|
|
|
|
@ -41,12 +41,13 @@ import traceback
|
|
|
|
|
import xml.etree.ElementTree
|
|
|
|
|
import zlib
|
|
|
|
|
import mimetypes
|
|
|
|
|
import urllib.parse
|
|
|
|
|
import shlex
|
|
|
|
|
|
|
|
|
|
from .compat import (
|
|
|
|
|
compat_HTMLParseError,
|
|
|
|
|
compat_HTMLParser,
|
|
|
|
|
compat_HTTPError,
|
|
|
|
|
compat_basestring,
|
|
|
|
|
compat_brotli,
|
|
|
|
|
compat_chr,
|
|
|
|
|
compat_cookiejar,
|
|
|
|
|
@ -55,28 +56,19 @@ from .compat import (
|
|
|
|
|
compat_html_entities,
|
|
|
|
|
compat_html_entities_html5,
|
|
|
|
|
compat_http_client,
|
|
|
|
|
compat_integer_types,
|
|
|
|
|
compat_numeric_types,
|
|
|
|
|
compat_kwargs,
|
|
|
|
|
compat_os_name,
|
|
|
|
|
compat_parse_qs,
|
|
|
|
|
compat_shlex_split,
|
|
|
|
|
compat_shlex_quote,
|
|
|
|
|
compat_str,
|
|
|
|
|
compat_struct_pack,
|
|
|
|
|
compat_struct_unpack,
|
|
|
|
|
compat_urllib_error,
|
|
|
|
|
compat_urllib_parse,
|
|
|
|
|
compat_urllib_parse_urlencode,
|
|
|
|
|
compat_urllib_parse_urlparse,
|
|
|
|
|
compat_urllib_parse_urlunparse,
|
|
|
|
|
compat_urllib_parse_quote,
|
|
|
|
|
compat_urllib_parse_quote_plus,
|
|
|
|
|
compat_urllib_parse_unquote_plus,
|
|
|
|
|
compat_urllib_request,
|
|
|
|
|
compat_urlparse,
|
|
|
|
|
compat_websockets,
|
|
|
|
|
compat_xpath,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
from .socks import (
|
|
|
|
|
@ -340,7 +332,7 @@ def xpath_with_ns(path, ns_map):
|
|
|
|
|
|
|
|
|
|
def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
|
|
|
|
|
def _find_xpath(xpath):
|
|
|
|
|
return node.find(compat_xpath(xpath))
|
|
|
|
|
return node.find(xpath)
|
|
|
|
|
|
|
|
|
|
if isinstance(xpath, (str, compat_str)):
|
|
|
|
|
n = _find_xpath(xpath)
|
|
|
|
|
@ -1193,7 +1185,7 @@ class XAttrUnavailableError(YoutubeDLError):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
|
|
|
|
|
hc = http_class(*args, **compat_kwargs(kwargs))
|
|
|
|
|
hc = http_class(*args, **kwargs)
|
|
|
|
|
source_address = ydl_handler._params.get('source_address')
|
|
|
|
|
|
|
|
|
|
if source_address is not None:
|
|
|
|
|
@ -2401,7 +2393,7 @@ def str_or_none(v, default=None):
|
|
|
|
|
|
|
|
|
|
def str_to_int(int_str):
|
|
|
|
|
""" A more relaxed version of int_or_none """
|
|
|
|
|
if isinstance(int_str, compat_integer_types):
|
|
|
|
|
if isinstance(int_str, int):
|
|
|
|
|
return int_str
|
|
|
|
|
elif isinstance(int_str, compat_str):
|
|
|
|
|
int_str = re.sub(r'[,\.\+]', '', int_str)
|
|
|
|
|
@ -2442,7 +2434,7 @@ def request_to_url(req):
|
|
|
|
|
def strftime_or_none(timestamp, date_format, default=None):
|
|
|
|
|
datetime_object = None
|
|
|
|
|
try:
|
|
|
|
|
if isinstance(timestamp, compat_numeric_types): # unix timestamp
|
|
|
|
|
if isinstance(timestamp, (int, float)): # unix timestamp
|
|
|
|
|
datetime_object = datetime.datetime.utcfromtimestamp(timestamp)
|
|
|
|
|
elif isinstance(timestamp, compat_str): # assume YYYYMMDD
|
|
|
|
|
datetime_object = datetime.datetime.strptime(timestamp, '%Y%m%d')
|
|
|
|
|
@ -2452,7 +2444,7 @@ def strftime_or_none(timestamp, date_format, default=None):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def parse_duration(s):
|
|
|
|
|
if not isinstance(s, compat_basestring):
|
|
|
|
|
if not isinstance(s, str):
|
|
|
|
|
return None
|
|
|
|
|
s = s.strip()
|
|
|
|
|
if not s:
|
|
|
|
|
@ -2789,7 +2781,7 @@ def lowercase_escape(s):
|
|
|
|
|
|
|
|
|
|
def escape_rfc3986(s):
|
|
|
|
|
"""Escape non-ASCII characters as suggested by RFC 3986"""
|
|
|
|
|
return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
|
|
|
|
|
return urllib.parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def escape_url(url):
|
|
|
|
|
@ -2975,7 +2967,7 @@ TV_PARENTAL_GUIDELINES = {
|
|
|
|
|
def parse_age_limit(s):
|
|
|
|
|
if type(s) == int:
|
|
|
|
|
return s if 0 <= s <= 21 else None
|
|
|
|
|
if not isinstance(s, compat_basestring):
|
|
|
|
|
if not isinstance(s, str):
|
|
|
|
|
return None
|
|
|
|
|
m = re.match(r'^(?P<age>\d{1,2})\+?$', s)
|
|
|
|
|
if m:
|
|
|
|
|
@ -3405,7 +3397,7 @@ def _match_one(filter_part, dct, incomplete):
|
|
|
|
|
comparison_value = comparison_value.replace(r'\%s' % m['quote'], m['quote'])
|
|
|
|
|
actual_value = dct.get(m['key'])
|
|
|
|
|
numeric_comparison = None
|
|
|
|
|
if isinstance(actual_value, compat_numeric_types):
|
|
|
|
|
if isinstance(actual_value, (int, float)):
|
|
|
|
|
# If the original field is a string and matching comparisonvalue is
|
|
|
|
|
# a number we should respect the origin of the original field
|
|
|
|
|
# and process comparison value as a string (see
|
|
|
|
|
@ -4859,9 +4851,9 @@ def iri_to_uri(iri):
|
|
|
|
|
|
|
|
|
|
net_location = ''
|
|
|
|
|
if iri_parts.username:
|
|
|
|
|
net_location += compat_urllib_parse_quote(iri_parts.username, safe=r"!$%&'()*+,~")
|
|
|
|
|
net_location += urllib.parse.quote(iri_parts.username, safe=r"!$%&'()*+,~")
|
|
|
|
|
if iri_parts.password is not None:
|
|
|
|
|
net_location += ':' + compat_urllib_parse_quote(iri_parts.password, safe=r"!$%&'()*+,~")
|
|
|
|
|
net_location += ':' + urllib.parse.quote(iri_parts.password, safe=r"!$%&'()*+,~")
|
|
|
|
|
net_location += '@'
|
|
|
|
|
|
|
|
|
|
net_location += iri_parts.hostname.encode('idna').decode('utf-8') # Punycode for Unicode hostnames.
|
|
|
|
|
@ -4869,19 +4861,19 @@ def iri_to_uri(iri):
|
|
|
|
|
if iri_parts.port is not None and iri_parts.port != 80:
|
|
|
|
|
net_location += ':' + str(iri_parts.port)
|
|
|
|
|
|
|
|
|
|
return compat_urllib_parse_urlunparse(
|
|
|
|
|
return urllib.parse.urlunparse(
|
|
|
|
|
(iri_parts.scheme,
|
|
|
|
|
net_location,
|
|
|
|
|
|
|
|
|
|
compat_urllib_parse_quote_plus(iri_parts.path, safe=r"!$%&'()*+,/:;=@|~"),
|
|
|
|
|
urllib.parse.quote_plus(iri_parts.path, safe=r"!$%&'()*+,/:;=@|~"),
|
|
|
|
|
|
|
|
|
|
# Unsure about the `safe` argument, since this is a legacy way of handling parameters.
|
|
|
|
|
compat_urllib_parse_quote_plus(iri_parts.params, safe=r"!$%&'()*+,/:;=@|~"),
|
|
|
|
|
urllib.parse.quote_plus(iri_parts.params, safe=r"!$%&'()*+,/:;=@|~"),
|
|
|
|
|
|
|
|
|
|
# Not totally sure about the `safe` argument, since the source does not explicitly mention the query URI component.
|
|
|
|
|
compat_urllib_parse_quote_plus(iri_parts.query, safe=r"!$%&'()*+,/:;=?@{|}~"),
|
|
|
|
|
urllib.parse.quote_plus(iri_parts.query, safe=r"!$%&'()*+,/:;=?@{|}~"),
|
|
|
|
|
|
|
|
|
|
compat_urllib_parse_quote_plus(iri_parts.fragment, safe=r"!#$%&'()*+,/:;=?@{|}~")))
|
|
|
|
|
urllib.parse.quote_plus(iri_parts.fragment, safe=r"!#$%&'()*+,/:;=?@{|}~")))
|
|
|
|
|
|
|
|
|
|
# Source for `safe` arguments: https://url.spec.whatwg.org/#percent-encoded-bytes.
|
|
|
|
|
|
|
|
|
|
@ -5233,7 +5225,7 @@ class Config:
|
|
|
|
|
try:
|
|
|
|
|
# FIXME: https://github.com/ytdl-org/youtube-dl/commit/dfe5fa49aed02cf36ba9f743b11b0903554b5e56
|
|
|
|
|
contents = optionf.read()
|
|
|
|
|
res = compat_shlex_split(contents, comments=True)
|
|
|
|
|
res = shlex.split(contents, comments=True)
|
|
|
|
|
finally:
|
|
|
|
|
optionf.close()
|
|
|
|
|
return res
|
|
|
|
|
|
pukkandan
3 years ago