X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bc5059672e222ec4df4fe3983c399c0d0fca84d5..66ad35d33a13d775516bebaebf1f5fe26f97807d:/youtube_dl/utils.py
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index c486ef8..f620469 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1,191 +1,1780 @@
#!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+import binascii
+import calendar
+import codecs
+import contextlib
+import ctypes
import datetime
import email.utils
+import email.header
import errno
+import functools
import gzip
import io
+import itertools
import json
import locale
import math
+import operator
import os
-import pipes
import platform
+import random
import re
-import ssl
import socket
+import ssl
+import subprocess
import sys
+import tempfile
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 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 _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
-
- 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 = _unquote(name, encoding=encoding, errors=errors)
- name = _coerce_result(name)
- value = nv[1].replace('+', ' ')
- value = _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
+from .compat import (
+ compat_HTMLParseError,
+ compat_HTMLParser,
+ compat_basestring,
+ compat_chr,
+ compat_cookiejar,
+ compat_ctypes_WINFUNCTYPE,
+ compat_etree_fromstring,
+ compat_expanduser,
+ compat_html_entities,
+ compat_html_entities_html5,
+ compat_http_client,
+ compat_integer_types,
+ compat_kwargs,
+ compat_os_name,
+ compat_parse_qs,
+ 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_unquote_plus,
+ compat_urllib_request,
+ compat_urlparse,
+ compat_xpath,
+)
+
+from .socks import (
+ ProxyType,
+ sockssocket,
+)
+
+
+def register_socks_protocols():
+ # "Register" SOCKS protocols
+ # In Python < 2.6.5, urlsplit() suffers from bug https://bugs.python.org/issue7904
+ # URLs with protocols not in urlparse.uses_netloc are not handled correctly
+ for scheme in ('socks', 'socks4', 'socks4a', 'socks5'):
+ if scheme not in compat_urlparse.uses_netloc:
+ compat_urlparse.uses_netloc.append(scheme)
-def compat_ord(c):
- if type(c) is int: return c
- else: return ord(c)
# This is not clearly defined otherwise
compiled_regex_type = type(re.compile(''))
+
+def random_user_agent():
+ _USER_AGENT_TPL = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/%s Safari/537.36'
+ _CHROME_VERSIONS = (
+ '74.0.3729.129',
+ '76.0.3780.3',
+ '76.0.3780.2',
+ '74.0.3729.128',
+ '76.0.3780.1',
+ '76.0.3780.0',
+ '75.0.3770.15',
+ '74.0.3729.127',
+ '74.0.3729.126',
+ '76.0.3779.1',
+ '76.0.3779.0',
+ '75.0.3770.14',
+ '74.0.3729.125',
+ '76.0.3778.1',
+ '76.0.3778.0',
+ '75.0.3770.13',
+ '74.0.3729.124',
+ '74.0.3729.123',
+ '73.0.3683.121',
+ '76.0.3777.1',
+ '76.0.3777.0',
+ '75.0.3770.12',
+ '74.0.3729.122',
+ '76.0.3776.4',
+ '75.0.3770.11',
+ '74.0.3729.121',
+ '76.0.3776.3',
+ '76.0.3776.2',
+ '73.0.3683.120',
+ '74.0.3729.120',
+ '74.0.3729.119',
+ '74.0.3729.118',
+ '76.0.3776.1',
+ '76.0.3776.0',
+ '76.0.3775.5',
+ '75.0.3770.10',
+ '74.0.3729.117',
+ '76.0.3775.4',
+ '76.0.3775.3',
+ '74.0.3729.116',
+ '75.0.3770.9',
+ '76.0.3775.2',
+ '76.0.3775.1',
+ '76.0.3775.0',
+ '75.0.3770.8',
+ '74.0.3729.115',
+ '74.0.3729.114',
+ '76.0.3774.1',
+ '76.0.3774.0',
+ '75.0.3770.7',
+ '74.0.3729.113',
+ '74.0.3729.112',
+ '74.0.3729.111',
+ '76.0.3773.1',
+ '76.0.3773.0',
+ '75.0.3770.6',
+ '74.0.3729.110',
+ '74.0.3729.109',
+ '76.0.3772.1',
+ '76.0.3772.0',
+ '75.0.3770.5',
+ '74.0.3729.108',
+ '74.0.3729.107',
+ '76.0.3771.1',
+ '76.0.3771.0',
+ '75.0.3770.4',
+ '74.0.3729.106',
+ '74.0.3729.105',
+ '75.0.3770.3',
+ '74.0.3729.104',
+ '74.0.3729.103',
+ '74.0.3729.102',
+ '75.0.3770.2',
+ '74.0.3729.101',
+ '75.0.3770.1',
+ '75.0.3770.0',
+ '74.0.3729.100',
+ '75.0.3769.5',
+ '75.0.3769.4',
+ '74.0.3729.99',
+ '75.0.3769.3',
+ '75.0.3769.2',
+ '75.0.3768.6',
+ '74.0.3729.98',
+ '75.0.3769.1',
+ '75.0.3769.0',
+ '74.0.3729.97',
+ '73.0.3683.119',
+ '73.0.3683.118',
+ '74.0.3729.96',
+ '75.0.3768.5',
+ '75.0.3768.4',
+ '75.0.3768.3',
+ '75.0.3768.2',
+ '74.0.3729.95',
+ '74.0.3729.94',
+ '75.0.3768.1',
+ '75.0.3768.0',
+ '74.0.3729.93',
+ '74.0.3729.92',
+ '73.0.3683.117',
+ '74.0.3729.91',
+ '75.0.3766.3',
+ '74.0.3729.90',
+ '75.0.3767.2',
+ '75.0.3767.1',
+ '75.0.3767.0',
+ '74.0.3729.89',
+ '73.0.3683.116',
+ '75.0.3766.2',
+ '74.0.3729.88',
+ '75.0.3766.1',
+ '75.0.3766.0',
+ '74.0.3729.87',
+ '73.0.3683.115',
+ '74.0.3729.86',
+ '75.0.3765.1',
+ '75.0.3765.0',
+ '74.0.3729.85',
+ '73.0.3683.114',
+ '74.0.3729.84',
+ '75.0.3764.1',
+ '75.0.3764.0',
+ '74.0.3729.83',
+ '73.0.3683.113',
+ '75.0.3763.2',
+ '75.0.3761.4',
+ '74.0.3729.82',
+ '75.0.3763.1',
+ '75.0.3763.0',
+ '74.0.3729.81',
+ '73.0.3683.112',
+ '75.0.3762.1',
+ '75.0.3762.0',
+ '74.0.3729.80',
+ '75.0.3761.3',
+ '74.0.3729.79',
+ '73.0.3683.111',
+ '75.0.3761.2',
+ '74.0.3729.78',
+ '74.0.3729.77',
+ '75.0.3761.1',
+ '75.0.3761.0',
+ '73.0.3683.110',
+ '74.0.3729.76',
+ '74.0.3729.75',
+ '75.0.3760.0',
+ '74.0.3729.74',
+ '75.0.3759.8',
+ '75.0.3759.7',
+ '75.0.3759.6',
+ '74.0.3729.73',
+ '75.0.3759.5',
+ '74.0.3729.72',
+ '73.0.3683.109',
+ '75.0.3759.4',
+ '75.0.3759.3',
+ '74.0.3729.71',
+ '75.0.3759.2',
+ '74.0.3729.70',
+ '73.0.3683.108',
+ '74.0.3729.69',
+ '75.0.3759.1',
+ '75.0.3759.0',
+ '74.0.3729.68',
+ '73.0.3683.107',
+ '74.0.3729.67',
+ '75.0.3758.1',
+ '75.0.3758.0',
+ '74.0.3729.66',
+ '73.0.3683.106',
+ '74.0.3729.65',
+ '75.0.3757.1',
+ '75.0.3757.0',
+ '74.0.3729.64',
+ '73.0.3683.105',
+ '74.0.3729.63',
+ '75.0.3756.1',
+ '75.0.3756.0',
+ '74.0.3729.62',
+ '73.0.3683.104',
+ '75.0.3755.3',
+ '75.0.3755.2',
+ '73.0.3683.103',
+ '75.0.3755.1',
+ '75.0.3755.0',
+ '74.0.3729.61',
+ '73.0.3683.102',
+ '74.0.3729.60',
+ '75.0.3754.2',
+ '74.0.3729.59',
+ '75.0.3753.4',
+ '74.0.3729.58',
+ '75.0.3754.1',
+ '75.0.3754.0',
+ '74.0.3729.57',
+ '73.0.3683.101',
+ '75.0.3753.3',
+ '75.0.3752.2',
+ '75.0.3753.2',
+ '74.0.3729.56',
+ '75.0.3753.1',
+ '75.0.3753.0',
+ '74.0.3729.55',
+ '73.0.3683.100',
+ '74.0.3729.54',
+ '75.0.3752.1',
+ '75.0.3752.0',
+ '74.0.3729.53',
+ '73.0.3683.99',
+ '74.0.3729.52',
+ '75.0.3751.1',
+ '75.0.3751.0',
+ '74.0.3729.51',
+ '73.0.3683.98',
+ '74.0.3729.50',
+ '75.0.3750.0',
+ '74.0.3729.49',
+ '74.0.3729.48',
+ '74.0.3729.47',
+ '75.0.3749.3',
+ '74.0.3729.46',
+ '73.0.3683.97',
+ '75.0.3749.2',
+ '74.0.3729.45',
+ '75.0.3749.1',
+ '75.0.3749.0',
+ '74.0.3729.44',
+ '73.0.3683.96',
+ '74.0.3729.43',
+ '74.0.3729.42',
+ '75.0.3748.1',
+ '75.0.3748.0',
+ '74.0.3729.41',
+ '75.0.3747.1',
+ '73.0.3683.95',
+ '75.0.3746.4',
+ '74.0.3729.40',
+ '74.0.3729.39',
+ '75.0.3747.0',
+ '75.0.3746.3',
+ '75.0.3746.2',
+ '74.0.3729.38',
+ '75.0.3746.1',
+ '75.0.3746.0',
+ '74.0.3729.37',
+ '73.0.3683.94',
+ '75.0.3745.5',
+ '75.0.3745.4',
+ '75.0.3745.3',
+ '75.0.3745.2',
+ '74.0.3729.36',
+ '75.0.3745.1',
+ '75.0.3745.0',
+ '75.0.3744.2',
+ '74.0.3729.35',
+ '73.0.3683.93',
+ '74.0.3729.34',
+ '75.0.3744.1',
+ '75.0.3744.0',
+ '74.0.3729.33',
+ '73.0.3683.92',
+ '74.0.3729.32',
+ '74.0.3729.31',
+ '73.0.3683.91',
+ '75.0.3741.2',
+ '75.0.3740.5',
+ '74.0.3729.30',
+ '75.0.3741.1',
+ '75.0.3741.0',
+ '74.0.3729.29',
+ '75.0.3740.4',
+ '73.0.3683.90',
+ '74.0.3729.28',
+ '75.0.3740.3',
+ '73.0.3683.89',
+ '75.0.3740.2',
+ '74.0.3729.27',
+ '75.0.3740.1',
+ '75.0.3740.0',
+ '74.0.3729.26',
+ '73.0.3683.88',
+ '73.0.3683.87',
+ '74.0.3729.25',
+ '75.0.3739.1',
+ '75.0.3739.0',
+ '73.0.3683.86',
+ '74.0.3729.24',
+ '73.0.3683.85',
+ '75.0.3738.4',
+ '75.0.3738.3',
+ '75.0.3738.2',
+ '75.0.3738.1',
+ '75.0.3738.0',
+ '74.0.3729.23',
+ '73.0.3683.84',
+ '74.0.3729.22',
+ '74.0.3729.21',
+ '75.0.3737.1',
+ '75.0.3737.0',
+ '74.0.3729.20',
+ '73.0.3683.83',
+ '74.0.3729.19',
+ '75.0.3736.1',
+ '75.0.3736.0',
+ '74.0.3729.18',
+ '73.0.3683.82',
+ '74.0.3729.17',
+ '75.0.3735.1',
+ '75.0.3735.0',
+ '74.0.3729.16',
+ '73.0.3683.81',
+ '75.0.3734.1',
+ '75.0.3734.0',
+ '74.0.3729.15',
+ '73.0.3683.80',
+ '74.0.3729.14',
+ '75.0.3733.1',
+ '75.0.3733.0',
+ '75.0.3732.1',
+ '74.0.3729.13',
+ '74.0.3729.12',
+ '73.0.3683.79',
+ '74.0.3729.11',
+ '75.0.3732.0',
+ '74.0.3729.10',
+ '73.0.3683.78',
+ '74.0.3729.9',
+ '74.0.3729.8',
+ '74.0.3729.7',
+ '75.0.3731.3',
+ '75.0.3731.2',
+ '75.0.3731.0',
+ '74.0.3729.6',
+ '73.0.3683.77',
+ '73.0.3683.76',
+ '75.0.3730.5',
+ '75.0.3730.4',
+ '73.0.3683.75',
+ '74.0.3729.5',
+ '73.0.3683.74',
+ '75.0.3730.3',
+ '75.0.3730.2',
+ '74.0.3729.4',
+ '73.0.3683.73',
+ '73.0.3683.72',
+ '75.0.3730.1',
+ '75.0.3730.0',
+ '74.0.3729.3',
+ '73.0.3683.71',
+ '74.0.3729.2',
+ '73.0.3683.70',
+ '74.0.3729.1',
+ '74.0.3729.0',
+ '74.0.3726.4',
+ '73.0.3683.69',
+ '74.0.3726.3',
+ '74.0.3728.0',
+ '74.0.3726.2',
+ '73.0.3683.68',
+ '74.0.3726.1',
+ '74.0.3726.0',
+ '74.0.3725.4',
+ '73.0.3683.67',
+ '73.0.3683.66',
+ '74.0.3725.3',
+ '74.0.3725.2',
+ '74.0.3725.1',
+ '74.0.3724.8',
+ '74.0.3725.0',
+ '73.0.3683.65',
+ '74.0.3724.7',
+ '74.0.3724.6',
+ '74.0.3724.5',
+ '74.0.3724.4',
+ '74.0.3724.3',
+ '74.0.3724.2',
+ '74.0.3724.1',
+ '74.0.3724.0',
+ '73.0.3683.64',
+ '74.0.3723.1',
+ '74.0.3723.0',
+ '73.0.3683.63',
+ '74.0.3722.1',
+ '74.0.3722.0',
+ '73.0.3683.62',
+ '74.0.3718.9',
+ '74.0.3702.3',
+ '74.0.3721.3',
+ '74.0.3721.2',
+ '74.0.3721.1',
+ '74.0.3721.0',
+ '74.0.3720.6',
+ '73.0.3683.61',
+ '72.0.3626.122',
+ '73.0.3683.60',
+ '74.0.3720.5',
+ '72.0.3626.121',
+ '74.0.3718.8',
+ '74.0.3720.4',
+ '74.0.3720.3',
+ '74.0.3718.7',
+ '74.0.3720.2',
+ '74.0.3720.1',
+ '74.0.3720.0',
+ '74.0.3718.6',
+ '74.0.3719.5',
+ '73.0.3683.59',
+ '74.0.3718.5',
+ '74.0.3718.4',
+ '74.0.3719.4',
+ '74.0.3719.3',
+ '74.0.3719.2',
+ '74.0.3719.1',
+ '73.0.3683.58',
+ '74.0.3719.0',
+ '73.0.3683.57',
+ '73.0.3683.56',
+ '74.0.3718.3',
+ '73.0.3683.55',
+ '74.0.3718.2',
+ '74.0.3718.1',
+ '74.0.3718.0',
+ '73.0.3683.54',
+ '74.0.3717.2',
+ '73.0.3683.53',
+ '74.0.3717.1',
+ '74.0.3717.0',
+ '73.0.3683.52',
+ '74.0.3716.1',
+ '74.0.3716.0',
+ '73.0.3683.51',
+ '74.0.3715.1',
+ '74.0.3715.0',
+ '73.0.3683.50',
+ '74.0.3711.2',
+ '74.0.3714.2',
+ '74.0.3713.3',
+ '74.0.3714.1',
+ '74.0.3714.0',
+ '73.0.3683.49',
+ '74.0.3713.1',
+ '74.0.3713.0',
+ '72.0.3626.120',
+ '73.0.3683.48',
+ '74.0.3712.2',
+ '74.0.3712.1',
+ '74.0.3712.0',
+ '73.0.3683.47',
+ '72.0.3626.119',
+ '73.0.3683.46',
+ '74.0.3710.2',
+ '72.0.3626.118',
+ '74.0.3711.1',
+ '74.0.3711.0',
+ '73.0.3683.45',
+ '72.0.3626.117',
+ '74.0.3710.1',
+ '74.0.3710.0',
+ '73.0.3683.44',
+ '72.0.3626.116',
+ '74.0.3709.1',
+ '74.0.3709.0',
+ '74.0.3704.9',
+ '73.0.3683.43',
+ '72.0.3626.115',
+ '74.0.3704.8',
+ '74.0.3704.7',
+ '74.0.3708.0',
+ '74.0.3706.7',
+ '74.0.3704.6',
+ '73.0.3683.42',
+ '72.0.3626.114',
+ '74.0.3706.6',
+ '72.0.3626.113',
+ '74.0.3704.5',
+ '74.0.3706.5',
+ '74.0.3706.4',
+ '74.0.3706.3',
+ '74.0.3706.2',
+ '74.0.3706.1',
+ '74.0.3706.0',
+ '73.0.3683.41',
+ '72.0.3626.112',
+ '74.0.3705.1',
+ '74.0.3705.0',
+ '73.0.3683.40',
+ '72.0.3626.111',
+ '73.0.3683.39',
+ '74.0.3704.4',
+ '73.0.3683.38',
+ '74.0.3704.3',
+ '74.0.3704.2',
+ '74.0.3704.1',
+ '74.0.3704.0',
+ '73.0.3683.37',
+ '72.0.3626.110',
+ '72.0.3626.109',
+ '74.0.3703.3',
+ '74.0.3703.2',
+ '73.0.3683.36',
+ '74.0.3703.1',
+ '74.0.3703.0',
+ '73.0.3683.35',
+ '72.0.3626.108',
+ '74.0.3702.2',
+ '74.0.3699.3',
+ '74.0.3702.1',
+ '74.0.3702.0',
+ '73.0.3683.34',
+ '72.0.3626.107',
+ '73.0.3683.33',
+ '74.0.3701.1',
+ '74.0.3701.0',
+ '73.0.3683.32',
+ '73.0.3683.31',
+ '72.0.3626.105',
+ '74.0.3700.1',
+ '74.0.3700.0',
+ '73.0.3683.29',
+ '72.0.3626.103',
+ '74.0.3699.2',
+ '74.0.3699.1',
+ '74.0.3699.0',
+ '73.0.3683.28',
+ '72.0.3626.102',
+ '73.0.3683.27',
+ '73.0.3683.26',
+ '74.0.3698.0',
+ '74.0.3696.2',
+ '72.0.3626.101',
+ '73.0.3683.25',
+ '74.0.3696.1',
+ '74.0.3696.0',
+ '74.0.3694.8',
+ '72.0.3626.100',
+ '74.0.3694.7',
+ '74.0.3694.6',
+ '74.0.3694.5',
+ '74.0.3694.4',
+ '72.0.3626.99',
+ '72.0.3626.98',
+ '74.0.3694.3',
+ '73.0.3683.24',
+ '72.0.3626.97',
+ '72.0.3626.96',
+ '72.0.3626.95',
+ '73.0.3683.23',
+ '72.0.3626.94',
+ '73.0.3683.22',
+ '73.0.3683.21',
+ '72.0.3626.93',
+ '74.0.3694.2',
+ '72.0.3626.92',
+ '74.0.3694.1',
+ '74.0.3694.0',
+ '74.0.3693.6',
+ '73.0.3683.20',
+ '72.0.3626.91',
+ '74.0.3693.5',
+ '74.0.3693.4',
+ '74.0.3693.3',
+ '74.0.3693.2',
+ '73.0.3683.19',
+ '74.0.3693.1',
+ '74.0.3693.0',
+ '73.0.3683.18',
+ '72.0.3626.90',
+ '74.0.3692.1',
+ '74.0.3692.0',
+ '73.0.3683.17',
+ '72.0.3626.89',
+ '74.0.3687.3',
+ '74.0.3691.1',
+ '74.0.3691.0',
+ '73.0.3683.16',
+ '72.0.3626.88',
+ '72.0.3626.87',
+ '73.0.3683.15',
+ '74.0.3690.1',
+ '74.0.3690.0',
+ '73.0.3683.14',
+ '72.0.3626.86',
+ '73.0.3683.13',
+ '73.0.3683.12',
+ '74.0.3689.1',
+ '74.0.3689.0',
+ '73.0.3683.11',
+ '72.0.3626.85',
+ '73.0.3683.10',
+ '72.0.3626.84',
+ '73.0.3683.9',
+ '74.0.3688.1',
+ '74.0.3688.0',
+ '73.0.3683.8',
+ '72.0.3626.83',
+ '74.0.3687.2',
+ '74.0.3687.1',
+ '74.0.3687.0',
+ '73.0.3683.7',
+ '72.0.3626.82',
+ '74.0.3686.4',
+ '72.0.3626.81',
+ '74.0.3686.3',
+ '74.0.3686.2',
+ '74.0.3686.1',
+ '74.0.3686.0',
+ '73.0.3683.6',
+ '72.0.3626.80',
+ '74.0.3685.1',
+ '74.0.3685.0',
+ '73.0.3683.5',
+ '72.0.3626.79',
+ '74.0.3684.1',
+ '74.0.3684.0',
+ '73.0.3683.4',
+ '72.0.3626.78',
+ '72.0.3626.77',
+ '73.0.3683.3',
+ '73.0.3683.2',
+ '72.0.3626.76',
+ '73.0.3683.1',
+ '73.0.3683.0',
+ '72.0.3626.75',
+ '71.0.3578.141',
+ '73.0.3682.1',
+ '73.0.3682.0',
+ '72.0.3626.74',
+ '71.0.3578.140',
+ '73.0.3681.4',
+ '73.0.3681.3',
+ '73.0.3681.2',
+ '73.0.3681.1',
+ '73.0.3681.0',
+ '72.0.3626.73',
+ '71.0.3578.139',
+ '72.0.3626.72',
+ '72.0.3626.71',
+ '73.0.3680.1',
+ '73.0.3680.0',
+ '72.0.3626.70',
+ '71.0.3578.138',
+ '73.0.3678.2',
+ '73.0.3679.1',
+ '73.0.3679.0',
+ '72.0.3626.69',
+ '71.0.3578.137',
+ '73.0.3678.1',
+ '73.0.3678.0',
+ '71.0.3578.136',
+ '73.0.3677.1',
+ '73.0.3677.0',
+ '72.0.3626.68',
+ '72.0.3626.67',
+ '71.0.3578.135',
+ '73.0.3676.1',
+ '73.0.3676.0',
+ '73.0.3674.2',
+ '72.0.3626.66',
+ '71.0.3578.134',
+ '73.0.3674.1',
+ '73.0.3674.0',
+ '72.0.3626.65',
+ '71.0.3578.133',
+ '73.0.3673.2',
+ '73.0.3673.1',
+ '73.0.3673.0',
+ '72.0.3626.64',
+ '71.0.3578.132',
+ '72.0.3626.63',
+ '72.0.3626.62',
+ '72.0.3626.61',
+ '72.0.3626.60',
+ '73.0.3672.1',
+ '73.0.3672.0',
+ '72.0.3626.59',
+ '71.0.3578.131',
+ '73.0.3671.3',
+ '73.0.3671.2',
+ '73.0.3671.1',
+ '73.0.3671.0',
+ '72.0.3626.58',
+ '71.0.3578.130',
+ '73.0.3670.1',
+ '73.0.3670.0',
+ '72.0.3626.57',
+ '71.0.3578.129',
+ '73.0.3669.1',
+ '73.0.3669.0',
+ '72.0.3626.56',
+ '71.0.3578.128',
+ '73.0.3668.2',
+ '73.0.3668.1',
+ '73.0.3668.0',
+ '72.0.3626.55',
+ '71.0.3578.127',
+ '73.0.3667.2',
+ '73.0.3667.1',
+ '73.0.3667.0',
+ '72.0.3626.54',
+ '71.0.3578.126',
+ '73.0.3666.1',
+ '73.0.3666.0',
+ '72.0.3626.53',
+ '71.0.3578.125',
+ '73.0.3665.4',
+ '73.0.3665.3',
+ '72.0.3626.52',
+ '73.0.3665.2',
+ '73.0.3664.4',
+ '73.0.3665.1',
+ '73.0.3665.0',
+ '72.0.3626.51',
+ '71.0.3578.124',
+ '72.0.3626.50',
+ '73.0.3664.3',
+ '73.0.3664.2',
+ '73.0.3664.1',
+ '73.0.3664.0',
+ '73.0.3663.2',
+ '72.0.3626.49',
+ '71.0.3578.123',
+ '73.0.3663.1',
+ '73.0.3663.0',
+ '72.0.3626.48',
+ '71.0.3578.122',
+ '73.0.3662.1',
+ '73.0.3662.0',
+ '72.0.3626.47',
+ '71.0.3578.121',
+ '73.0.3661.1',
+ '72.0.3626.46',
+ '73.0.3661.0',
+ '72.0.3626.45',
+ '71.0.3578.120',
+ '73.0.3660.2',
+ '73.0.3660.1',
+ '73.0.3660.0',
+ '72.0.3626.44',
+ '71.0.3578.119',
+ '73.0.3659.1',
+ '73.0.3659.0',
+ '72.0.3626.43',
+ '71.0.3578.118',
+ '73.0.3658.1',
+ '73.0.3658.0',
+ '72.0.3626.42',
+ '71.0.3578.117',
+ '73.0.3657.1',
+ '73.0.3657.0',
+ '72.0.3626.41',
+ '71.0.3578.116',
+ '73.0.3656.1',
+ '73.0.3656.0',
+ '72.0.3626.40',
+ '71.0.3578.115',
+ '73.0.3655.1',
+ '73.0.3655.0',
+ '72.0.3626.39',
+ '71.0.3578.114',
+ '73.0.3654.1',
+ '73.0.3654.0',
+ '72.0.3626.38',
+ '71.0.3578.113',
+ '73.0.3653.1',
+ '73.0.3653.0',
+ '72.0.3626.37',
+ '71.0.3578.112',
+ '73.0.3652.1',
+ '73.0.3652.0',
+ '72.0.3626.36',
+ '71.0.3578.111',
+ '73.0.3651.1',
+ '73.0.3651.0',
+ '72.0.3626.35',
+ '71.0.3578.110',
+ '73.0.3650.1',
+ '73.0.3650.0',
+ '72.0.3626.34',
+ '71.0.3578.109',
+ '73.0.3649.1',
+ '73.0.3649.0',
+ '72.0.3626.33',
+ '71.0.3578.108',
+ '73.0.3648.2',
+ '73.0.3648.1',
+ '73.0.3648.0',
+ '72.0.3626.32',
+ '71.0.3578.107',
+ '73.0.3647.2',
+ '73.0.3647.1',
+ '73.0.3647.0',
+ '72.0.3626.31',
+ '71.0.3578.106',
+ '73.0.3635.3',
+ '73.0.3646.2',
+ '73.0.3646.1',
+ '73.0.3646.0',
+ '72.0.3626.30',
+ '71.0.3578.105',
+ '72.0.3626.29',
+ '73.0.3645.2',
+ '73.0.3645.1',
+ '73.0.3645.0',
+ '72.0.3626.28',
+ '71.0.3578.104',
+ '72.0.3626.27',
+ '72.0.3626.26',
+ '72.0.3626.25',
+ '72.0.3626.24',
+ '73.0.3644.0',
+ '73.0.3643.2',
+ '72.0.3626.23',
+ '71.0.3578.103',
+ '73.0.3643.1',
+ '73.0.3643.0',
+ '72.0.3626.22',
+ '71.0.3578.102',
+ '73.0.3642.1',
+ '73.0.3642.0',
+ '72.0.3626.21',
+ '71.0.3578.101',
+ '73.0.3641.1',
+ '73.0.3641.0',
+ '72.0.3626.20',
+ '71.0.3578.100',
+ '72.0.3626.19',
+ '73.0.3640.1',
+ '73.0.3640.0',
+ '72.0.3626.18',
+ '73.0.3639.1',
+ '71.0.3578.99',
+ '73.0.3639.0',
+ '72.0.3626.17',
+ '73.0.3638.2',
+ '72.0.3626.16',
+ '73.0.3638.1',
+ '73.0.3638.0',
+ '72.0.3626.15',
+ '71.0.3578.98',
+ '73.0.3635.2',
+ '71.0.3578.97',
+ '73.0.3637.1',
+ '73.0.3637.0',
+ '72.0.3626.14',
+ '71.0.3578.96',
+ '71.0.3578.95',
+ '72.0.3626.13',
+ '71.0.3578.94',
+ '73.0.3636.2',
+ '71.0.3578.93',
+ '73.0.3636.1',
+ '73.0.3636.0',
+ '72.0.3626.12',
+ '71.0.3578.92',
+ '73.0.3635.1',
+ '73.0.3635.0',
+ '72.0.3626.11',
+ '71.0.3578.91',
+ '73.0.3634.2',
+ '73.0.3634.1',
+ '73.0.3634.0',
+ '72.0.3626.10',
+ '71.0.3578.90',
+ '71.0.3578.89',
+ '73.0.3633.2',
+ '73.0.3633.1',
+ '73.0.3633.0',
+ '72.0.3610.4',
+ '72.0.3626.9',
+ '71.0.3578.88',
+ '73.0.3632.5',
+ '73.0.3632.4',
+ '73.0.3632.3',
+ '73.0.3632.2',
+ '73.0.3632.1',
+ '73.0.3632.0',
+ '72.0.3626.8',
+ '71.0.3578.87',
+ '73.0.3631.2',
+ '73.0.3631.1',
+ '73.0.3631.0',
+ '72.0.3626.7',
+ '71.0.3578.86',
+ '72.0.3626.6',
+ '73.0.3630.1',
+ '73.0.3630.0',
+ '72.0.3626.5',
+ '71.0.3578.85',
+ '72.0.3626.4',
+ '73.0.3628.3',
+ '73.0.3628.2',
+ '73.0.3629.1',
+ '73.0.3629.0',
+ '72.0.3626.3',
+ '71.0.3578.84',
+ '73.0.3628.1',
+ '73.0.3628.0',
+ '71.0.3578.83',
+ '73.0.3627.1',
+ '73.0.3627.0',
+ '72.0.3626.2',
+ '71.0.3578.82',
+ '71.0.3578.81',
+ '71.0.3578.80',
+ '72.0.3626.1',
+ '72.0.3626.0',
+ '71.0.3578.79',
+ '70.0.3538.124',
+ '71.0.3578.78',
+ '72.0.3623.4',
+ '72.0.3625.2',
+ '72.0.3625.1',
+ '72.0.3625.0',
+ '71.0.3578.77',
+ '70.0.3538.123',
+ '72.0.3624.4',
+ '72.0.3624.3',
+ '72.0.3624.2',
+ '71.0.3578.76',
+ '72.0.3624.1',
+ '72.0.3624.0',
+ '72.0.3623.3',
+ '71.0.3578.75',
+ '70.0.3538.122',
+ '71.0.3578.74',
+ '72.0.3623.2',
+ '72.0.3610.3',
+ '72.0.3623.1',
+ '72.0.3623.0',
+ '72.0.3622.3',
+ '72.0.3622.2',
+ '71.0.3578.73',
+ '70.0.3538.121',
+ '72.0.3622.1',
+ '72.0.3622.0',
+ '71.0.3578.72',
+ '70.0.3538.120',
+ '72.0.3621.1',
+ '72.0.3621.0',
+ '71.0.3578.71',
+ '70.0.3538.119',
+ '72.0.3620.1',
+ '72.0.3620.0',
+ '71.0.3578.70',
+ '70.0.3538.118',
+ '71.0.3578.69',
+ '72.0.3619.1',
+ '72.0.3619.0',
+ '71.0.3578.68',
+ '70.0.3538.117',
+ '71.0.3578.67',
+ '72.0.3618.1',
+ '72.0.3618.0',
+ '71.0.3578.66',
+ '70.0.3538.116',
+ '72.0.3617.1',
+ '72.0.3617.0',
+ '71.0.3578.65',
+ '70.0.3538.115',
+ '72.0.3602.3',
+ '71.0.3578.64',
+ '72.0.3616.1',
+ '72.0.3616.0',
+ '71.0.3578.63',
+ '70.0.3538.114',
+ '71.0.3578.62',
+ '72.0.3615.1',
+ '72.0.3615.0',
+ '71.0.3578.61',
+ '70.0.3538.113',
+ '72.0.3614.1',
+ '72.0.3614.0',
+ '71.0.3578.60',
+ '70.0.3538.112',
+ '72.0.3613.1',
+ '72.0.3613.0',
+ '71.0.3578.59',
+ '70.0.3538.111',
+ '72.0.3612.2',
+ '72.0.3612.1',
+ '72.0.3612.0',
+ '70.0.3538.110',
+ '71.0.3578.58',
+ '70.0.3538.109',
+ '72.0.3611.2',
+ '72.0.3611.1',
+ '72.0.3611.0',
+ '71.0.3578.57',
+ '70.0.3538.108',
+ '72.0.3610.2',
+ '71.0.3578.56',
+ '71.0.3578.55',
+ '72.0.3610.1',
+ '72.0.3610.0',
+ '71.0.3578.54',
+ '70.0.3538.107',
+ '71.0.3578.53',
+ '72.0.3609.3',
+ '71.0.3578.52',
+ '72.0.3609.2',
+ '71.0.3578.51',
+ '72.0.3608.5',
+ '72.0.3609.1',
+ '72.0.3609.0',
+ '71.0.3578.50',
+ '70.0.3538.106',
+ '72.0.3608.4',
+ '72.0.3608.3',
+ '72.0.3608.2',
+ '71.0.3578.49',
+ '72.0.3608.1',
+ '72.0.3608.0',
+ '70.0.3538.105',
+ '71.0.3578.48',
+ '72.0.3607.1',
+ '72.0.3607.0',
+ '71.0.3578.47',
+ '70.0.3538.104',
+ '72.0.3606.2',
+ '72.0.3606.1',
+ '72.0.3606.0',
+ '71.0.3578.46',
+ '70.0.3538.103',
+ '70.0.3538.102',
+ '72.0.3605.3',
+ '72.0.3605.2',
+ '72.0.3605.1',
+ '72.0.3605.0',
+ '71.0.3578.45',
+ '70.0.3538.101',
+ '71.0.3578.44',
+ '71.0.3578.43',
+ '70.0.3538.100',
+ '70.0.3538.99',
+ '71.0.3578.42',
+ '72.0.3604.1',
+ '72.0.3604.0',
+ '71.0.3578.41',
+ '70.0.3538.98',
+ '71.0.3578.40',
+ '72.0.3603.2',
+ '72.0.3603.1',
+ '72.0.3603.0',
+ '71.0.3578.39',
+ '70.0.3538.97',
+ '72.0.3602.2',
+ '71.0.3578.38',
+ '71.0.3578.37',
+ '72.0.3602.1',
+ '72.0.3602.0',
+ '71.0.3578.36',
+ '70.0.3538.96',
+ '72.0.3601.1',
+ '72.0.3601.0',
+ '71.0.3578.35',
+ '70.0.3538.95',
+ '72.0.3600.1',
+ '72.0.3600.0',
+ '71.0.3578.34',
+ '70.0.3538.94',
+ '72.0.3599.3',
+ '72.0.3599.2',
+ '72.0.3599.1',
+ '72.0.3599.0',
+ '71.0.3578.33',
+ '70.0.3538.93',
+ '72.0.3598.1',
+ '72.0.3598.0',
+ '71.0.3578.32',
+ '70.0.3538.87',
+ '72.0.3597.1',
+ '72.0.3597.0',
+ '72.0.3596.2',
+ '71.0.3578.31',
+ '70.0.3538.86',
+ '71.0.3578.30',
+ '71.0.3578.29',
+ '72.0.3596.1',
+ '72.0.3596.0',
+ '71.0.3578.28',
+ '70.0.3538.85',
+ '72.0.3595.2',
+ '72.0.3591.3',
+ '72.0.3595.1',
+ '72.0.3595.0',
+ '71.0.3578.27',
+ '70.0.3538.84',
+ '72.0.3594.1',
+ '72.0.3594.0',
+ '71.0.3578.26',
+ '70.0.3538.83',
+ '72.0.3593.2',
+ '72.0.3593.1',
+ '72.0.3593.0',
+ '71.0.3578.25',
+ '70.0.3538.82',
+ '72.0.3589.3',
+ '72.0.3592.2',
+ '72.0.3592.1',
+ '72.0.3592.0',
+ '71.0.3578.24',
+ '72.0.3589.2',
+ '70.0.3538.81',
+ '70.0.3538.80',
+ '72.0.3591.2',
+ '72.0.3591.1',
+ '72.0.3591.0',
+ '71.0.3578.23',
+ '70.0.3538.79',
+ '71.0.3578.22',
+ '72.0.3590.1',
+ '72.0.3590.0',
+ '71.0.3578.21',
+ '70.0.3538.78',
+ '70.0.3538.77',
+ '72.0.3589.1',
+ '72.0.3589.0',
+ '71.0.3578.20',
+ '70.0.3538.76',
+ '71.0.3578.19',
+ '70.0.3538.75',
+ '72.0.3588.1',
+ '72.0.3588.0',
+ '71.0.3578.18',
+ '70.0.3538.74',
+ '72.0.3586.2',
+ '72.0.3587.0',
+ '71.0.3578.17',
+ '70.0.3538.73',
+ '72.0.3586.1',
+ '72.0.3586.0',
+ '71.0.3578.16',
+ '70.0.3538.72',
+ '72.0.3585.1',
+ '72.0.3585.0',
+ '71.0.3578.15',
+ '70.0.3538.71',
+ '71.0.3578.14',
+ '72.0.3584.1',
+ '72.0.3584.0',
+ '71.0.3578.13',
+ '70.0.3538.70',
+ '72.0.3583.2',
+ '71.0.3578.12',
+ '72.0.3583.1',
+ '72.0.3583.0',
+ '71.0.3578.11',
+ '70.0.3538.69',
+ '71.0.3578.10',
+ '72.0.3582.0',
+ '72.0.3581.4',
+ '71.0.3578.9',
+ '70.0.3538.67',
+ '72.0.3581.3',
+ '72.0.3581.2',
+ '72.0.3581.1',
+ '72.0.3581.0',
+ '71.0.3578.8',
+ '70.0.3538.66',
+ '72.0.3580.1',
+ '72.0.3580.0',
+ '71.0.3578.7',
+ '70.0.3538.65',
+ '71.0.3578.6',
+ '72.0.3579.1',
+ '72.0.3579.0',
+ '71.0.3578.5',
+ '70.0.3538.64',
+ '71.0.3578.4',
+ '71.0.3578.3',
+ '71.0.3578.2',
+ '71.0.3578.1',
+ '71.0.3578.0',
+ '70.0.3538.63',
+ '69.0.3497.128',
+ '70.0.3538.62',
+ '70.0.3538.61',
+ '70.0.3538.60',
+ '70.0.3538.59',
+ '71.0.3577.1',
+ '71.0.3577.0',
+ '70.0.3538.58',
+ '69.0.3497.127',
+ '71.0.3576.2',
+ '71.0.3576.1',
+ '71.0.3576.0',
+ '70.0.3538.57',
+ '70.0.3538.56',
+ '71.0.3575.2',
+ '70.0.3538.55',
+ '69.0.3497.126',
+ '70.0.3538.54',
+ '71.0.3575.1',
+ '71.0.3575.0',
+ '71.0.3574.1',
+ '71.0.3574.0',
+ '70.0.3538.53',
+ '69.0.3497.125',
+ '70.0.3538.52',
+ '71.0.3573.1',
+ '71.0.3573.0',
+ '70.0.3538.51',
+ '69.0.3497.124',
+ '71.0.3572.1',
+ '71.0.3572.0',
+ '70.0.3538.50',
+ '69.0.3497.123',
+ '71.0.3571.2',
+ '70.0.3538.49',
+ '69.0.3497.122',
+ '71.0.3571.1',
+ '71.0.3571.0',
+ '70.0.3538.48',
+ '69.0.3497.121',
+ '71.0.3570.1',
+ '71.0.3570.0',
+ '70.0.3538.47',
+ '69.0.3497.120',
+ '71.0.3568.2',
+ '71.0.3569.1',
+ '71.0.3569.0',
+ '70.0.3538.46',
+ '69.0.3497.119',
+ '70.0.3538.45',
+ '71.0.3568.1',
+ '71.0.3568.0',
+ '70.0.3538.44',
+ '69.0.3497.118',
+ '70.0.3538.43',
+ '70.0.3538.42',
+ '71.0.3567.1',
+ '71.0.3567.0',
+ '70.0.3538.41',
+ '69.0.3497.117',
+ '71.0.3566.1',
+ '71.0.3566.0',
+ '70.0.3538.40',
+ '69.0.3497.116',
+ '71.0.3565.1',
+ '71.0.3565.0',
+ '70.0.3538.39',
+ '69.0.3497.115',
+ '71.0.3564.1',
+ '71.0.3564.0',
+ '70.0.3538.38',
+ '69.0.3497.114',
+ '71.0.3563.0',
+ '71.0.3562.2',
+ '70.0.3538.37',
+ '69.0.3497.113',
+ '70.0.3538.36',
+ '70.0.3538.35',
+ '71.0.3562.1',
+ '71.0.3562.0',
+ '70.0.3538.34',
+ '69.0.3497.112',
+ '70.0.3538.33',
+ '71.0.3561.1',
+ '71.0.3561.0',
+ '70.0.3538.32',
+ '69.0.3497.111',
+ '71.0.3559.6',
+ '71.0.3560.1',
+ '71.0.3560.0',
+ '71.0.3559.5',
+ '71.0.3559.4',
+ '70.0.3538.31',
+ '69.0.3497.110',
+ '71.0.3559.3',
+ '70.0.3538.30',
+ '69.0.3497.109',
+ '71.0.3559.2',
+ '71.0.3559.1',
+ '71.0.3559.0',
+ '70.0.3538.29',
+ '69.0.3497.108',
+ '71.0.3558.2',
+ '71.0.3558.1',
+ '71.0.3558.0',
+ '70.0.3538.28',
+ '69.0.3497.107',
+ '71.0.3557.2',
+ '71.0.3557.1',
+ '71.0.3557.0',
+ '70.0.3538.27',
+ '69.0.3497.106',
+ '71.0.3554.4',
+ '70.0.3538.26',
+ '71.0.3556.1',
+ '71.0.3556.0',
+ '70.0.3538.25',
+ '71.0.3554.3',
+ '69.0.3497.105',
+ '71.0.3554.2',
+ '70.0.3538.24',
+ '69.0.3497.104',
+ '71.0.3555.2',
+ '70.0.3538.23',
+ '71.0.3555.1',
+ '71.0.3555.0',
+ '70.0.3538.22',
+ '69.0.3497.103',
+ '71.0.3554.1',
+ '71.0.3554.0',
+ '70.0.3538.21',
+ '69.0.3497.102',
+ '71.0.3553.3',
+ '70.0.3538.20',
+ '69.0.3497.101',
+ '71.0.3553.2',
+ '69.0.3497.100',
+ '71.0.3553.1',
+ '71.0.3553.0',
+ '70.0.3538.19',
+ '69.0.3497.99',
+ '69.0.3497.98',
+ '69.0.3497.97',
+ '71.0.3552.6',
+ '71.0.3552.5',
+ '71.0.3552.4',
+ '71.0.3552.3',
+ '71.0.3552.2',
+ '71.0.3552.1',
+ '71.0.3552.0',
+ '70.0.3538.18',
+ '69.0.3497.96',
+ '71.0.3551.3',
+ '71.0.3551.2',
+ '71.0.3551.1',
+ '71.0.3551.0',
+ '70.0.3538.17',
+ '69.0.3497.95',
+ '71.0.3550.3',
+ '71.0.3550.2',
+ '71.0.3550.1',
+ '71.0.3550.0',
+ '70.0.3538.16',
+ '69.0.3497.94',
+ '71.0.3549.1',
+ '71.0.3549.0',
+ '70.0.3538.15',
+ '69.0.3497.93',
+ '69.0.3497.92',
+ '71.0.3548.1',
+ '71.0.3548.0',
+ '70.0.3538.14',
+ '69.0.3497.91',
+ '71.0.3547.1',
+ '71.0.3547.0',
+ '70.0.3538.13',
+ '69.0.3497.90',
+ '71.0.3546.2',
+ '69.0.3497.89',
+ '71.0.3546.1',
+ '71.0.3546.0',
+ '70.0.3538.12',
+ '69.0.3497.88',
+ '71.0.3545.4',
+ '71.0.3545.3',
+ '71.0.3545.2',
+ '71.0.3545.1',
+ '71.0.3545.0',
+ '70.0.3538.11',
+ '69.0.3497.87',
+ '71.0.3544.5',
+ '71.0.3544.4',
+ '71.0.3544.3',
+ '71.0.3544.2',
+ '71.0.3544.1',
+ '71.0.3544.0',
+ '69.0.3497.86',
+ '70.0.3538.10',
+ '69.0.3497.85',
+ '70.0.3538.9',
+ '69.0.3497.84',
+ '71.0.3543.4',
+ '70.0.3538.8',
+ '71.0.3543.3',
+ '71.0.3543.2',
+ '71.0.3543.1',
+ '71.0.3543.0',
+ '70.0.3538.7',
+ '69.0.3497.83',
+ '71.0.3542.2',
+ '71.0.3542.1',
+ '71.0.3542.0',
+ '70.0.3538.6',
+ '69.0.3497.82',
+ '69.0.3497.81',
+ '71.0.3541.1',
+ '71.0.3541.0',
+ '70.0.3538.5',
+ '69.0.3497.80',
+ '71.0.3540.1',
+ '71.0.3540.0',
+ '70.0.3538.4',
+ '69.0.3497.79',
+ '70.0.3538.3',
+ '71.0.3539.1',
+ '71.0.3539.0',
+ '69.0.3497.78',
+ '68.0.3440.134',
+ '69.0.3497.77',
+ '70.0.3538.2',
+ '70.0.3538.1',
+ '70.0.3538.0',
+ '69.0.3497.76',
+ '68.0.3440.133',
+ '69.0.3497.75',
+ '70.0.3537.2',
+ '70.0.3537.1',
+ '70.0.3537.0',
+ '69.0.3497.74',
+ '68.0.3440.132',
+ '70.0.3536.0',
+ '70.0.3535.5',
+ '70.0.3535.4',
+ '70.0.3535.3',
+ '69.0.3497.73',
+ '68.0.3440.131',
+ '70.0.3532.8',
+ '70.0.3532.7',
+ '69.0.3497.72',
+ '69.0.3497.71',
+ '70.0.3535.2',
+ '70.0.3535.1',
+ '70.0.3535.0',
+ '69.0.3497.70',
+ '68.0.3440.130',
+ '69.0.3497.69',
+ '68.0.3440.129',
+ '70.0.3534.4',
+ '70.0.3534.3',
+ '70.0.3534.2',
+ '70.0.3534.1',
+ '70.0.3534.0',
+ '69.0.3497.68',
+ '68.0.3440.128',
+ '70.0.3533.2',
+ '70.0.3533.1',
+ '70.0.3533.0',
+ '69.0.3497.67',
+ '68.0.3440.127',
+ '70.0.3532.6',
+ '70.0.3532.5',
+ '70.0.3532.4',
+ '69.0.3497.66',
+ '68.0.3440.126',
+ '70.0.3532.3',
+ '70.0.3532.2',
+ '70.0.3532.1',
+ '69.0.3497.60',
+ '69.0.3497.65',
+ '69.0.3497.64',
+ '70.0.3532.0',
+ '70.0.3531.0',
+ '70.0.3530.4',
+ '70.0.3530.3',
+ '70.0.3530.2',
+ '69.0.3497.58',
+ '68.0.3440.125',
+ '69.0.3497.57',
+ '69.0.3497.56',
+ '69.0.3497.55',
+ '69.0.3497.54',
+ '70.0.3530.1',
+ '70.0.3530.0',
+ '69.0.3497.53',
+ '68.0.3440.124',
+ '69.0.3497.52',
+ '70.0.3529.3',
+ '70.0.3529.2',
+ '70.0.3529.1',
+ '70.0.3529.0',
+ '69.0.3497.51',
+ '70.0.3528.4',
+ '68.0.3440.123',
+ '70.0.3528.3',
+ '70.0.3528.2',
+ '70.0.3528.1',
+ '70.0.3528.0',
+ '69.0.3497.50',
+ '68.0.3440.122',
+ '70.0.3527.1',
+ '70.0.3527.0',
+ '69.0.3497.49',
+ '68.0.3440.121',
+ '70.0.3526.1',
+ '70.0.3526.0',
+ '68.0.3440.120',
+ '69.0.3497.48',
+ '69.0.3497.47',
+ '68.0.3440.119',
+ '68.0.3440.118',
+ '70.0.3525.5',
+ '70.0.3525.4',
+ '70.0.3525.3',
+ '68.0.3440.117',
+ '69.0.3497.46',
+ '70.0.3525.2',
+ '70.0.3525.1',
+ '70.0.3525.0',
+ '69.0.3497.45',
+ '68.0.3440.116',
+ '70.0.3524.4',
+ '70.0.3524.3',
+ '69.0.3497.44',
+ '70.0.3524.2',
+ '70.0.3524.1',
+ '70.0.3524.0',
+ '70.0.3523.2',
+ '69.0.3497.43',
+ '68.0.3440.115',
+ '70.0.3505.9',
+ '69.0.3497.42',
+ '70.0.3505.8',
+ '70.0.3523.1',
+ '70.0.3523.0',
+ '69.0.3497.41',
+ '68.0.3440.114',
+ '70.0.3505.7',
+ '69.0.3497.40',
+ '70.0.3522.1',
+ '70.0.3522.0',
+ '70.0.3521.2',
+ '69.0.3497.39',
+ '68.0.3440.113',
+ '70.0.3505.6',
+ '70.0.3521.1',
+ '70.0.3521.0',
+ '69.0.3497.38',
+ '68.0.3440.112',
+ '70.0.3520.1',
+ '70.0.3520.0',
+ '69.0.3497.37',
+ '68.0.3440.111',
+ '70.0.3519.3',
+ '70.0.3519.2',
+ '70.0.3519.1',
+ '70.0.3519.0',
+ '69.0.3497.36',
+ '68.0.3440.110',
+ '70.0.3518.1',
+ '70.0.3518.0',
+ '69.0.3497.35',
+ '69.0.3497.34',
+ '68.0.3440.109',
+ '70.0.3517.1',
+ '70.0.3517.0',
+ '69.0.3497.33',
+ '68.0.3440.108',
+ '69.0.3497.32',
+ '70.0.3516.3',
+ '70.0.3516.2',
+ '70.0.3516.1',
+ '70.0.3516.0',
+ '69.0.3497.31',
+ '68.0.3440.107',
+ '70.0.3515.4',
+ '68.0.3440.106',
+ '70.0.3515.3',
+ '70.0.3515.2',
+ '70.0.3515.1',
+ '70.0.3515.0',
+ '69.0.3497.30',
+ '68.0.3440.105',
+ '68.0.3440.104',
+ '70.0.3514.2',
+ '70.0.3514.1',
+ '70.0.3514.0',
+ '69.0.3497.29',
+ '68.0.3440.103',
+ '70.0.3513.1',
+ '70.0.3513.0',
+ '69.0.3497.28',
+ )
+ return _USER_AGENT_TPL % random.choice(_CHROME_VERSIONS)
+
+
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)',
+ 'User-Agent': random_user_agent(),
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
}
+
+USER_AGENTS = {
+ 'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
+}
+
+
+NO_DEFAULT = object()
+
+ENGLISH_MONTH_NAMES = [
+ 'January', 'February', 'March', 'April', 'May', 'June',
+ 'July', 'August', 'September', 'October', 'November', 'December']
+
+MONTH_NAMES = {
+ 'en': ENGLISH_MONTH_NAMES,
+ 'fr': [
+ 'janvier', 'février', 'mars', 'avril', 'mai', 'juin',
+ 'juillet', 'août', 'septembre', 'octobre', 'novembre', 'décembre'],
+}
+
+KNOWN_EXTENSIONS = (
+ 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac',
+ 'flv', 'f4v', 'f4a', 'f4b',
+ 'webm', 'ogg', 'ogv', 'oga', 'ogx', 'spx', 'opus',
+ 'mkv', 'mka', 'mk3d',
+ 'avi', 'divx',
+ 'mov',
+ 'asf', 'wmv', 'wma',
+ '3gp', '3g2',
+ 'mp3',
+ 'flac',
+ 'ape',
+ 'wav',
+ 'f4f', 'f4m', 'm3u8', 'smil')
+
+# needed for sanitizing filenames in restricted mode
+ACCENT_CHARS = dict(zip('ÃÃÃÃÃÃ
ÃÃÃÃÃÃÃÃÃÃÃÃÃÃÃÃÃÅÃÅÃÃÃÃÅ°ÃÃÃà áâãäåæçèéêëìÃîïðñòóôõöÅøÅùúûüűýþÿ',
+ itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUY', ['TH', 'ss'],
+ 'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuy', ['th'], 'y')))
+
+DATE_FORMATS = (
+ '%d %B %Y',
+ '%d %b %Y',
+ '%B %d %Y',
+ '%B %dst %Y',
+ '%B %dnd %Y',
+ '%B %drd %Y',
+ '%B %dth %Y',
+ '%b %d %Y',
+ '%b %dst %Y',
+ '%b %dnd %Y',
+ '%b %drd %Y',
+ '%b %dth %Y',
+ '%b %dst %Y %I:%M',
+ '%b %dnd %Y %I:%M',
+ '%b %drd %Y %I:%M',
+ '%b %dth %Y %I:%M',
+ '%Y %m %d',
+ '%Y-%m-%d',
+ '%Y/%m/%d',
+ '%Y/%m/%d %H:%M',
+ '%Y/%m/%d %H:%M:%S',
+ '%Y-%m-%d %H:%M',
+ '%Y-%m-%d %H:%M:%S',
+ '%Y-%m-%d %H:%M:%S.%f',
+ '%d.%m.%Y %H:%M',
+ '%d.%m.%Y %H.%M',
+ '%Y-%m-%dT%H:%M:%SZ',
+ '%Y-%m-%dT%H:%M:%S.%fZ',
+ '%Y-%m-%dT%H:%M:%S.%f0Z',
+ '%Y-%m-%dT%H:%M:%S',
+ '%Y-%m-%dT%H:%M:%S.%f',
+ '%Y-%m-%dT%H:%M',
+ '%b %d %Y at %H:%M',
+ '%b %d %Y at %H:%M:%S',
+ '%B %d %Y at %H:%M',
+ '%B %d %Y at %H:%M:%S',
+)
+
+DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)
+DATE_FORMATS_DAY_FIRST.extend([
+ '%d-%m-%Y',
+ '%d.%m.%Y',
+ '%d.%m.%y',
+ '%d/%m/%Y',
+ '%d/%m/%y',
+ '%d/%m/%Y %H:%M:%S',
+])
+
+DATE_FORMATS_MONTH_FIRST = list(DATE_FORMATS)
+DATE_FORMATS_MONTH_FIRST.extend([
+ '%m-%d-%Y',
+ '%m.%d.%Y',
+ '%m/%d/%Y',
+ '%m/%d/%y',
+ '%m/%d/%Y %H:%M:%S',
+])
+
+PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)"
+JSON_LD_RE = r'(?is)'
+
+
def preferredencoding():
"""Get preferred encoding.
@@ -194,47 +1783,86 @@ def preferredencoding():
"""
try:
pref = locale.getpreferredencoding()
- u'TEST'.encode(pref)
- except:
+ 'TEST'.encode(pref)
+ except Exception:
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)
-
-# In Python 2.x, json.dump expects a bytestream.
-# In Python 3.x, it writes to a character stream
-if sys.version_info < (3,0):
- def write_json_file(obj, fn):
- with open(fn, 'wb') as f:
- json.dump(obj, f)
-else:
- def write_json_file(obj, fn):
- with open(fn, 'w', encoding='utf-8') as f:
- json.dump(obj, f)
-if sys.version_info >= (2,7):
- def find_xpath_attr(node, xpath, key, val):
+def write_json_file(obj, fn):
+ """ 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': path_basename(fn) + '.',
+ 'dir': path_dirname(fn),
+ 'delete': False,
+ }
+
+ # In Python 2.x, json.dump expects a bytestream.
+ # In Python 3.x, it writes to a character stream
+ if sys.version_info < (3, 0):
+ args['mode'] = 'wb'
+ else:
+ args.update({
+ 'mode': 'w',
+ 'encoding': 'utf-8',
+ })
+
+ tf = tempfile.NamedTemporaryFile(**compat_kwargs(args))
+
+ 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 Exception:
+ try:
+ os.remove(tf.name)
+ except OSError:
+ pass
+ raise
+
+
+if sys.version_info >= (2, 7):
+ def find_xpath_attr(node, xpath, key, val=None):
""" 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)
+ assert re.match(r'^[a-zA-Z_-]+$', key)
+ expr = xpath + ('[@%s]' % key if val is None else "[@%s='%s']" % (key, val))
return node.find(expr)
else:
- def find_xpath_attr(node, xpath, key, val):
- for f in node.findall(xpath):
- if f.attrib.get(key) == val:
+ def find_xpath_attr(node, xpath, key, val=None):
+ for f in node.findall(compat_xpath(xpath)):
+ if key not in f.attrib:
+ continue
+ if val is None or f.attrib.get(key) == val:
return f
return None
# 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 = []
@@ -246,160 +1874,152 @@ def xpath_with_ns(path, ns_map):
replaced.append('{%s}%s' % (ns_map[ns], tag))
return '/'.join(replaced)
-def htmlentity_transform(matchobj):
- """Transforms an HTML entity to a character.
-
- This function receives a match object and is intended to be used with
- the re.sub() function.
- """
- entity = matchobj.group(1)
- # Known non-numeric HTML entity
- if entity in compat_html_entities.name2codepoint:
- return compat_chr(compat_html_entities.name2codepoint[entity])
+def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
+ def _find_xpath(xpath):
+ return node.find(compat_xpath(xpath))
- mobj = re.match(u'(?u)#(x?\\d+)', entity)
- if mobj is not None:
- numstr = mobj.group(1)
- if numstr.startswith(u'x'):
- base = 16
- numstr = u'0%s' % numstr
+ if isinstance(xpath, (str, compat_str)):
+ n = _find_xpath(xpath)
+ else:
+ for xp in xpath:
+ n = _find_xpath(xp)
+ if n is not None:
+ break
+
+ if n is None:
+ if default is not NO_DEFAULT:
+ return default
+ elif fatal:
+ name = xpath if name is None else name
+ raise ExtractorError('Could not find XML element %s' % name)
else:
- base = 10
- return compat_chr(int(numstr, base))
+ return None
+ return n
+
+
+def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
+ n = xpath_element(node, xpath, name, fatal=fatal, default=default)
+ if n is None or n == default:
+ return n
+ if n.text is None:
+ if default is not NO_DEFAULT:
+ return default
+ elif fatal:
+ name = xpath if name is None else name
+ raise ExtractorError('Could not find XML element\'s text %s' % name)
+ else:
+ return None
+ return n.text
- # Unknown entity in name, return its literal representation
- return (u'&%s;' % entity)
-
-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:
+def xpath_attr(node, xpath, key, name=None, fatal=False, default=NO_DEFAULT):
+ n = find_xpath_attr(node, xpath, key)
+ if n is None:
+ if default is not NO_DEFAULT:
+ return default
+ elif fatal:
+ name = '%s[@%s]' % (xpath, key) if name is None else name
+ raise ExtractorError('Could not find XML attribute %s' % name)
+ else:
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))
+ return n.attrib[key]
+
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)
+ return get_element_by_attribute('id', id, html)
+
+
+def get_element_by_class(class_name, html):
+ """Return the content of the first tag with the specified class in the passed HTML document"""
+ retval = get_elements_by_class(class_name, html)
+ return retval[0] if retval else None
+
+
+def get_element_by_attribute(attribute, value, html, escape_value=True):
+ retval = get_elements_by_attribute(attribute, value, html, escape_value)
+ return retval[0] if retval else None
+
-def get_element_by_attribute(attribute, value, html):
+def get_elements_by_class(class_name, html):
+ """Return the content of all tags with the specified class in the passed HTML document as a list"""
+ return get_elements_by_attribute(
+ 'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
+ html, escape_value=False)
+
+
+def get_elements_by_attribute(attribute, value, html, escape_value=True):
"""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
+ value = re.escape(value) if escape_value else value
- def handle_starttag(self, tag, attrs):
- if tag != 'meta':
- return
- attrs = dict(attrs)
- if attrs.get('name') == self.name:
- self.result = attrs.get('content')
+ retlist = []
+ for m in re.finditer(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.*?)
+ \1>
+ ''' % (re.escape(attribute), value), html):
+ res = m.group('content')
- def get_result(self):
- return self.result
+ if res.startswith('"') or res.startswith("'"):
+ res = res[1:-1]
-def get_meta_content(name, html):
- """
- Return the content attribute from the meta tag with the given name attribute.
+ retlist.append(unescapeHTML(res))
+
+ return retlist
+
+
+class HTMLAttributeParser(compat_HTMLParser):
+ """Trivial HTML parser to gather the attributes for a single element"""
+ def __init__(self):
+ self.attrs = {}
+ compat_HTMLParser.__init__(self)
+
+ def handle_starttag(self, tag, attrs):
+ self.attrs = dict(attrs)
+
+
+def extract_attributes(html_element):
+ """Given a string for an HTML element such as
+
+ Decode and return a dictionary of attributes.
+ {
+ 'a': 'foo', 'b': 'bar', c: 'baz', d: 'boz',
+ 'empty': '', 'noval': None, 'entity': '&',
+ 'sq': '"', 'dq': '\''
+ }.
+ NB HTMLParser is stricter in Python 2.6 & 3.2 than in later versions,
+ but the cases in the unit test will work for all of 2.6, 2.7, 3.2-3.5.
"""
- parser = MetaParser(name)
+ parser = HTMLAttributeParser()
try:
- parser.loads(html)
- except compat_html_parser.HTMLParseError:
+ parser.feed(html_element)
+ parser.close()
+ # Older Python may throw HTMLParseError in case of malformed HTML
+ except compat_HTMLParseError:
pass
- return parser.get_result()
+ return parser.attrs
def clean_html(html):
"""Clean an HTML snippet into a readable string"""
+
+ if html is None: # Convenience for sanitizing descriptions etc.
+ return html
+
# Newline vs
html = html.replace('\n', ' ')
- html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
- html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
+ html = re.sub(r'(?u)\s*<\s*br\s*/?\s*>\s*', '\n', html)
+ html = re.sub(r'(?u)<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
# Strip html tags
html = re.sub('<.*?>', '', html)
# Replace html entities
@@ -418,7 +2038,7 @@ 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)
@@ -430,15 +2050,12 @@ def sanitize_open(filename, open_mode):
raise
# 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)
- )
+ alt_filename = sanitize_path(filename)
if alt_filename == filename:
raise
else:
# An exception here should be caught in the caller
- stream = open(encodeFilename(filename), open_mode)
+ stream = open(encodeFilename(alt_filename), open_mode)
return (stream, alt_filename)
@@ -450,12 +2067,16 @@ 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.
- Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
+ Set is_id if this is not an arbitrary string, but an ID that should be kept
+ if possible.
"""
def replace_insane(char):
+ if restricted and char in ACCENT_CHARS:
+ return ACCENT_CHARS[char]
if char == '?' or ord(char) < 32 or ord(char) == 127:
return ''
elif char == '"':
@@ -470,7 +2091,9 @@ def sanitize_filename(s, restricted=False, is_id=False):
return '_'
return char
- result = u''.join(map(replace_insane, s))
+ # Handle timestamps
+ s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)
+ result = ''.join(map(replace_insane, s))
if not is_id:
while '__' in result:
result = result.replace('__', '_')
@@ -478,10 +2101,59 @@ def sanitize_filename(s, restricted=False, is_id=False):
# Common case of "Foreign band name - English song title"
if restricted and result.startswith('-_'):
result = result[2:]
+ if result.startswith('-'):
+ result = '_' + result[len('-'):]
+ result = result.lstrip('.')
if not result:
result = '_'
return result
+
+def sanitize_path(s):
+ """Sanitizes and normalizes path on Windows"""
+ if sys.platform != 'win32':
+ return s
+ drive_or_unc, _ = os.path.splitdrive(s)
+ if sys.version_info < (2, 7) and not drive_or_unc:
+ drive_or_unc, _ = os.path.splitunc(s)
+ norm_path = os.path.normpath(remove_start(s, drive_or_unc)).split(os.path.sep)
+ if drive_or_unc:
+ norm_path.pop(0)
+ sanitized_path = [
+ path_part if path_part in ['.', '..'] else re.sub(r'(?:[/<>:"\|\\?\*]|[\s.]$)', '#', path_part)
+ for path_part in norm_path]
+ if drive_or_unc:
+ sanitized_path.insert(0, drive_or_unc + os.path.sep)
+ return os.path.join(*sanitized_path)
+
+
+def sanitize_url(url):
+ # Prepend protocol-less URLs with `http:` scheme in order to mitigate
+ # the number of unwanted failures due to missing protocol
+ if url.startswith('//'):
+ return 'http:%s' % url
+ # Fix some common typos seen so far
+ COMMON_TYPOS = (
+ # https://github.com/ytdl-org/youtube-dl/issues/15649
+ (r'^httpss://', r'https://'),
+ # https://bx1.be/lives/direct-tv/
+ (r'^rmtp([es]?)://', r'rtmp\1://'),
+ )
+ for mistake, fixup in COMMON_TYPOS:
+ if re.match(mistake, url):
+ return re.sub(mistake, fixup, url)
+ return url
+
+
+def sanitized_Request(url, *args, **kwargs):
+ return compat_urllib_request.Request(sanitize_url(url), *args, **kwargs)
+
+
+def expand_path(s):
+ """Expand shell variables and ~"""
+ return os.path.expandvars(compat_expanduser(s))
+
+
def orderedSet(iterable):
""" Remove all duplicates from the input iterable """
res = []
@@ -490,36 +2162,106 @@ def orderedSet(iterable):
res.append(el)
return res
+
+def _htmlentity_transform(entity_with_semicolon):
+ """Transforms an HTML entity to a character."""
+ entity = entity_with_semicolon[:-1]
+
+ # Known non-numeric HTML entity
+ if entity in compat_html_entities.name2codepoint:
+ return compat_chr(compat_html_entities.name2codepoint[entity])
+
+ # TODO: HTML5 allows entities without a semicolon. For example,
+ # 'Éric' should be decoded as 'Ãric'.
+ if entity_with_semicolon in compat_html_entities_html5:
+ return compat_html_entities_html5[entity_with_semicolon]
+
+ mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
+ if mobj is not None:
+ numstr = mobj.group(1)
+ if numstr.startswith('x'):
+ base = 16
+ numstr = '0%s' % numstr
+ else:
+ base = 10
+ # See https://github.com/ytdl-org/youtube-dl/issues/7518
+ try:
+ return compat_chr(int(numstr, base))
+ except ValueError:
+ pass
+
+ # Unknown entity in name, return its literal representation
+ return '&%s;' % entity
+
+
def unescapeHTML(s):
- """
- @param s a string
- """
- assert type(s) == type(u'')
+ if s is None:
+ return None
+ assert type(s) == compat_str
- result = re.sub(u'(?u)&(.+?);', htmlentity_transform, s)
- return result
+ return re.sub(
+ r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
+
+
+def get_subprocess_encoding():
+ if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
+ # For subprocess calls, encode with locale encoding
+ # Refer to http://stackoverflow.com/a/9951851/35070
+ encoding = preferredencoding()
+ else:
+ encoding = sys.getfilesystemencoding()
+ if encoding is None:
+ encoding = 'utf-8'
+ return encoding
-def encodeFilename(s):
+
+def encodeFilename(s, for_subprocess=False):
"""
@param s The name of the file
"""
- assert type(s) == type(u'')
+ assert type(s) == compat_str
# Python 3 has a Unicode API
if sys.version_info >= (3, 0):
return s
- if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
- # Pass u'' 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.)
+ # 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 and sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
return s
- else:
- encoding = sys.getfilesystemencoding()
- if encoding is None:
- encoding = 'utf-8'
- return s.encode(encoding, 'ignore')
+
+ # Jython assumes filenames are Unicode strings though reported as Python 2.x compatible
+ if sys.platform.startswith('java'):
+ return s
+
+ return s.encode(get_subprocess_encoding(), 'ignore')
+
+
+def decodeFilename(b, for_subprocess=False):
+
+ if sys.version_info >= (3, 0):
+ return b
+
+ if not isinstance(b, bytes):
+ return b
+
+ return b.decode(get_subprocess_encoding(), 'ignore')
+
+
+def encodeArgument(s):
+ if not isinstance(s, compat_str):
+ # Legacy code that uses byte strings
+ # Uncomment the following line after fixing all post processors
+ # assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s))
+ s = s.decode('ascii')
+ return encodeFilename(s, True)
+
+
+def decodeArgument(b):
+ return decodeFilename(b, True)
+
def decodeOption(optval):
if optval is None:
@@ -530,6 +2272,7 @@ 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)
@@ -538,58 +2281,82 @@ def formatSeconds(secs):
else:
return '%d' % secs
-def make_HTTPS_handler(opts_no_check_certificate):
- if sys.version_info < (3, 2):
- import httplib
- class HTTPSConnectionV3(httplib.HTTPSConnection):
- def __init__(self, *args, **kwargs):
- httplib.HTTPSConnection.__init__(self, *args, **kwargs)
+def make_HTTPS_handler(params, **kwargs):
+ opts_no_check_certificate = params.get('nocheckcertificate', False)
+ if hasattr(ssl, 'create_default_context'): # Python >= 3.4 or 2.7.9
+ context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
+ if opts_no_check_certificate:
+ context.check_hostname = False
+ context.verify_mode = ssl.CERT_NONE
+ try:
+ return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
+ except TypeError:
+ # Python 2.7.8
+ # (create_default_context present but HTTPSHandler has no context=)
+ pass
- def connect(self):
- sock = socket.create_connection((self.host, self.port), self.timeout)
- if self._tunnel_host:
- self.sock = sock
- self._tunnel()
- try:
- self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv3)
- except ssl.SSLError:
- self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)
-
- class HTTPSHandlerV3(compat_urllib_request.HTTPSHandler):
- def https_open(self, req):
- return self.do_open(HTTPSConnectionV3, req)
- return HTTPSHandlerV3()
- else:
- context = ssl.SSLContext(ssl.PROTOCOL_SSLv3)
- context.set_default_verify_paths()
-
+ if sys.version_info < (3, 2):
+ return YoutubeDLHTTPSHandler(params, **kwargs)
+ else: # Python < 3.4
+ context = ssl.SSLContext(ssl.PROTOCOL_TLSv1)
context.verify_mode = (ssl.CERT_NONE
if opts_no_check_certificate
else ssl.CERT_REQUIRED)
- return compat_urllib_request.HTTPSHandler(context=context)
+ context.set_default_verify_paths()
+ return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
+
+
+def bug_reports_message():
+ 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.'
+ return msg
+
+
+class YoutubeDLError(Exception):
+ """Base exception for YoutubeDL errors."""
+ pass
-class ExtractorError(Exception):
+
+class ExtractorError(YoutubeDLError):
"""Error during info extraction."""
- def __init__(self, msg, tb=None, expected=False, cause=None):
+
+ 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.
"""
if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
expected = True
+ if video_id is not None:
+ msg = video_id + ': ' + msg
+ if 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.'
+ msg += bug_reports_message()
super(ExtractorError, self).__init__(msg)
self.traceback = tb
self.exc_info = sys.exc_info() # preserve original exception
self.cause = cause
+ self.video_id = video_id
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 UnsupportedError(ExtractorError):
+ def __init__(self, url):
+ super(UnsupportedError, self).__init__(
+ 'Unsupported URL: %s' % url, expected=True)
+ self.url = url
class RegexNotFoundError(ExtractorError):
@@ -597,20 +2364,33 @@ class RegexNotFoundError(ExtractorError):
pass
-class DownloadError(Exception):
+class GeoRestrictedError(ExtractorError):
+ """Geographic restriction Error exception.
+
+ This exception may be thrown when a video is not available from your
+ geographic location due to geographic restrictions imposed by a website.
+ """
+ def __init__(self, msg, countries=None):
+ super(GeoRestrictedError, self).__init__(msg, expected=True)
+ self.msg = msg
+ self.countries = countries
+
+
+class DownloadError(YoutubeDLError):
"""Download Error exception.
This exception may be thrown by FileDownloader objects if they are not
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)
self.exc_info = exc_info
-class SameFileError(Exception):
+class SameFileError(YoutubeDLError):
"""Same File exception.
This exception will be thrown by FileDownloader objects if they detect
@@ -619,21 +2399,24 @@ class SameFileError(Exception):
pass
-class PostProcessingError(Exception):
+class PostProcessingError(YoutubeDLError):
"""Post Processing exception.
This exception may be raised by PostProcessor's .run() method to
indicate an error in the postprocessing task.
"""
+
def __init__(self, msg):
+ super(PostProcessingError, self).__init__(msg)
self.msg = msg
-class MaxDownloadsReached(Exception):
+
+class MaxDownloadsReached(YoutubeDLError):
""" --max-downloads limit has been reached. """
pass
-class UnavailableVideoError(Exception):
+class UnavailableVideoError(YoutubeDLError):
"""Unavailable Format exception.
This exception will be thrown when a video is requested
@@ -642,21 +2425,118 @@ class UnavailableVideoError(Exception):
pass
-class ContentTooShortError(Exception):
+class ContentTooShortError(YoutubeDLError):
"""Content Too Short exception.
This exception may be raised by FileDownloader objects when a file they
download is too small for what the server announced first, indicating
the connection was probably interrupted.
"""
- # Both in bytes
- downloaded = None
- expected = None
def __init__(self, downloaded, expected):
+ super(ContentTooShortError, self).__init__(
+ 'Downloaded {0} bytes, expected {1} bytes'.format(downloaded, expected)
+ )
+ # Both in bytes
self.downloaded = downloaded
self.expected = expected
+
+class XAttrMetadataError(YoutubeDLError):
+ def __init__(self, code=None, msg='Unknown error'):
+ super(XAttrMetadataError, self).__init__(msg)
+ self.code = code
+ self.msg = msg
+
+ # Parsing code and msg
+ if (self.code in (errno.ENOSPC, errno.EDQUOT)
+ or 'No space left' in self.msg or 'Disk quota excedded' in self.msg):
+ self.reason = 'NO_SPACE'
+ elif self.code == errno.E2BIG or 'Argument list too long' in self.msg:
+ self.reason = 'VALUE_TOO_LONG'
+ else:
+ self.reason = 'NOT_SUPPORTED'
+
+
+class XAttrUnavailableError(YoutubeDLError):
+ pass
+
+
+def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
+ # Working around python 2 bug (see http://bugs.python.org/issue17849) by limiting
+ # expected HTTP responses to meet HTTP/1.0 or later (see also
+ # https://github.com/ytdl-org/youtube-dl/issues/6727)
+ if sys.version_info < (3, 0):
+ kwargs['strict'] = True
+ hc = http_class(*args, **compat_kwargs(kwargs))
+ source_address = ydl_handler._params.get('source_address')
+
+ if source_address is not None:
+ # This is to workaround _create_connection() from socket where it will try all
+ # address data from getaddrinfo() including IPv6. This filters the result from
+ # getaddrinfo() based on the source_address value.
+ # This is based on the cpython socket.create_connection() function.
+ # https://github.com/python/cpython/blob/master/Lib/socket.py#L691
+ def _create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None):
+ host, port = address
+ err = None
+ addrs = socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM)
+ af = socket.AF_INET if '.' in source_address[0] else socket.AF_INET6
+ ip_addrs = [addr for addr in addrs if addr[0] == af]
+ if addrs and not ip_addrs:
+ ip_version = 'v4' if af == socket.AF_INET else 'v6'
+ raise socket.error(
+ "No remote IP%s addresses available for connect, can't use '%s' as source address"
+ % (ip_version, source_address[0]))
+ for res in ip_addrs:
+ af, socktype, proto, canonname, sa = res
+ sock = None
+ try:
+ sock = socket.socket(af, socktype, proto)
+ if timeout is not socket._GLOBAL_DEFAULT_TIMEOUT:
+ sock.settimeout(timeout)
+ sock.bind(source_address)
+ sock.connect(sa)
+ err = None # Explicitly break reference cycle
+ return sock
+ except socket.error as _:
+ err = _
+ if sock is not None:
+ sock.close()
+ if err is not None:
+ raise err
+ else:
+ raise socket.error('getaddrinfo returns an empty list')
+ if hasattr(hc, '_create_connection'):
+ hc._create_connection = _create_connection
+ sa = (source_address, 0)
+ if hasattr(hc, 'source_address'): # Python 2.7+
+ hc.source_address = sa
+ else: # Python 2.6
+ def _hc_connect(self, *args, **kwargs):
+ sock = _create_connection(
+ (self.host, self.port), self.timeout, sa)
+ if is_https:
+ self.sock = ssl.wrap_socket(
+ sock, self.key_file, self.cert_file,
+ ssl_version=ssl.PROTOCOL_TLSv1)
+ else:
+ self.sock = sock
+ hc.connect = functools.partial(_hc_connect, hc)
+
+ return hc
+
+
+def handle_youtubedl_headers(headers):
+ filtered_headers = headers
+
+ if 'Youtubedl-no-compression' in filtered_headers:
+ filtered_headers = dict((k, v) for k, v in filtered_headers.items() if k.lower() != 'accept-encoding')
+ del filtered_headers['Youtubedl-no-compression']
+
+ return filtered_headers
+
+
class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
"""Handler for HTTP requests and responses.
@@ -664,7 +2544,7 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
the standard headers to every HTTP request and handles gzipped and
deflated responses from web servers. If compression is to be avoided in
a particular request, the original request in the program code only has
- to include the HTTP header "Youtubedl-No-Compression", which will be
+ to include the HTTP header "Youtubedl-no-compression", which will be
removed before making the real request.
Part of this code was copied from:
@@ -675,6 +2555,22 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
public domain.
"""
+ def __init__(self, params, *args, **kwargs):
+ compat_urllib_request.HTTPHandler.__init__(self, *args, **kwargs)
+ self._params = params
+
+ def http_open(self, req):
+ conn_class = compat_http_client.HTTPConnection
+
+ socks_proxy = req.headers.get('Ytdl-socks-proxy')
+ if socks_proxy:
+ conn_class = make_socks_conn_class(conn_class, socks_proxy)
+ del req.headers['Ytdl-socks-proxy']
+
+ return self.do_open(functools.partial(
+ _create_http_connection, self, conn_class, False),
+ req)
+
@staticmethod
def deflate(data):
try:
@@ -682,28 +2578,35 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
except zlib.error:
return zlib.decompress(data)
- @staticmethod
- def addinfourl_wrapper(stream, headers, url, code):
- if hasattr(compat_urllib_request.addinfourl, 'getcode'):
- return compat_urllib_request.addinfourl(stream, headers, url, code)
- ret = compat_urllib_request.addinfourl(stream, headers, url)
- ret.code = code
- return ret
-
def http_request(self, req):
- for h,v in std_headers.items():
- if h in req.headers:
- del req.headers[h]
- req.add_header(h, v)
- if 'Youtubedl-no-compression' in req.headers:
- if 'Accept-encoding' in req.headers:
- del req.headers['Accept-encoding']
- del req.headers['Youtubedl-no-compression']
- if 'Youtubedl-user-agent' in req.headers:
- if 'User-agent' in req.headers:
- del req.headers['User-agent']
- req.headers['User-agent'] = req.headers['Youtubedl-user-agent']
- del req.headers['Youtubedl-user-agent']
+ # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
+ # always respected by websites, some tend to give out URLs with non percent-encoded
+ # non-ASCII characters (see telemb.py, ard.py [#3412])
+ # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
+ # To work around aforementioned issue we will replace request's original URL with
+ # percent-encoded one
+ # Since redirects are also affected (e.g. http://www.southpark.de/alle-episoden/s18e09)
+ # the code of this workaround has been moved here from YoutubeDL.urlopen()
+ url = req.get_full_url()
+ url_escaped = escape_url(url)
+
+ # Substitute URL if any change after escaping
+ if url != url_escaped:
+ req = update_Request(req, url=url_escaped)
+
+ for h, v in std_headers.items():
+ # Capitalize is needed because of Python bug 2275: http://bugs.python.org/issue2275
+ # The dict keys are capitalized because of this bug by urllib
+ if h.capitalize() not in req.headers:
+ req.add_header(h, v)
+
+ req.headers = handle_youtubedl_headers(req.headers)
+
+ if sys.version_info < (2, 7) and '#' in req.get_full_url():
+ # Python 2.6 is brain-dead when it comes to fragments
+ req._Request__original = req._Request__original.partition('#')[0]
+ req._Request__r_type = req._Request__r_type.partition('#')[0]
+
return req
def http_response(self, req, resp):
@@ -726,70 +2629,308 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
break
else:
raise original_ioerror
- resp = self.addinfourl_wrapper(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
+ resp = compat_urllib_request.addinfourl(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
+ del resp.headers['Content-encoding']
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = io.BytesIO(self.deflate(resp.read()))
- resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+ resp = compat_urllib_request.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
+ del resp.headers['Content-encoding']
+ # Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986 (see
+ # https://github.com/ytdl-org/youtube-dl/issues/6457).
+ if 300 <= resp.code < 400:
+ location = resp.headers.get('Location')
+ if location:
+ # As of RFC 2616 default charset is iso-8859-1 that is respected by python 3
+ if sys.version_info >= (3, 0):
+ location = location.encode('iso-8859-1').decode('utf-8')
+ else:
+ location = location.decode('utf-8')
+ location_escaped = escape_url(location)
+ if location != location_escaped:
+ del resp.headers['Location']
+ if sys.version_info < (3, 0):
+ location_escaped = location_escaped.encode('utf-8')
+ resp.headers['Location'] = location_escaped
return resp
https_request = http_request
https_response = http_response
-def unified_strdate(date_str):
+
+def make_socks_conn_class(base_class, socks_proxy):
+ assert issubclass(base_class, (
+ compat_http_client.HTTPConnection, compat_http_client.HTTPSConnection))
+
+ url_components = compat_urlparse.urlparse(socks_proxy)
+ if url_components.scheme.lower() == 'socks5':
+ socks_type = ProxyType.SOCKS5
+ elif url_components.scheme.lower() in ('socks', 'socks4'):
+ socks_type = ProxyType.SOCKS4
+ elif url_components.scheme.lower() == 'socks4a':
+ socks_type = ProxyType.SOCKS4A
+
+ def unquote_if_non_empty(s):
+ if not s:
+ return s
+ return compat_urllib_parse_unquote_plus(s)
+
+ proxy_args = (
+ socks_type,
+ url_components.hostname, url_components.port or 1080,
+ True, # Remote DNS
+ unquote_if_non_empty(url_components.username),
+ unquote_if_non_empty(url_components.password),
+ )
+
+ class SocksConnection(base_class):
+ def connect(self):
+ self.sock = sockssocket()
+ self.sock.setproxy(*proxy_args)
+ if type(self.timeout) in (int, float):
+ self.sock.settimeout(self.timeout)
+ self.sock.connect((self.host, self.port))
+
+ if isinstance(self, compat_http_client.HTTPSConnection):
+ if hasattr(self, '_context'): # Python > 2.6
+ self.sock = self._context.wrap_socket(
+ self.sock, server_hostname=self.host)
+ else:
+ self.sock = ssl.wrap_socket(self.sock)
+
+ return SocksConnection
+
+
+class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
+ def __init__(self, params, https_conn_class=None, *args, **kwargs):
+ compat_urllib_request.HTTPSHandler.__init__(self, *args, **kwargs)
+ self._https_conn_class = https_conn_class or compat_http_client.HTTPSConnection
+ self._params = params
+
+ def https_open(self, req):
+ kwargs = {}
+ conn_class = self._https_conn_class
+
+ if hasattr(self, '_context'): # python > 2.6
+ kwargs['context'] = self._context
+ if hasattr(self, '_check_hostname'): # python 3.x
+ kwargs['check_hostname'] = self._check_hostname
+
+ socks_proxy = req.headers.get('Ytdl-socks-proxy')
+ if socks_proxy:
+ conn_class = make_socks_conn_class(conn_class, socks_proxy)
+ del req.headers['Ytdl-socks-proxy']
+
+ return self.do_open(functools.partial(
+ _create_http_connection, self, conn_class, True),
+ req, **kwargs)
+
+
+class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
+ _HTTPONLY_PREFIX = '#HttpOnly_'
+
+ def save(self, filename=None, ignore_discard=False, ignore_expires=False):
+ # Store session cookies with `expires` set to 0 instead of an empty
+ # string
+ for cookie in self:
+ if cookie.expires is None:
+ cookie.expires = 0
+ compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires)
+
+ def load(self, filename=None, ignore_discard=False, ignore_expires=False):
+ """Load cookies from a file."""
+ if filename is None:
+ if self.filename is not None:
+ filename = self.filename
+ else:
+ raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
+
+ cf = io.StringIO()
+ with open(filename) as f:
+ for line in f:
+ if line.startswith(self._HTTPONLY_PREFIX):
+ line = line[len(self._HTTPONLY_PREFIX):]
+ cf.write(compat_str(line))
+ cf.seek(0)
+ self._really_load(cf, filename, ignore_discard, ignore_expires)
+ # Session cookies are denoted by either `expires` field set to
+ # an empty string or 0. MozillaCookieJar only recognizes the former
+ # (see [1]). So we need force the latter to be recognized as session
+ # cookies on our own.
+ # Session cookies may be important for cookies-based authentication,
+ # e.g. usually, when user does not check 'Remember me' check box while
+ # logging in on a site, some important cookies are stored as session
+ # cookies so that not recognizing them will result in failed login.
+ # 1. https://bugs.python.org/issue17164
+ for cookie in self:
+ # Treat `expires=0` cookies as session cookies
+ if cookie.expires == 0:
+ cookie.expires = None
+ cookie.discard = True
+
+
+class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
+ def __init__(self, cookiejar=None):
+ compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar)
+
+ def http_response(self, request, response):
+ # Python 2 will choke on next HTTP request in row if there are non-ASCII
+ # characters in Set-Cookie HTTP header of last response (see
+ # https://github.com/ytdl-org/youtube-dl/issues/6769).
+ # In order to at least prevent crashing we will percent encode Set-Cookie
+ # header before HTTPCookieProcessor starts processing it.
+ # if sys.version_info < (3, 0) and response.headers:
+ # for set_cookie_header in ('Set-Cookie', 'Set-Cookie2'):
+ # set_cookie = response.headers.get(set_cookie_header)
+ # if set_cookie:
+ # set_cookie_escaped = compat_urllib_parse.quote(set_cookie, b"%/;:@&=+$,!~*'()?#[] ")
+ # if set_cookie != set_cookie_escaped:
+ # del response.headers[set_cookie_header]
+ # response.headers[set_cookie_header] = set_cookie_escaped
+ return compat_urllib_request.HTTPCookieProcessor.http_response(self, request, response)
+
+ https_request = compat_urllib_request.HTTPCookieProcessor.http_request
+ https_response = http_response
+
+
+def extract_timezone(date_str):
+ m = re.search(
+ r'^.{8,}?(?PZ$| ?(?P\+|-)(?P[0-9]{2}):?(?P[0-9]{2})$)',
+ date_str)
+ if not m:
+ timezone = datetime.timedelta()
+ else:
+ date_str = date_str[:-len(m.group('tz'))]
+ if not m.group('sign'):
+ timezone = datetime.timedelta()
+ else:
+ sign = 1 if m.group('sign') == '+' else -1
+ timezone = datetime.timedelta(
+ hours=sign * int(m.group('hours')),
+ minutes=sign * int(m.group('minutes')))
+ return timezone, date_str
+
+
+def parse_iso8601(date_str, delimiter='T', timezone=None):
+ """ Return a UNIX timestamp from the given date """
+
+ if date_str is None:
+ return None
+
+ date_str = re.sub(r'\.[0-9]+', '', date_str)
+
+ if timezone is None:
+ timezone, date_str = extract_timezone(date_str)
+
+ try:
+ date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
+ dt = datetime.datetime.strptime(date_str, date_format) - timezone
+ return calendar.timegm(dt.timetuple())
+ except ValueError:
+ pass
+
+
+def date_formats(day_first=True):
+ return DATE_FORMATS_DAY_FIRST if day_first else DATE_FORMATS_MONTH_FIRST
+
+
+def unified_strdate(date_str, day_first=True):
"""Return a string with the date in the format YYYYMMDD"""
+
+ if date_str is None:
+ return None
upload_date = None
- #Replace commas
- date_str = date_str.replace(',',' ')
- # %z (UTC offset) is only supported in python>=3.2
- date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
- format_expressions = [
- '%d %B %Y',
- '%B %d %Y',
- '%b %d %Y',
- '%Y-%m-%d',
- '%d/%m/%Y',
- '%Y/%m/%d %H:%M:%S',
- '%d.%m.%Y %H:%M',
- '%Y-%m-%dT%H:%M:%SZ',
- '%Y-%m-%dT%H:%M:%S.%fZ',
- '%Y-%m-%dT%H:%M:%S.%f0Z',
- '%Y-%m-%dT%H:%M:%S',
- ]
- for expression in format_expressions:
+ # Replace commas
+ date_str = date_str.replace(',', ' ')
+ # Remove AM/PM + timezone
+ date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
+ _, date_str = extract_timezone(date_str)
+
+ for expression in date_formats(day_first):
try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
- except:
+ except ValueError:
pass
- return upload_date
+ if upload_date is None:
+ timetuple = email.utils.parsedate_tz(date_str)
+ if timetuple:
+ try:
+ upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
+ except ValueError:
+ pass
+ if upload_date is not None:
+ return compat_str(upload_date)
+
+
+def unified_timestamp(date_str, day_first=True):
+ if date_str is None:
+ return None
+
+ date_str = re.sub(r'[,|]', '', date_str)
+
+ pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
+ timezone, date_str = extract_timezone(date_str)
+
+ # Remove AM/PM + timezone
+ date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
-def determine_ext(url, default_ext=u'unknown_video'):
- guess = url.partition(u'?')[0].rpartition(u'.')[2]
+ # Remove unrecognized timezones from ISO 8601 alike timestamps
+ m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P\s*[A-Z]+)$', date_str)
+ if m:
+ date_str = date_str[:-len(m.group('tz'))]
+
+ # Python only supports microseconds, so remove nanoseconds
+ m = re.search(r'^([0-9]{4,}-[0-9]{1,2}-[0-9]{1,2}T[0-9]{1,2}:[0-9]{1,2}:[0-9]{1,2}\.[0-9]{6})[0-9]+$', date_str)
+ if m:
+ date_str = m.group(1)
+
+ for expression in date_formats(day_first):
+ try:
+ dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
+ return calendar.timegm(dt.timetuple())
+ except ValueError:
+ pass
+ timetuple = email.utils.parsedate_tz(date_str)
+ if timetuple:
+ return calendar.timegm(timetuple) + pm_delta * 3600
+
+
+def determine_ext(url, default_ext='unknown_video'):
+ if url is None or '.' not in url:
+ return default_ext
+ guess = url.partition('?')[0].rpartition('.')[2]
if re.match(r'^[A-Za-z0-9]+$', guess):
return guess
+ # Try extract ext from URLs like http://example.com/foo/bar.mp4/?download
+ elif guess.rstrip('/') in KNOWN_EXTENSIONS:
+ return guess.rstrip('/')
else:
return default_ext
-def subtitles_filename(filename, sub_lang, sub_format):
- return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
+
+def subtitles_filename(filename, sub_lang, sub_format, expected_real_ext=None):
+ return replace_extension(filename, sub_lang + '.' + sub_format, expected_real_ext)
+
def date_from_str(date_str):
"""
Return a datetime object from a string in the format YYYYMMDD or
(now|today)[+-][0-9](day|week|month|year)(s)?"""
today = datetime.date.today()
- if date_str == 'now'or date_str == 'today':
+ if date_str in ('now', 'today'):
return today
- match = re.match('(now|today)(?P[+-])(?P