list of possible values """
+ def q(qid):
+ try:
+ return quality_ids.index(qid)
+ except ValueError:
+ return -1
+ return q
+
+
+DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)s'
+
+
+def limit_length(s, length):
+ """ Add ellipses to overly long strings """
+ if s is None:
+ return None
+ ELLIPSES = '...'
+ if len(s) > length:
+ return s[:length - len(ELLIPSES)] + ELLIPSES
+ return s
+
+
+def version_tuple(v):
+ return tuple(int(e) for e in re.split(r'[-.]', v))
+
+
+def is_outdated_version(version, limit, assume_new=True):
+ if not version:
+ return not assume_new
+ try:
+ 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(compat_shlex_quote(a) for a in args)
+
+
+def error_to_compat_str(err):
+ err_str = str(err)
+ # On python 2 error byte string must be decoded with proper
+ # encoding rather than ascii
+ if sys.version_info[0] < 3:
+ err_str = err_str.decode(preferredencoding())
+ return err_str
+
+
+def mimetype2ext(mt):
+ if mt is None:
+ return None
+
+ ext = {
+ 'audio/mp4': 'm4a',
+ # Per RFC 3003, audio/mpeg can be .mp1, .mp2 or .mp3. Here use .mp3 as
+ # it's the most popular one
+ 'audio/mpeg': 'mp3',
+ }.get(mt)
+ if ext is not None:
+ return ext
+
+ _, _, res = mt.rpartition('/')
+ res = res.split(';')[0].strip().lower()
+
+ return {
+ '3gpp': '3gp',
+ 'smptett+xml': 'tt',
+ 'ttaf+xml': 'dfxp',
+ 'ttml+xml': 'ttml',
+ 'x-flv': 'flv',
+ 'x-mp4-fragmented': 'mp4',
+ 'x-ms-sami': 'sami',
+ 'x-ms-wmv': 'wmv',
+ 'mpegurl': 'm3u8',
+ 'x-mpegurl': 'm3u8',
+ 'vnd.apple.mpegurl': 'm3u8',
+ 'dash+xml': 'mpd',
+ 'f4m+xml': 'f4m',
+ 'hds+xml': 'f4m',
+ 'vnd.ms-sstr+xml': 'ism',
+ 'quicktime': 'mov',
+ 'mp2t': 'ts',
+ }.get(res, res)
+
+
+def parse_codecs(codecs_str):
+ # http://tools.ietf.org/html/rfc6381
+ if not codecs_str:
+ return {}
+ splited_codecs = list(filter(None, map(
+ lambda str: str.strip(), codecs_str.strip().strip(',').split(','))))
+ vcodec, acodec = None, None
+ for full_codec in splited_codecs:
+ codec = full_codec.split('.')[0]
+ if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1'):
+ if not vcodec:
+ vcodec = full_codec
+ elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
+ if not acodec:
+ acodec = full_codec
+ else:
+ write_string('WARNING: Unknown codec %s\n' % full_codec, sys.stderr)
+ if not vcodec and not acodec:
+ if len(splited_codecs) == 2:
+ return {
+ 'vcodec': vcodec,
+ 'acodec': acodec,
+ }
+ elif len(splited_codecs) == 1:
+ return {
+ 'vcodec': 'none',
+ 'acodec': vcodec,
+ }
+ else:
+ return {
+ 'vcodec': vcodec or 'none',
+ 'acodec': acodec or 'none',
+ }
+ return {}
+
+
+def urlhandle_detect_ext(url_handle):
+ getheader = url_handle.headers.get
+
+ cd = getheader('Content-Disposition')
+ if cd:
+ m = re.match(r'attachment;\s*filename="(?P<filename>[^"]+)"', cd)
+ if m:
+ e = determine_ext(m.group('filename'), default_ext=None)
+ if e:
+ return e
+
+ return mimetype2ext(getheader('Content-Type'))
+
+
+def encode_data_uri(data, mime_type):
+ return 'data:%s;base64,%s' % (mime_type, base64.b64encode(data).decode('ascii'))
+
+
+def age_restricted(content_limit, age_limit):
+ """ Returns True iff the content should be blocked """
+
+ if age_limit is None: # No limit set
+ return False
+ if content_limit is None:
+ return False # Content available for everyone
+ return age_limit < content_limit
+
+
+def is_html(first_bytes):
+ """ Detect whether a file contains HTML by examining its first bytes. """
+
+ BOMS = [
+ (b'\xef\xbb\xbf', 'utf-8'),
+ (b'\x00\x00\xfe\xff', 'utf-32-be'),
+ (b'\xff\xfe\x00\x00', 'utf-32-le'),
+ (b'\xff\xfe', 'utf-16-le'),
+ (b'\xfe\xff', 'utf-16-be'),
+ ]
+ for bom, enc in BOMS:
+ if first_bytes.startswith(bom):
+ s = first_bytes[len(bom):].decode(enc, 'replace')
+ break
+ else:
+ s = first_bytes.decode('utf-8', 'replace')
+
+ return re.match(r'^\s*<', s)
+
+
+def determine_protocol(info_dict):
+ protocol = info_dict.get('protocol')
+ if protocol is not None:
+ return protocol
+
+ url = info_dict['url']
+ if url.startswith('rtmp'):
+ return 'rtmp'
+ elif url.startswith('mms'):
+ return 'mms'
+ elif url.startswith('rtsp'):
+ return 'rtsp'
+
+ ext = determine_ext(url)
+ if ext == 'm3u8':
+ return 'm3u8'
+ elif ext == 'f4m':
+ return 'f4m'
+
+ return compat_urllib_parse_urlparse(url).scheme
+
+
+def render_table(header_row, data):
+ """ Render a list of rows, each as a list of values """
+ table = [header_row] + data
+ max_lens = [max(len(compat_str(v)) for v in col) for col in zip(*table)]
+ format_str = ' '.join('%-' + compat_str(ml + 1) + 's' for ml in max_lens[:-1]) + '%s'
+ return '\n'.join(format_str % tuple(row) for row in table)
+
+
+def _match_one(filter_part, dct):
+ COMPARISON_OPERATORS = {
+ '<': operator.lt,
+ '<=': operator.le,
+ '>': operator.gt,
+ '>=': operator.ge,
+ '=': operator.eq,
+ '!=': operator.ne,
+ }
+ operator_rex = re.compile(r'''(?x)\s*
+ (?P<key>[a-z_]+)
+ \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
+ (?:
+ (?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)|
+ (?P<quote>["\'])(?P<quotedstrval>(?:\\.|(?!(?P=quote)|\\).)+?)(?P=quote)|
+ (?P<strval>(?![0-9.])[a-z0-9A-Z]*)
+ )
+ \s*$
+ ''' % '|'.join(map(re.escape, COMPARISON_OPERATORS.keys())))
+ m = operator_rex.search(filter_part)
+ if m:
+ op = COMPARISON_OPERATORS[m.group('op')]
+ actual_value = dct.get(m.group('key'))
+ if (m.group('quotedstrval') is not None or
+ m.group('strval') is not None or
+ # If the original field is a string and matching comparisonvalue is
+ # a number we should respect the origin of the original field
+ # and process comparison value as a string (see
+ # https://github.com/rg3/youtube-dl/issues/11082).
+ actual_value is not None and m.group('intval') is not None and
+ isinstance(actual_value, compat_str)):
+ if m.group('op') not in ('=', '!='):
+ raise ValueError(
+ 'Operator %s does not support string values!' % m.group('op'))
+ comparison_value = m.group('quotedstrval') or m.group('strval') or m.group('intval')
+ quote = m.group('quote')
+ if quote is not None:
+ comparison_value = comparison_value.replace(r'\%s' % quote, quote)
+ else:
+ try:
+ comparison_value = int(m.group('intval'))
+ except ValueError:
+ comparison_value = parse_filesize(m.group('intval'))
+ if comparison_value is None:
+ comparison_value = parse_filesize(m.group('intval') + 'B')
+ if comparison_value is None:
+ raise ValueError(
+ 'Invalid integer value %r in filter part %r' % (
+ m.group('intval'), filter_part))
+ if actual_value is None:
+ return m.group('none_inclusive')
+ return op(actual_value, comparison_value)
+
+ UNARY_OPERATORS = {
+ '': lambda v: (v is True) if isinstance(v, bool) else (v is not None),
+ '!': lambda v: (v is False) if isinstance(v, bool) else (v is None),
+ }
+ operator_rex = re.compile(r'''(?x)\s*
+ (?P<op>%s)\s*(?P<key>[a-z_]+)
+ \s*$
+ ''' % '|'.join(map(re.escape, UNARY_OPERATORS.keys())))
+ m = operator_rex.search(filter_part)
+ if m:
+ op = UNARY_OPERATORS[m.group('op')]
+ actual_value = dct.get(m.group('key'))
+ return op(actual_value)
+
+ raise ValueError('Invalid filter part %r' % filter_part)
+
+
+def match_str(filter_str, dct):
+ """ Filter a dictionary with a simple string syntax. Returns True (=passes filter) or false """
+
+ return all(
+ _match_one(filter_part, dct) for filter_part in filter_str.split('&'))
+
+
+def match_filter_func(filter_str):
+ def _match_func(info_dict):
+ if match_str(filter_str, info_dict):
+ return None
+ else:
+ video_title = info_dict.get('title', info_dict.get('id', 'video'))
+ return '%s does not pass filter %s, skipping ..' % (video_title, filter_str)
+ return _match_func
+
+
+def parse_dfxp_time_expr(time_expr):
+ if not time_expr:
+ return
+
+ mobj = re.match(r'^(?P<time_offset>\d+(?:\.\d+)?)s?$', time_expr)
+ if mobj:
+ return float(mobj.group('time_offset'))
+
+ mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:(?:\.|:)\d+)?)$', time_expr)
+ if mobj:
+ return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3).replace(':', '.'))
+
+
+def srt_subtitles_timecode(seconds):
+ return '%02d:%02d:%02d,%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
+
+
+def dfxp2srt(dfxp_data):
+ '''
+ @param dfxp_data A bytes-like object containing DFXP data
+ @returns A unicode object containing converted SRT data
+ '''
+ LEGACY_NAMESPACES = (
+ (b'http://www.w3.org/ns/ttml', [
+ b'http://www.w3.org/2004/11/ttaf1',
+ b'http://www.w3.org/2006/04/ttaf1',
+ b'http://www.w3.org/2006/10/ttaf1',
+ ]),
+ (b'http://www.w3.org/ns/ttml#styling', [
+ b'http://www.w3.org/ns/ttml#style',
+ ]),
+ )
+
+ SUPPORTED_STYLING = [
+ 'color',
+ 'fontFamily',
+ 'fontSize',
+ 'fontStyle',
+ 'fontWeight',
+ 'textDecoration'
+ ]
+
+ _x = functools.partial(xpath_with_ns, ns_map={
+ 'xml': 'http://www.w3.org/XML/1998/namespace',
+ 'ttml': 'http://www.w3.org/ns/ttml',
+ 'tts': 'http://www.w3.org/ns/ttml#styling',
+ })
+
+ styles = {}
+ default_style = {}
+
+ class TTMLPElementParser(object):
+ _out = ''
+ _unclosed_elements = []
+ _applied_styles = []
+
+ def start(self, tag, attrib):
+ if tag in (_x('ttml:br'), 'br'):
+ self._out += '\n'
+ else:
+ unclosed_elements = []
+ style = {}
+ element_style_id = attrib.get('style')
+ if default_style:
+ style.update(default_style)
+ if element_style_id:
+ style.update(styles.get(element_style_id, {}))
+ for prop in SUPPORTED_STYLING:
+ prop_val = attrib.get(_x('tts:' + prop))
+ if prop_val:
+ style[prop] = prop_val
+ if style:
+ font = ''
+ for k, v in sorted(style.items()):
+ if self._applied_styles and self._applied_styles[-1].get(k) == v:
+ continue
+ if k == 'color':
+ font += ' color="%s"' % v
+ elif k == 'fontSize':
+ font += ' size="%s"' % v
+ elif k == 'fontFamily':
+ font += ' face="%s"' % v
+ elif k == 'fontWeight' and v == 'bold':
+ self._out += '<b>'
+ unclosed_elements.append('b')
+ elif k == 'fontStyle' and v == 'italic':
+ self._out += '<i>'
+ unclosed_elements.append('i')
+ elif k == 'textDecoration' and v == 'underline':
+ self._out += '<u>'
+ unclosed_elements.append('u')
+ if font:
+ self._out += '<font' + font + '>'
+ unclosed_elements.append('font')
+ applied_style = {}
+ if self._applied_styles:
+ applied_style.update(self._applied_styles[-1])
+ applied_style.update(style)
+ self._applied_styles.append(applied_style)
+ self._unclosed_elements.append(unclosed_elements)
+
+ def end(self, tag):
+ if tag not in (_x('ttml:br'), 'br'):
+ unclosed_elements = self._unclosed_elements.pop()
+ for element in reversed(unclosed_elements):
+ self._out += '</%s>' % element
+ if unclosed_elements and self._applied_styles:
+ self._applied_styles.pop()
+
+ def data(self, data):
+ self._out += data
+
+ def close(self):
+ return self._out.strip()
+
+ def parse_node(node):
+ target = TTMLPElementParser()
+ parser = xml.etree.ElementTree.XMLParser(target=target)
+ parser.feed(xml.etree.ElementTree.tostring(node))
+ return parser.close()
+
+ for k, v in LEGACY_NAMESPACES:
+ for ns in v:
+ dfxp_data = dfxp_data.replace(ns, k)
+
+ dfxp = compat_etree_fromstring(dfxp_data)
+ out = []
+ paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p')
+
+ if not paras:
+ raise ValueError('Invalid dfxp/TTML subtitle')
+
+ repeat = False
+ while True:
+ for style in dfxp.findall(_x('.//ttml:style')):
+ style_id = style.get('id') or style.get(_x('xml:id'))
+ if not style_id:
+ continue
+ parent_style_id = style.get('style')
+ if parent_style_id:
+ if parent_style_id not in styles:
+ repeat = True
+ continue
+ styles[style_id] = styles[parent_style_id].copy()
+ for prop in SUPPORTED_STYLING:
+ prop_val = style.get(_x('tts:' + prop))
+ if prop_val:
+ styles.setdefault(style_id, {})[prop] = prop_val
+ if repeat:
+ repeat = False
+ else:
+ break
+
+ for p in ('body', 'div'):
+ ele = xpath_element(dfxp, [_x('.//ttml:' + p), './/' + p])
+ if ele is None:
+ continue
+ style = styles.get(ele.get('style'))
+ if not style:
+ continue
+ default_style.update(style)
+
+ for para, index in zip(paras, itertools.count(1)):
+ begin_time = parse_dfxp_time_expr(para.attrib.get('begin'))
+ end_time = parse_dfxp_time_expr(para.attrib.get('end'))
+ dur = parse_dfxp_time_expr(para.attrib.get('dur'))
+ if begin_time is None:
+ continue
+ if not end_time:
+ if not dur:
+ continue
+ end_time = begin_time + dur
+ out.append('%d\n%s --> %s\n%s\n\n' % (
+ index,
+ srt_subtitles_timecode(begin_time),
+ srt_subtitles_timecode(end_time),
+ parse_node(para)))
+
+ return ''.join(out)
+
+
+def cli_option(params, command_option, param):
+ param = params.get(param)
+ if param:
+ param = compat_str(param)
+ return [command_option, param] if param is not None else []
+
+
+def cli_bool_option(params, command_option, param, true_value='true', false_value='false', separator=None):
+ param = params.get(param)
+ if param is None:
+ return []
+ assert isinstance(param, bool)
+ if separator:
+ return [command_option + separator + (true_value if param else false_value)]
+ return [command_option, true_value if param else false_value]
+
+
+def cli_valueless_option(params, command_option, param, expected_value=True):
+ param = params.get(param)
+ return [command_option] if param == expected_value else []
+
+
+def cli_configuration_args(params, param, default=[]):
+ ex_args = params.get(param)
+ if ex_args is None:
+ return default
+ assert isinstance(ex_args, list)
+ return ex_args
+
+
+class ISO639Utils(object):
+ # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+ _lang_map = {
+ 'aa': 'aar',
+ 'ab': 'abk',
+ 'ae': 'ave',
+ 'af': 'afr',
+ 'ak': 'aka',
+ 'am': 'amh',
+ 'an': 'arg',
+ 'ar': 'ara',
+ 'as': 'asm',
+ 'av': 'ava',
+ 'ay': 'aym',
+ 'az': 'aze',
+ 'ba': 'bak',
+ 'be': 'bel',
+ 'bg': 'bul',
+ 'bh': 'bih',
+ 'bi': 'bis',
+ 'bm': 'bam',
+ 'bn': 'ben',
+ 'bo': 'bod',
+ 'br': 'bre',
+ 'bs': 'bos',
+ 'ca': 'cat',
+ 'ce': 'che',
+ 'ch': 'cha',
+ 'co': 'cos',
+ 'cr': 'cre',
+ 'cs': 'ces',
+ 'cu': 'chu',
+ 'cv': 'chv',
+ 'cy': 'cym',
+ 'da': 'dan',
+ 'de': 'deu',
+ 'dv': 'div',
+ 'dz': 'dzo',
+ 'ee': 'ewe',
+ 'el': 'ell',
+ 'en': 'eng',
+ 'eo': 'epo',
+ 'es': 'spa',
+ 'et': 'est',
+ 'eu': 'eus',
+ 'fa': 'fas',
+ 'ff': 'ful',
+ 'fi': 'fin',
+ 'fj': 'fij',
+ 'fo': 'fao',
+ 'fr': 'fra',
+ 'fy': 'fry',
+ 'ga': 'gle',
+ 'gd': 'gla',
+ 'gl': 'glg',
+ 'gn': 'grn',
+ 'gu': 'guj',
+ 'gv': 'glv',
+ 'ha': 'hau',
+ 'he': 'heb',
+ 'hi': 'hin',
+ 'ho': 'hmo',
+ 'hr': 'hrv',
+ 'ht': 'hat',
+ 'hu': 'hun',
+ 'hy': 'hye',
+ 'hz': 'her',
+ 'ia': 'ina',
+ 'id': 'ind',
+ 'ie': 'ile',
+ 'ig': 'ibo',
+ 'ii': 'iii',
+ 'ik': 'ipk',
+ 'io': 'ido',
+ 'is': 'isl',
+ 'it': 'ita',
+ 'iu': 'iku',
+ 'ja': 'jpn',
+ 'jv': 'jav',
+ 'ka': 'kat',
+ 'kg': 'kon',
+ 'ki': 'kik',
+ 'kj': 'kua',
+ 'kk': 'kaz',
+ 'kl': 'kal',
+ 'km': 'khm',
+ 'kn': 'kan',
+ 'ko': 'kor',
+ 'kr': 'kau',
+ 'ks': 'kas',
+ 'ku': 'kur',
+ 'kv': 'kom',
+ 'kw': 'cor',
+ 'ky': 'kir',
+ 'la': 'lat',
+ 'lb': 'ltz',
+ 'lg': 'lug',
+ 'li': 'lim',
+ 'ln': 'lin',
+ 'lo': 'lao',
+ 'lt': 'lit',
+ 'lu': 'lub',
+ 'lv': 'lav',
+ 'mg': 'mlg',
+ 'mh': 'mah',
+ 'mi': 'mri',
+ 'mk': 'mkd',
+ 'ml': 'mal',
+ 'mn': 'mon',
+ 'mr': 'mar',
+ 'ms': 'msa',
+ 'mt': 'mlt',
+ 'my': 'mya',
+ 'na': 'nau',
+ 'nb': 'nob',
+ 'nd': 'nde',
+ 'ne': 'nep',
+ 'ng': 'ndo',
+ 'nl': 'nld',
+ 'nn': 'nno',
+ 'no': 'nor',
+ 'nr': 'nbl',
+ 'nv': 'nav',
+ 'ny': 'nya',
+ 'oc': 'oci',
+ 'oj': 'oji',
+ 'om': 'orm',
+ 'or': 'ori',
+ 'os': 'oss',
+ 'pa': 'pan',
+ 'pi': 'pli',
+ 'pl': 'pol',
+ 'ps': 'pus',
+ 'pt': 'por',
+ 'qu': 'que',
+ 'rm': 'roh',
+ 'rn': 'run',
+ 'ro': 'ron',
+ 'ru': 'rus',
+ 'rw': 'kin',
+ 'sa': 'san',
+ 'sc': 'srd',
+ 'sd': 'snd',
+ 'se': 'sme',
+ 'sg': 'sag',
+ 'si': 'sin',
+ 'sk': 'slk',
+ 'sl': 'slv',
+ 'sm': 'smo',
+ 'sn': 'sna',
+ 'so': 'som',
+ 'sq': 'sqi',
+ 'sr': 'srp',
+ 'ss': 'ssw',
+ 'st': 'sot',
+ 'su': 'sun',
+ 'sv': 'swe',
+ 'sw': 'swa',
+ 'ta': 'tam',
+ 'te': 'tel',
+ 'tg': 'tgk',
+ 'th': 'tha',
+ 'ti': 'tir',
+ 'tk': 'tuk',
+ 'tl': 'tgl',
+ 'tn': 'tsn',
+ 'to': 'ton',
+ 'tr': 'tur',
+ 'ts': 'tso',
+ 'tt': 'tat',
+ 'tw': 'twi',
+ 'ty': 'tah',
+ 'ug': 'uig',
+ 'uk': 'ukr',
+ 'ur': 'urd',
+ 'uz': 'uzb',
+ 've': 'ven',
+ 'vi': 'vie',
+ 'vo': 'vol',
+ 'wa': 'wln',
+ 'wo': 'wol',
+ 'xh': 'xho',
+ 'yi': 'yid',
+ 'yo': 'yor',
+ 'za': 'zha',
+ 'zh': 'zho',
+ 'zu': 'zul',
+ }
+
+ @classmethod
+ def short2long(cls, code):
+ """Convert language code from ISO 639-1 to ISO 639-2/T"""
+ return cls._lang_map.get(code[:2])
+
+ @classmethod
+ def long2short(cls, code):
+ """Convert language code from ISO 639-2/T to ISO 639-1"""
+ for short_name, long_name in cls._lang_map.items():
+ if long_name == code:
+ return short_name
+
+
+class ISO3166Utils(object):
+ # From http://data.okfn.org/data/core/country-list
+ _country_map = {
+ 'AF': 'Afghanistan',
+ 'AX': 'Åland Islands',
+ 'AL': 'Albania',
+ 'DZ': 'Algeria',
+ 'AS': 'American Samoa',
+ 'AD': 'Andorra',
+ 'AO': 'Angola',
+ 'AI': 'Anguilla',
+ 'AQ': 'Antarctica',
+ 'AG': 'Antigua and Barbuda',
+ 'AR': 'Argentina',
+ 'AM': 'Armenia',
+ 'AW': 'Aruba',
+ 'AU': 'Australia',
+ 'AT': 'Austria',
+ 'AZ': 'Azerbaijan',
+ 'BS': 'Bahamas',
+ 'BH': 'Bahrain',
+ 'BD': 'Bangladesh',
+ 'BB': 'Barbados',
+ 'BY': 'Belarus',
+ 'BE': 'Belgium',
+ 'BZ': 'Belize',
+ 'BJ': 'Benin',
+ 'BM': 'Bermuda',
+ 'BT': 'Bhutan',
+ 'BO': 'Bolivia, Plurinational State of',
+ 'BQ': 'Bonaire, Sint Eustatius and Saba',
+ 'BA': 'Bosnia and Herzegovina',
+ 'BW': 'Botswana',
+ 'BV': 'Bouvet Island',
+ 'BR': 'Brazil',
+ 'IO': 'British Indian Ocean Territory',
+ 'BN': 'Brunei Darussalam',
+ 'BG': 'Bulgaria',
+ 'BF': 'Burkina Faso',
+ 'BI': 'Burundi',
+ 'KH': 'Cambodia',
+ 'CM': 'Cameroon',
+ 'CA': 'Canada',
+ 'CV': 'Cape Verde',
+ 'KY': 'Cayman Islands',
+ 'CF': 'Central African Republic',
+ 'TD': 'Chad',
+ 'CL': 'Chile',
+ 'CN': 'China',
+ 'CX': 'Christmas Island',
+ 'CC': 'Cocos (Keeling) Islands',
+ 'CO': 'Colombia',
+ 'KM': 'Comoros',
+ 'CG': 'Congo',
+ 'CD': 'Congo, the Democratic Republic of the',
+ 'CK': 'Cook Islands',
+ 'CR': 'Costa Rica',
+ 'CI': 'Côte d\'Ivoire',
+ 'HR': 'Croatia',
+ 'CU': 'Cuba',
+ 'CW': 'Curaçao',
+ 'CY': 'Cyprus',
+ 'CZ': 'Czech Republic',
+ 'DK': 'Denmark',
+ 'DJ': 'Djibouti',
+ 'DM': 'Dominica',
+ 'DO': 'Dominican Republic',
+ 'EC': 'Ecuador',
+ 'EG': 'Egypt',
+ 'SV': 'El Salvador',
+ 'GQ': 'Equatorial Guinea',
+ 'ER': 'Eritrea',
+ 'EE': 'Estonia',
+ 'ET': 'Ethiopia',
+ 'FK': 'Falkland Islands (Malvinas)',
+ 'FO': 'Faroe Islands',
+ 'FJ': 'Fiji',
+ 'FI': 'Finland',
+ 'FR': 'France',
+ 'GF': 'French Guiana',
+ 'PF': 'French Polynesia',
+ 'TF': 'French Southern Territories',
+ 'GA': 'Gabon',
+ 'GM': 'Gambia',
+ 'GE': 'Georgia',
+ 'DE': 'Germany',
+ 'GH': 'Ghana',
+ 'GI': 'Gibraltar',
+ 'GR': 'Greece',
+ 'GL': 'Greenland',
+ 'GD': 'Grenada',
+ 'GP': 'Guadeloupe',
+ 'GU': 'Guam',
+ 'GT': 'Guatemala',
+ 'GG': 'Guernsey',
+ 'GN': 'Guinea',
+ 'GW': 'Guinea-Bissau',
+ 'GY': 'Guyana',
+ 'HT': 'Haiti',
+ 'HM': 'Heard Island and McDonald Islands',
+ 'VA': 'Holy See (Vatican City State)',
+ 'HN': 'Honduras',
+ 'HK': 'Hong Kong',
+ 'HU': 'Hungary',
+ 'IS': 'Iceland',
+ 'IN': 'India',
+ 'ID': 'Indonesia',
+ 'IR': 'Iran, Islamic Republic of',
+ 'IQ': 'Iraq',
+ 'IE': 'Ireland',
+ 'IM': 'Isle of Man',
+ 'IL': 'Israel',
+ 'IT': 'Italy',
+ 'JM': 'Jamaica',
+ 'JP': 'Japan',
+ 'JE': 'Jersey',
+ 'JO': 'Jordan',
+ 'KZ': 'Kazakhstan',
+ 'KE': 'Kenya',
+ 'KI': 'Kiribati',
+ 'KP': 'Korea, Democratic People\'s Republic of',
+ 'KR': 'Korea, Republic of',
+ 'KW': 'Kuwait',
+ 'KG': 'Kyrgyzstan',
+ 'LA': 'Lao People\'s Democratic Republic',
+ 'LV': 'Latvia',
+ 'LB': 'Lebanon',
+ 'LS': 'Lesotho',
+ 'LR': 'Liberia',
+ 'LY': 'Libya',
+ 'LI': 'Liechtenstein',
+ 'LT': 'Lithuania',
+ 'LU': 'Luxembourg',
+ 'MO': 'Macao',
+ 'MK': 'Macedonia, the Former Yugoslav Republic of',
+ 'MG': 'Madagascar',
+ 'MW': 'Malawi',
+ 'MY': 'Malaysia',
+ 'MV': 'Maldives',
+ 'ML': 'Mali',
+ 'MT': 'Malta',
+ 'MH': 'Marshall Islands',
+ 'MQ': 'Martinique',
+ 'MR': 'Mauritania',
+ 'MU': 'Mauritius',
+ 'YT': 'Mayotte',
+ 'MX': 'Mexico',
+ 'FM': 'Micronesia, Federated States of',
+ 'MD': 'Moldova, Republic of',
+ 'MC': 'Monaco',
+ 'MN': 'Mongolia',
+ 'ME': 'Montenegro',
+ 'MS': 'Montserrat',
+ 'MA': 'Morocco',
+ 'MZ': 'Mozambique',
+ 'MM': 'Myanmar',
+ 'NA': 'Namibia',
+ 'NR': 'Nauru',
+ 'NP': 'Nepal',
+ 'NL': 'Netherlands',
+ 'NC': 'New Caledonia',
+ 'NZ': 'New Zealand',
+ 'NI': 'Nicaragua',
+ 'NE': 'Niger',
+ 'NG': 'Nigeria',
+ 'NU': 'Niue',
+ 'NF': 'Norfolk Island',
+ 'MP': 'Northern Mariana Islands',
+ 'NO': 'Norway',
+ 'OM': 'Oman',
+ 'PK': 'Pakistan',
+ 'PW': 'Palau',
+ 'PS': 'Palestine, State of',
+ 'PA': 'Panama',
+ 'PG': 'Papua New Guinea',
+ 'PY': 'Paraguay',
+ 'PE': 'Peru',
+ 'PH': 'Philippines',
+ 'PN': 'Pitcairn',
+ 'PL': 'Poland',
+ 'PT': 'Portugal',
+ 'PR': 'Puerto Rico',
+ 'QA': 'Qatar',
+ 'RE': 'Réunion',
+ 'RO': 'Romania',
+ 'RU': 'Russian Federation',
+ 'RW': 'Rwanda',
+ 'BL': 'Saint Barthélemy',
+ 'SH': 'Saint Helena, Ascension and Tristan da Cunha',
+ 'KN': 'Saint Kitts and Nevis',
+ 'LC': 'Saint Lucia',
+ 'MF': 'Saint Martin (French part)',
+ 'PM': 'Saint Pierre and Miquelon',
+ 'VC': 'Saint Vincent and the Grenadines',
+ 'WS': 'Samoa',
+ 'SM': 'San Marino',
+ 'ST': 'Sao Tome and Principe',
+ 'SA': 'Saudi Arabia',
+ 'SN': 'Senegal',
+ 'RS': 'Serbia',
+ 'SC': 'Seychelles',
+ 'SL': 'Sierra Leone',
+ 'SG': 'Singapore',
+ 'SX': 'Sint Maarten (Dutch part)',
+ 'SK': 'Slovakia',
+ 'SI': 'Slovenia',
+ 'SB': 'Solomon Islands',
+ 'SO': 'Somalia',
+ 'ZA': 'South Africa',
+ 'GS': 'South Georgia and the South Sandwich Islands',
+ 'SS': 'South Sudan',
+ 'ES': 'Spain',
+ 'LK': 'Sri Lanka',
+ 'SD': 'Sudan',
+ 'SR': 'Suriname',
+ 'SJ': 'Svalbard and Jan Mayen',
+ 'SZ': 'Swaziland',
+ 'SE': 'Sweden',
+ 'CH': 'Switzerland',
+ 'SY': 'Syrian Arab Republic',
+ 'TW': 'Taiwan, Province of China',
+ 'TJ': 'Tajikistan',
+ 'TZ': 'Tanzania, United Republic of',
+ 'TH': 'Thailand',
+ 'TL': 'Timor-Leste',
+ 'TG': 'Togo',
+ 'TK': 'Tokelau',
+ 'TO': 'Tonga',
+ 'TT': 'Trinidad and Tobago',
+ 'TN': 'Tunisia',
+ 'TR': 'Turkey',
+ 'TM': 'Turkmenistan',
+ 'TC': 'Turks and Caicos Islands',
+ 'TV': 'Tuvalu',
+ 'UG': 'Uganda',
+ 'UA': 'Ukraine',
+ 'AE': 'United Arab Emirates',
+ 'GB': 'United Kingdom',
+ 'US': 'United States',
+ 'UM': 'United States Minor Outlying Islands',
+ 'UY': 'Uruguay',
+ 'UZ': 'Uzbekistan',
+ 'VU': 'Vanuatu',
+ 'VE': 'Venezuela, Bolivarian Republic of',
+ 'VN': 'Viet Nam',
+ 'VG': 'Virgin Islands, British',
+ 'VI': 'Virgin Islands, U.S.',
+ 'WF': 'Wallis and Futuna',
+ 'EH': 'Western Sahara',
+ 'YE': 'Yemen',
+ 'ZM': 'Zambia',
+ 'ZW': 'Zimbabwe',
+ }
+
+ @classmethod
+ def short2full(cls, code):
+ """Convert an ISO 3166-2 country code to the corresponding full name"""
+ return cls._country_map.get(code.upper())
+
+
+class GeoUtils(object):
+ # Major IPv4 address blocks per country
+ _country_ip_map = {
+ 'AD': '85.94.160.0/19',
+ 'AE': '94.200.0.0/13',
+ 'AF': '149.54.0.0/17',
+ 'AG': '209.59.64.0/18',
+ 'AI': '204.14.248.0/21',
+ 'AL': '46.99.0.0/16',
+ 'AM': '46.70.0.0/15',
+ 'AO': '105.168.0.0/13',
+ 'AP': '159.117.192.0/21',
+ 'AR': '181.0.0.0/12',
+ 'AS': '202.70.112.0/20',
+ 'AT': '84.112.0.0/13',
+ 'AU': '1.128.0.0/11',
+ 'AW': '181.41.0.0/18',
+ 'AZ': '5.191.0.0/16',
+ 'BA': '31.176.128.0/17',
+ 'BB': '65.48.128.0/17',
+ 'BD': '114.130.0.0/16',
+ 'BE': '57.0.0.0/8',
+ 'BF': '129.45.128.0/17',
+ 'BG': '95.42.0.0/15',
+ 'BH': '37.131.0.0/17',
+ 'BI': '154.117.192.0/18',
+ 'BJ': '137.255.0.0/16',
+ 'BL': '192.131.134.0/24',
+ 'BM': '196.12.64.0/18',
+ 'BN': '156.31.0.0/16',
+ 'BO': '161.56.0.0/16',
+ 'BQ': '161.0.80.0/20',
+ 'BR': '152.240.0.0/12',
+ 'BS': '24.51.64.0/18',
+ 'BT': '119.2.96.0/19',
+ 'BW': '168.167.0.0/16',
+ 'BY': '178.120.0.0/13',
+ 'BZ': '179.42.192.0/18',
+ 'CA': '99.224.0.0/11',
+ 'CD': '41.243.0.0/16',
+ 'CF': '196.32.200.0/21',
+ 'CG': '197.214.128.0/17',
+ 'CH': '85.0.0.0/13',
+ 'CI': '154.232.0.0/14',
+ 'CK': '202.65.32.0/19',
+ 'CL': '152.172.0.0/14',
+ 'CM': '165.210.0.0/15',
+ 'CN': '36.128.0.0/10',
+ 'CO': '181.240.0.0/12',
+ 'CR': '201.192.0.0/12',
+ 'CU': '152.206.0.0/15',
+ 'CV': '165.90.96.0/19',
+ 'CW': '190.88.128.0/17',
+ 'CY': '46.198.0.0/15',
+ 'CZ': '88.100.0.0/14',
+ 'DE': '53.0.0.0/8',
+ 'DJ': '197.241.0.0/17',
+ 'DK': '87.48.0.0/12',
+ 'DM': '192.243.48.0/20',
+ 'DO': '152.166.0.0/15',
+ 'DZ': '41.96.0.0/12',
+ 'EC': '186.68.0.0/15',
+ 'EE': '90.190.0.0/15',
+ 'EG': '156.160.0.0/11',
+ 'ER': '196.200.96.0/20',
+ 'ES': '88.0.0.0/11',
+ 'ET': '196.188.0.0/14',
+ 'EU': '2.16.0.0/13',
+ 'FI': '91.152.0.0/13',
+ 'FJ': '144.120.0.0/16',
+ 'FM': '119.252.112.0/20',
+ 'FO': '88.85.32.0/19',
+ 'FR': '90.0.0.0/9',
+ 'GA': '41.158.0.0/15',
+ 'GB': '25.0.0.0/8',
+ 'GD': '74.122.88.0/21',
+ 'GE': '31.146.0.0/16',
+ 'GF': '161.22.64.0/18',
+ 'GG': '62.68.160.0/19',
+ 'GH': '45.208.0.0/14',
+ 'GI': '85.115.128.0/19',
+ 'GL': '88.83.0.0/19',
+ 'GM': '160.182.0.0/15',
+ 'GN': '197.149.192.0/18',
+ 'GP': '104.250.0.0/19',
+ 'GQ': '105.235.224.0/20',
+ 'GR': '94.64.0.0/13',
+ 'GT': '168.234.0.0/16',
+ 'GU': '168.123.0.0/16',
+ 'GW': '197.214.80.0/20',
+ 'GY': '181.41.64.0/18',
+ 'HK': '113.252.0.0/14',
+ 'HN': '181.210.0.0/16',
+ 'HR': '93.136.0.0/13',
+ 'HT': '148.102.128.0/17',
+ 'HU': '84.0.0.0/14',
+ 'ID': '39.192.0.0/10',
+ 'IE': '87.32.0.0/12',
+ 'IL': '79.176.0.0/13',
+ 'IM': '5.62.80.0/20',
+ 'IN': '117.192.0.0/10',
+ 'IO': '203.83.48.0/21',
+ 'IQ': '37.236.0.0/14',
+ 'IR': '2.176.0.0/12',
+ 'IS': '82.221.0.0/16',
+ 'IT': '79.0.0.0/10',
+ 'JE': '87.244.64.0/18',
+ 'JM': '72.27.0.0/17',
+ 'JO': '176.29.0.0/16',
+ 'JP': '126.0.0.0/8',
+ 'KE': '105.48.0.0/12',
+ 'KG': '158.181.128.0/17',
+ 'KH': '36.37.128.0/17',
+ 'KI': '103.25.140.0/22',
+ 'KM': '197.255.224.0/20',
+ 'KN': '198.32.32.0/19',
+ 'KP': '175.45.176.0/22',
+ 'KR': '175.192.0.0/10',
+ 'KW': '37.36.0.0/14',
+ 'KY': '64.96.0.0/15',
+ 'KZ': '2.72.0.0/13',
+ 'LA': '115.84.64.0/18',
+ 'LB': '178.135.0.0/16',
+ 'LC': '192.147.231.0/24',
+ 'LI': '82.117.0.0/19',
+ 'LK': '112.134.0.0/15',
+ 'LR': '41.86.0.0/19',
+ 'LS': '129.232.0.0/17',
+ 'LT': '78.56.0.0/13',
+ 'LU': '188.42.0.0/16',
+ 'LV': '46.109.0.0/16',
+ 'LY': '41.252.0.0/14',
+ 'MA': '105.128.0.0/11',
+ 'MC': '88.209.64.0/18',
+ 'MD': '37.246.0.0/16',
+ 'ME': '178.175.0.0/17',
+ 'MF': '74.112.232.0/21',
+ 'MG': '154.126.0.0/17',
+ 'MH': '117.103.88.0/21',
+ 'MK': '77.28.0.0/15',
+ 'ML': '154.118.128.0/18',
+ 'MM': '37.111.0.0/17',
+ 'MN': '49.0.128.0/17',
+ 'MO': '60.246.0.0/16',
+ 'MP': '202.88.64.0/20',
+ 'MQ': '109.203.224.0/19',
+ 'MR': '41.188.64.0/18',
+ 'MS': '208.90.112.0/22',
+ 'MT': '46.11.0.0/16',
+ 'MU': '105.16.0.0/12',
+ 'MV': '27.114.128.0/18',
+ 'MW': '105.234.0.0/16',
+ 'MX': '187.192.0.0/11',
+ 'MY': '175.136.0.0/13',
+ 'MZ': '197.218.0.0/15',
+ 'NA': '41.182.0.0/16',
+ 'NC': '101.101.0.0/18',
+ 'NE': '197.214.0.0/18',
+ 'NF': '203.17.240.0/22',
+ 'NG': '105.112.0.0/12',
+ 'NI': '186.76.0.0/15',
+ 'NL': '145.96.0.0/11',
+ 'NO': '84.208.0.0/13',
+ 'NP': '36.252.0.0/15',
+ 'NR': '203.98.224.0/19',
+ 'NU': '49.156.48.0/22',
+ 'NZ': '49.224.0.0/14',
+ 'OM': '5.36.0.0/15',
+ 'PA': '186.72.0.0/15',
+ 'PE': '186.160.0.0/14',
+ 'PF': '123.50.64.0/18',
+ 'PG': '124.240.192.0/19',
+ 'PH': '49.144.0.0/13',
+ 'PK': '39.32.0.0/11',
+ 'PL': '83.0.0.0/11',
+ 'PM': '70.36.0.0/20',
+ 'PR': '66.50.0.0/16',
+ 'PS': '188.161.0.0/16',
+ 'PT': '85.240.0.0/13',
+ 'PW': '202.124.224.0/20',
+ 'PY': '181.120.0.0/14',
+ 'QA': '37.210.0.0/15',
+ 'RE': '139.26.0.0/16',
+ 'RO': '79.112.0.0/13',
+ 'RS': '178.220.0.0/14',
+ 'RU': '5.136.0.0/13',
+ 'RW': '105.178.0.0/15',
+ 'SA': '188.48.0.0/13',
+ 'SB': '202.1.160.0/19',
+ 'SC': '154.192.0.0/11',
+ 'SD': '154.96.0.0/13',
+ 'SE': '78.64.0.0/12',
+ 'SG': '152.56.0.0/14',
+ 'SI': '188.196.0.0/14',
+ 'SK': '78.98.0.0/15',
+ 'SL': '197.215.0.0/17',
+ 'SM': '89.186.32.0/19',
+ 'SN': '41.82.0.0/15',
+ 'SO': '197.220.64.0/19',
+ 'SR': '186.179.128.0/17',
+ 'SS': '105.235.208.0/21',
+ 'ST': '197.159.160.0/19',
+ 'SV': '168.243.0.0/16',
+ 'SX': '190.102.0.0/20',
+ 'SY': '5.0.0.0/16',
+ 'SZ': '41.84.224.0/19',
+ 'TC': '65.255.48.0/20',
+ 'TD': '154.68.128.0/19',
+ 'TG': '196.168.0.0/14',
+ 'TH': '171.96.0.0/13',
+ 'TJ': '85.9.128.0/18',
+ 'TK': '27.96.24.0/21',
+ 'TL': '180.189.160.0/20',
+ 'TM': '95.85.96.0/19',
+ 'TN': '197.0.0.0/11',
+ 'TO': '175.176.144.0/21',
+ 'TR': '78.160.0.0/11',
+ 'TT': '186.44.0.0/15',
+ 'TV': '202.2.96.0/19',
+ 'TW': '120.96.0.0/11',
+ 'TZ': '156.156.0.0/14',
+ 'UA': '93.72.0.0/13',
+ 'UG': '154.224.0.0/13',
+ 'US': '3.0.0.0/8',
+ 'UY': '167.56.0.0/13',
+ 'UZ': '82.215.64.0/18',
+ 'VA': '212.77.0.0/19',
+ 'VC': '24.92.144.0/20',
+ 'VE': '186.88.0.0/13',
+ 'VG': '172.103.64.0/18',
+ 'VI': '146.226.0.0/16',
+ 'VN': '14.160.0.0/11',
+ 'VU': '202.80.32.0/20',
+ 'WF': '117.20.32.0/21',
+ 'WS': '202.4.32.0/19',
+ 'YE': '134.35.0.0/16',
+ 'YT': '41.242.116.0/22',
+ 'ZA': '41.0.0.0/11',
+ 'ZM': '165.56.0.0/13',
+ 'ZW': '41.85.192.0/19',
+ }
+
+ @classmethod
+ def random_ipv4(cls, code_or_block):
+ if len(code_or_block) == 2:
+ block = cls._country_ip_map.get(code_or_block.upper())
+ if not block:
+ return None
+ else:
+ block = code_or_block
+ addr, preflen = block.split('/')
+ addr_min = compat_struct_unpack('!L', socket.inet_aton(addr))[0]
+ addr_max = addr_min | (0xffffffff >> int(preflen))
+ return compat_str(socket.inet_ntoa(
+ compat_struct_pack('!L', random.randint(addr_min, addr_max))))
+
+
+class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
+ def __init__(self, proxies=None):
+ # Set default handlers
+ for type in ('http', 'https'):
+ setattr(self, '%s_open' % type,
+ lambda r, proxy='__noproxy__', type=type, meth=self.proxy_open:
+ meth(r, proxy, type))
+ return compat_urllib_request.ProxyHandler.__init__(self, proxies)
+
+ def proxy_open(self, req, proxy, type):
+ req_proxy = req.headers.get('Ytdl-request-proxy')
+ if req_proxy is not None:
+ proxy = req_proxy
+ del req.headers['Ytdl-request-proxy']
+
+ if proxy == '__noproxy__':
+ return None # No Proxy
+ if compat_urlparse.urlparse(proxy).scheme.lower() in ('socks', 'socks4', 'socks4a', 'socks5'):
+ req.add_header('Ytdl-socks-proxy', proxy)
+ # youtube-dl's http/https handlers do wrapping the socket with socks
+ return None
+ return compat_urllib_request.ProxyHandler.proxy_open(
+ self, req, proxy, type)
+
+
+# Both long_to_bytes and bytes_to_long are adapted from PyCrypto, which is
+# released into Public Domain
+# https://github.com/dlitz/pycrypto/blob/master/lib/Crypto/Util/number.py#L387
+
+def long_to_bytes(n, blocksize=0):
+ """long_to_bytes(n:long, blocksize:int) : string
+ Convert a long integer to a byte string.
+
+ If optional blocksize is given and greater than zero, pad the front of the
+ byte string with binary zeros so that the length is a multiple of
+ blocksize.
+ """
+ # after much testing, this algorithm was deemed to be the fastest
+ s = b''
+ n = int(n)
+ while n > 0:
+ s = compat_struct_pack('>I', n & 0xffffffff) + s
+ n = n >> 32
+ # strip off leading zeros
+ for i in range(len(s)):
+ if s[i] != b'\000'[0]:
+ break
+ else:
+ # only happens when n == 0
+ s = b'\000'
+ i = 0
+ s = s[i:]
+ # add back some pad bytes. this could be done more efficiently w.r.t. the
+ # de-padding being done above, but sigh...
+ if blocksize > 0 and len(s) % blocksize:
+ s = (blocksize - len(s) % blocksize) * b'\000' + s
+ return s
+
+
+def bytes_to_long(s):
+ """bytes_to_long(string) : long
+ Convert a byte string to a long integer.
+
+ This is (essentially) the inverse of long_to_bytes().
+ """
+ acc = 0
+ length = len(s)
+ if length % 4:
+ extra = (4 - length % 4)
+ s = b'\000' * extra + s
+ length = length + extra
+ for i in range(0, length, 4):
+ acc = (acc << 32) + compat_struct_unpack('>I', s[i:i + 4])[0]
+ return acc
+
+
+def ohdave_rsa_encrypt(data, exponent, modulus):
+ '''
+ Implement OHDave's RSA algorithm. See http://www.ohdave.com/rsa/
+
+ Input:
+ data: data to encrypt, bytes-like object
+ exponent, modulus: parameter e and N of RSA algorithm, both integer
+ Output: hex string of encrypted data
+
+ Limitation: supports one block encryption only
+ '''
+
+ payload = int(binascii.hexlify(data[::-1]), 16)
+ encrypted = pow(payload, exponent, modulus)
+ return '%x' % encrypted
+
+
+def pkcs1pad(data, length):
+ """
+ Padding input data with PKCS#1 scheme
+
+ @param {int[]} data input data
+ @param {int} length target length
+ @returns {int[]} padded data
+ """
+ if len(data) > length - 11:
+ raise ValueError('Input data too long for PKCS#1 padding')
+
+ pseudo_random = [random.randint(0, 254) for _ in range(length - len(data) - 3)]
+ return [0, 2] + pseudo_random + [0] + data
+
+
+def encode_base_n(num, n, table=None):
+ FULL_TABLE = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
+ if not table:
+ table = FULL_TABLE[:n]
+
+ if n > len(table):
+ raise ValueError('base %d exceeds table length %d' % (n, len(table)))
+
+ if num == 0:
+ return table[0]
+
+ ret = ''
+ while num:
+ ret = table[num % n] + ret
+ num = num // n
+ return ret
+
+
+def decode_packed_codes(code):
+ mobj = re.search(PACKED_CODES_RE, code)
+ obfucasted_code, base, count, symbols = mobj.groups()
+ base = int(base)
+ count = int(count)
+ symbols = symbols.split('|')
+ symbol_table = {}
+
+ while count:
+ count -= 1
+ base_n_count = encode_base_n(count, base)
+ symbol_table[base_n_count] = symbols[count] or base_n_count
+
+ return re.sub(
+ r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)],
+ obfucasted_code)
+
+
+def parse_m3u8_attributes(attrib):
+ info = {}
+ for (key, val) in re.findall(r'(?P<key>[A-Z0-9-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)', attrib):
+ if val.startswith('"'):
+ val = val[1:-1]
+ info[key] = val
+ return info
+
+
+def urshift(val, n):
+ return val >> n if val >= 0 else (val + 0x100000000) >> n
+
+
+# Based on png2str() written by @gdkchan and improved by @yokrysty
+# Originally posted at https://github.com/rg3/youtube-dl/issues/9706
+def decode_png(png_data):
+ # Reference: https://www.w3.org/TR/PNG/
+ header = png_data[8:]
+
+ if png_data[:8] != b'\x89PNG\x0d\x0a\x1a\x0a' or header[4:8] != b'IHDR':
+ raise IOError('Not a valid PNG file.')
+
+ int_map = {1: '>B', 2: '>H', 4: '>I'}
+ unpack_integer = lambda x: compat_struct_unpack(int_map[len(x)], x)[0]
+
+ chunks = []
+
+ while header:
+ length = unpack_integer(header[:4])
+ header = header[4:]
+
+ chunk_type = header[:4]
+ header = header[4:]
+
+ chunk_data = header[:length]
+ header = header[length:]
+
+ header = header[4:] # Skip CRC
+
+ chunks.append({
+ 'type': chunk_type,
+ 'length': length,
+ 'data': chunk_data
+ })
+
+ ihdr = chunks[0]['data']
+
+ width = unpack_integer(ihdr[:4])
+ height = unpack_integer(ihdr[4:8])
+
+ idat = b''
+
+ for chunk in chunks:
+ if chunk['type'] == b'IDAT':
+ idat += chunk['data']
+
+ if not idat:
+ raise IOError('Unable to read PNG data.')
+
+ decompressed_data = bytearray(zlib.decompress(idat))
+
+ stride = width * 3
+ pixels = []
+
+ def _get_pixel(idx):
+ x = idx % stride
+ y = idx // stride
+ return pixels[y][x]
+
+ for y in range(height):
+ basePos = y * (1 + stride)
+ filter_type = decompressed_data[basePos]
+
+ current_row = []
+
+ pixels.append(current_row)
+
+ for x in range(stride):
+ color = decompressed_data[1 + basePos + x]
+ basex = y * stride + x
+ left = 0
+ up = 0
+
+ if x > 2:
+ left = _get_pixel(basex - 3)
+ if y > 0:
+ up = _get_pixel(basex - stride)
+
+ if filter_type == 1: # Sub
+ color = (color + left) & 0xff
+ elif filter_type == 2: # Up
+ color = (color + up) & 0xff
+ elif filter_type == 3: # Average
+ color = (color + ((left + up) >> 1)) & 0xff
+ elif filter_type == 4: # Paeth
+ a = left
+ b = up
+ c = 0
+
+ if x > 2 and y > 0:
+ c = _get_pixel(basex - stride - 3)
+
+ p = a + b - c
+
+ pa = abs(p - a)
+ pb = abs(p - b)
+ pc = abs(p - c)
+
+ if pa <= pb and pa <= pc:
+ color = (color + a) & 0xff
+ elif pb <= pc:
+ color = (color + b) & 0xff
+ else:
+ color = (color + c) & 0xff
+
+ current_row.append(color)
+
+ return width, height, pixels
+
+
+def write_xattr(path, key, value):
+ # This mess below finds the best xattr tool for the job
+ try:
+ # try the pyxattr module...
+ import xattr
+
+ if hasattr(xattr, 'set'): # pyxattr
+ # Unicode arguments are not supported in python-pyxattr until
+ # version 0.5.0
+ # See https://github.com/rg3/youtube-dl/issues/5498
+ pyxattr_required_version = '0.5.0'
+ if version_tuple(xattr.__version__) < version_tuple(pyxattr_required_version):
+ # TODO: fallback to CLI tools
+ raise XAttrUnavailableError(
+ 'python-pyxattr is detected but is too old. '
+ 'youtube-dl requires %s or above while your version is %s. '
+ 'Falling back to other xattr implementations' % (
+ pyxattr_required_version, xattr.__version__))
+
+ setxattr = xattr.set
+ else: # xattr
+ setxattr = xattr.setxattr
+
+ try:
+ setxattr(path, key, value)
+ except EnvironmentError as e:
+ raise XAttrMetadataError(e.errno, e.strerror)
+
+ except ImportError:
+ if compat_os_name == 'nt':
+ # Write xattrs to NTFS Alternate Data Streams:
+ # http://en.wikipedia.org/wiki/NTFS#Alternate_data_streams_.28ADS.29
+ assert ':' not in key
+ assert os.path.exists(path)
+
+ ads_fn = path + ':' + key
+ try:
+ with open(ads_fn, 'wb') as f:
+ f.write(value)
+ except EnvironmentError as e:
+ raise XAttrMetadataError(e.errno, e.strerror)
+ else:
+ user_has_setfattr = check_executable('setfattr', ['--version'])
+ user_has_xattr = check_executable('xattr', ['-h'])
+
+ if user_has_setfattr or user_has_xattr:
+
+ value = value.decode('utf-8')
+ if user_has_setfattr:
+ executable = 'setfattr'
+ opts = ['-n', key, '-v', value]
+ elif user_has_xattr:
+ executable = 'xattr'
+ opts = ['-w', key, value]
+
+ cmd = ([encodeFilename(executable, True)] +
+ [encodeArgument(o) for o in opts] +
+ [encodeFilename(path, True)])
+
+ try:
+ p = subprocess.Popen(
+ cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
+ except EnvironmentError as e:
+ raise XAttrMetadataError(e.errno, e.strerror)
+ stdout, stderr = p.communicate()
+ stderr = stderr.decode('utf-8', 'replace')
+ if p.returncode != 0:
+ raise XAttrMetadataError(p.returncode, stderr)
+
+ else:
+ # On Unix, and can't find pyxattr, setfattr, or xattr.
+ if sys.platform.startswith('linux'):
+ raise XAttrUnavailableError(
+ "Couldn't find a tool to set the xattrs. "
+ "Install either the python 'pyxattr' or 'xattr' "
+ "modules, or the GNU 'attr' package "
+ "(which contains the 'setfattr' tool).")
+ else:
+ raise XAttrUnavailableError(
+ "Couldn't find a tool to set the xattrs. "
+ "Install either the python 'xattr' module, "
+ "or the 'xattr' binary.")
+
+
+def random_birthday(year_field, month_field, day_field):
+ return {
+ year_field: str(random.randint(1950, 1995)),
+ month_field: str(random.randint(1, 12)),
+ day_field: str(random.randint(1, 31)),
+ }
Rapsys Git / youtubedl / blobdiff