#!/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 errno
+import functools
import gzip
import io
+import itertools
import json
import locale
+import math
+import operator
import os
+import pipes
+import platform
import re
+import socket
+import ssl
+import subprocess
import sys
+import tempfile
import traceback
+import xml.etree.ElementTree
import zlib
-import email.utils
-import json
-import datetime
-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 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 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_HTMLParser,
+ compat_basestring,
+ compat_chr,
+ compat_etree_fromstring,
+ compat_html_entities,
+ compat_html_entities_html5,
+ compat_http_client,
+ compat_kwargs,
+ compat_os_name,
+ compat_parse_qs,
+ compat_shlex_quote,
+ compat_socket_create_connection,
+ 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)
+
+
+# This is not clearly defined otherwise
+compiled_regex_type = type(re.compile(''))
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
+ 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/47.0 (Chrome)',
'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('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ',
+ itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUYP', ['ss'],
+ 'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuypy')))
+
+DATE_FORMATS = (
+ '%d %B %Y',
+ '%d %b %Y',
+ '%B %d %Y',
+ '%B %dst %Y',
+ '%B %dnd %Y',
+ '%B %dth %Y',
+ '%b %d %Y',
+ '%b %dst %Y',
+ '%b %dnd %Y',
+ '%b %dth %Y',
+ '%b %dst %Y %I:%M',
+ '%b %dnd %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',
+)
+
+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\('\|'\)"
+
+
def preferredencoding():
"""Get preferred encoding.
"""
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)
-def htmlentity_transform(matchobj):
- """Transforms an HTML entity to a character.
+def write_json_file(obj, fn):
+ """ Encode obj as JSON and write it to fn, atomically if possible """
- This function receives a match object and is intended to be used with
- the re.sub() function.
- """
- entity = matchobj.group(1)
+ 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',
+ })
- # Known non-numeric HTML entity
- if entity in compat_html_entities.name2codepoint:
- return compat_chr(compat_html_entities.name2codepoint[entity])
+ tf = tempfile.NamedTemporaryFile(**compat_kwargs(args))
- 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
+ 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)
+ 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=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 = []
+ for c in components:
+ if len(c) == 1:
+ replaced.append(c[0])
else:
- base = 10
- return compat_chr(int(numstr, base))
+ ns, tag = c
+ replaced.append('{%s}%s' % (ns_map[ns], tag))
+ return '/'.join(replaced)
- # 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 AttrParser(compat_html_parser.HTMLParser):
- """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.html = None
- self.watch_startpos = False
- self.error_count = 0
- compat_html_parser.HTMLParser.__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 loads(self, html):
- self.html = html
- self.feed(html)
- self.close()
- 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:
+def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
+ def _find_xpath(xpath):
+ return node.find(compat_xpath(xpath))
+
+ 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:
return None
- if len(self.result) != 3:
+ 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
- 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("</scr'+'ipt>")
- if self.rawdata[i:].startswith("</scr'+'ipt>")
- else compat_html_parser.HTMLParser.parse_endtag(self, i))
+ return n.text
+
+
+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
+ 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_attribute(attribute, value, html):
+
+def get_element_by_class(class_name, html):
+ return get_element_by_attribute(
+ 'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
+ html, escape_value=False)
+
+
+def get_element_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()
+
+ value = re.escape(value) if escape_value else value
+
+ m = re.search(r'''(?xs)
+ <([a-zA-Z0-9:._-]+)
+ (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
+ \s+%s=['"]?%s['"]?
+ (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
+ \s*>
+ (?P<content>.*?)
+ </\1>
+ ''' % (re.escape(attribute), value), html)
+
+ if not m:
+ return None
+ res = m.group('content')
+
+ if res.startswith('"') or res.startswith("'"):
+ res = res[1:-1]
+
+ return unescapeHTML(res)
+
+
+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
+ <el
+ a="foo" B="bar" c="&98;az" d=boz
+ empty= noval entity="&"
+ sq='"' dq="'"
+ >
+ 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 = HTMLAttributeParser()
+ parser.feed(html_element)
+ parser.close()
+ 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 <br />
html = html.replace('\n', ' ')
html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
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)
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)
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
"""
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 == '"':
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('__', '_')
# 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)
+
+
+# Prepend protocol-less URLs with `http:` scheme in order to mitigate the number of
+# unwanted failures due to missing protocol
+def sanitize_url(url):
+ return 'http:%s' % url if url.startswith('//') else url
+
+
+def sanitized_Request(url, *args, **kwargs):
+ return compat_urllib_request.Request(sanitize_url(url), *args, **kwargs)
+
+
def orderedSet(iterable):
""" Remove all duplicates from the input iterable """
res = []
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 'Éric'.
+ 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/rg3/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:
assert isinstance(optval, compat_str)
return optval
+
def formatSeconds(secs):
if secs > 3600:
return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
else:
return '%d' % secs
-def make_HTTPS_handler(opts):
- if sys.version_info < (3,2):
- # Python's 2.x handler is very simplistic
- return compat_urllib_request.HTTPSHandler()
- else:
- import ssl
- context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
- context.set_default_verify_paths()
-
+
+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
+
+ 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
+ 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 ExtractorError(Exception):
"""Error during info extraction."""
- def __init__(self, msg, tb=None):
- """ tb, if given, is the original traceback (so that it can be printed out). """
+
+ 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 += 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):
+ """Error when a regex didn't match"""
+ pass
class DownloadError(Exception):
configured to continue on errors. They will contain the appropriate
error message.
"""
+
def __init__(self, msg, exc_info=None):
""" exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
super(DownloadError, self).__init__(msg)
This exception may be raised by PostProcessor's .run() method to
indicate an error in the postprocessing task.
"""
+
def __init__(self, msg):
self.msg = msg
+
class MaxDownloadsReached(Exception):
""" --max-downloads limit has been reached. """
pass
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):
+ # Both in bytes
self.downloaded = downloaded
self.expected = expected
+
+class XAttrMetadataError(Exception):
+ 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(Exception):
+ 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/rg3/youtube-dl/issues/6727)
+ if sys.version_info < (3, 0):
+ kwargs[b'strict'] = True
+ hc = http_class(*args, **kwargs)
+ source_address = ydl_handler._params.get('source_address')
+ if source_address is not None:
+ 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 = compat_socket_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.
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:
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:
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):
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
- gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
- resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
+ content = resp.read()
+ gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
+ try:
+ uncompressed = io.BytesIO(gz.read())
+ except IOError as original_ioerror:
+ # There may be junk add the end of the file
+ # See http://stackoverflow.com/q/4928560/35070 for details
+ for i in range(1, 1024):
+ try:
+ gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
+ uncompressed = io.BytesIO(gz.read())
+ except IOError:
+ continue
+ break
+ else:
+ raise original_ioerror
+ resp = self.addinfourl_wrapper(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.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/rg3/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 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/rg3/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"%/;:@&=+$,!~*'()?#[] ")
+ # if set_cookie != set_cookie_escaped:
+ # del response.headers[set_cookie_header]
+ # response.headers[set_cookie_header] = set_cookie_escaped
+ return compat_urllib_request.HTTPCookieProcessor.http_response(self, request, response)
+
+ https_request = compat_urllib_request.HTTPCookieProcessor.http_request
+ https_response = http_response
+
+
+def extract_timezone(date_str):
+ m = re.search(
+ r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[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']
- 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 = date_str.replace(',', ' ')
+
+ 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)
+
+ 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:
+ return default_ext
+ guess = url.partition('?')[0].rpartition('.')[2]
+ if re.match(r'^[A-Za-z0-9]+$', guess):
+ return guess
+ # Try extract ext from URLs like http://example.com/foo/bar.mp4/?download
+ elif guess.rstrip('/') in KNOWN_EXTENSIONS:
+ return guess.rstrip('/')
+ else:
+ return default_ext
+
+
+def subtitles_filename(filename, sub_lang, sub_format):
+ return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format
+
def date_from_str(date_str):
"""
Return a datetime object from a string in the format YYYYMMDD or
(now|today)[+-][0-9](day|week|month|year)(s)?"""
today = datetime.date.today()
- if date_str == 'now'or date_str == 'today':
+ if date_str in ('now', 'today'):
return today
- match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
+ if date_str == 'yesterday':
+ return today - datetime.timedelta(days=1)
+ match = re.match(r'(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
if match is not None:
sign = match.group('sign')
time = int(match.group('time'))
if sign == '-':
time = -time
unit = match.group('unit')
- #A bad aproximation?
+ # A bad approximation?
if unit == 'month':
unit = 'day'
time *= 30
unit += 's'
delta = datetime.timedelta(**{unit: time})
return today + delta
- return datetime.datetime.strptime(date_str, "%Y%m%d").date()
-
+ return datetime.datetime.strptime(date_str, '%Y%m%d').date()
+
+
+def hyphenate_date(date_str):
+ """
+ Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
+ match = re.match(r'^(\d\d\d\d)(\d\d)(\d\d)$', date_str)
+ if match is not None:
+ return '-'.join(match.groups())
+ else:
+ return date_str
+
+
class DateRange(object):
"""Represents a time interval between two dates"""
+
def __init__(self, start=None, end=None):
"""start and end must be strings in the format accepted by date"""
if start is not None:
self.end = datetime.datetime.max.date()
if self.start > self.end:
raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
+
@classmethod
def day(cls, day):
"""Returns a range that only contains the given day"""
- return cls(day,day)
+ return cls(day, day)
+
def __contains__(self, date):
"""Check if the date is in the range"""
if not isinstance(date, datetime.date):
date = date_from_str(date)
return self.start <= date <= self.end
+
def __str__(self):
- return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())
+ return '%s - %s' % (self.start.isoformat(), self.end.isoformat())
+
+
+def platform_name():
+ """ Returns the platform name as a compat_str """
+ res = platform.platform()
+ if isinstance(res, bytes):
+ res = res.decode(preferredencoding())
+
+ assert isinstance(res, compat_str)
+ return res
+
+
+def _windows_write_string(s, out):
+ """ Returns True if the string was written using special methods,
+ False if it has yet to be written out."""
+ # Adapted from http://stackoverflow.com/a/3259271/35070
+
+ import ctypes
+ import ctypes.wintypes
+
+ WIN_OUTPUT_IDS = {
+ 1: -11,
+ 2: -12,
+ }
+
+ try:
+ fileno = out.fileno()
+ except AttributeError:
+ # If the output stream doesn't have a fileno, it's virtual
+ return False
+ except io.UnsupportedOperation:
+ # Some strange Windows pseudo files?
+ return False
+ if fileno not in WIN_OUTPUT_IDS:
+ return False
+
+ GetStdHandle = ctypes.WINFUNCTYPE(
+ ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)(
+ (b'GetStdHandle', ctypes.windll.kernel32))
+ h = GetStdHandle(WIN_OUTPUT_IDS[fileno])
+
+ WriteConsoleW = ctypes.WINFUNCTYPE(
+ ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR,
+ ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD),
+ ctypes.wintypes.LPVOID)((b'WriteConsoleW', ctypes.windll.kernel32))
+ written = ctypes.wintypes.DWORD(0)
+
+ GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)((b'GetFileType', ctypes.windll.kernel32))
+ FILE_TYPE_CHAR = 0x0002
+ FILE_TYPE_REMOTE = 0x8000
+ GetConsoleMode = ctypes.WINFUNCTYPE(
+ ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE,
+ ctypes.POINTER(ctypes.wintypes.DWORD))(
+ (b'GetConsoleMode', ctypes.windll.kernel32))
+ INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value
+
+ def not_a_console(handle):
+ if handle == INVALID_HANDLE_VALUE or handle is None:
+ return True
+ return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR or
+ GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
+
+ if not_a_console(h):
+ return False
+
+ def next_nonbmp_pos(s):
+ try:
+ return next(i for i, c in enumerate(s) if ord(c) > 0xffff)
+ except StopIteration:
+ return len(s)
+
+ while s:
+ count = min(next_nonbmp_pos(s), 1024)
+
+ ret = WriteConsoleW(
+ h, s, count if count else 2, ctypes.byref(written), None)
+ if ret == 0:
+ raise OSError('Failed to write string')
+ if not count: # We just wrote a non-BMP character
+ assert written.value == 2
+ s = s[1:]
+ else:
+ assert written.value > 0
+ s = s[written.value:]
+ return True
+
+
+def write_string(s, out=None, encoding=None):
+ if out is None:
+ out = sys.stderr
+ assert type(s) == compat_str
+
+ if sys.platform == 'win32' and encoding is None and hasattr(out, 'fileno'):
+ if _windows_write_string(s, out):
+ return
+
+ if ('b' in getattr(out, 'mode', '') or
+ sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
+ byt = s.encode(encoding or preferredencoding(), 'ignore')
+ out.write(byt)
+ elif hasattr(out, 'buffer'):
+ enc = encoding or getattr(out, 'encoding', None) or preferredencoding()
+ byt = s.encode(enc, 'ignore')
+ out.buffer.write(byt)
+ else:
+ out.write(s)
+ out.flush()
+
+
+def bytes_to_intlist(bs):
+ if not bs:
+ return []
+ if isinstance(bs[0], int): # Python 3
+ return list(bs)
+ else:
+ return [ord(c) for c in bs]
+
+
+def intlist_to_bytes(xs):
+ if not xs:
+ return b''
+ return compat_struct_pack('%dB' % len(xs), *xs)
+
+
+# Cross-platform file locking
+if sys.platform == 'win32':
+ import ctypes.wintypes
+ import msvcrt
+
+ class OVERLAPPED(ctypes.Structure):
+ _fields_ = [
+ ('Internal', ctypes.wintypes.LPVOID),
+ ('InternalHigh', ctypes.wintypes.LPVOID),
+ ('Offset', ctypes.wintypes.DWORD),
+ ('OffsetHigh', ctypes.wintypes.DWORD),
+ ('hEvent', ctypes.wintypes.HANDLE),
+ ]
+
+ kernel32 = ctypes.windll.kernel32
+ LockFileEx = kernel32.LockFileEx
+ LockFileEx.argtypes = [
+ ctypes.wintypes.HANDLE, # hFile
+ ctypes.wintypes.DWORD, # dwFlags
+ ctypes.wintypes.DWORD, # dwReserved
+ ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
+ ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
+ ctypes.POINTER(OVERLAPPED) # Overlapped
+ ]
+ LockFileEx.restype = ctypes.wintypes.BOOL
+ UnlockFileEx = kernel32.UnlockFileEx
+ UnlockFileEx.argtypes = [
+ ctypes.wintypes.HANDLE, # hFile
+ ctypes.wintypes.DWORD, # dwReserved
+ ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
+ ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
+ ctypes.POINTER(OVERLAPPED) # Overlapped
+ ]
+ UnlockFileEx.restype = ctypes.wintypes.BOOL
+ whole_low = 0xffffffff
+ whole_high = 0x7fffffff
+
+ def _lock_file(f, exclusive):
+ overlapped = OVERLAPPED()
+ overlapped.Offset = 0
+ overlapped.OffsetHigh = 0
+ overlapped.hEvent = 0
+ f._lock_file_overlapped_p = ctypes.pointer(overlapped)
+ handle = msvcrt.get_osfhandle(f.fileno())
+ if not LockFileEx(handle, 0x2 if exclusive else 0x0, 0,
+ whole_low, whole_high, f._lock_file_overlapped_p):
+ raise OSError('Locking file failed: %r' % ctypes.FormatError())
+
+ def _unlock_file(f):
+ assert f._lock_file_overlapped_p
+ handle = msvcrt.get_osfhandle(f.fileno())
+ if not UnlockFileEx(handle, 0,
+ whole_low, whole_high, f._lock_file_overlapped_p):
+ raise OSError('Unlocking file failed: %r' % ctypes.FormatError())
+
+else:
+ # Some platforms, such as Jython, is missing fcntl
+ try:
+ import fcntl
+
+ def _lock_file(f, exclusive):
+ fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)
+
+ def _unlock_file(f):
+ fcntl.flock(f, fcntl.LOCK_UN)
+ except ImportError:
+ UNSUPPORTED_MSG = 'file locking is not supported on this platform'
+
+ def _lock_file(f, exclusive):
+ raise IOError(UNSUPPORTED_MSG)
+
+ def _unlock_file(f):
+ raise IOError(UNSUPPORTED_MSG)
+
+
+class locked_file(object):
+ def __init__(self, filename, mode, encoding=None):
+ assert mode in ['r', 'a', 'w']
+ self.f = io.open(filename, mode, encoding=encoding)
+ self.mode = mode
+
+ def __enter__(self):
+ exclusive = self.mode != 'r'
+ try:
+ _lock_file(self.f, exclusive)
+ except IOError:
+ self.f.close()
+ raise
+ return self
+
+ def __exit__(self, etype, value, traceback):
+ try:
+ _unlock_file(self.f)
+ finally:
+ self.f.close()
+
+ def __iter__(self):
+ return iter(self.f)
+
+ def write(self, *args):
+ return self.f.write(*args)
+
+ def read(self, *args):
+ return self.f.read(*args)
+
+
+def get_filesystem_encoding():
+ encoding = sys.getfilesystemencoding()
+ return encoding if encoding is not None else 'utf-8'
+
+
+def shell_quote(args):
+ quoted_args = []
+ encoding = get_filesystem_encoding()
+ for a in args:
+ if isinstance(a, bytes):
+ # We may get a filename encoded with 'encodeFilename'
+ a = a.decode(encoding)
+ quoted_args.append(pipes.quote(a))
+ return ' '.join(quoted_args)
+
+
+def smuggle_url(url, data):
+ """ Pass additional data in a URL for internal use. """
+
+ url, idata = unsmuggle_url(url, {})
+ data.update(idata)
+ sdata = compat_urllib_parse_urlencode(
+ {'__youtubedl_smuggle': json.dumps(data)})
+ return url + '#' + sdata
+
+
+def unsmuggle_url(smug_url, default=None):
+ if '#__youtubedl_smuggle' not in smug_url:
+ return smug_url, default
+ url, _, sdata = smug_url.rpartition('#')
+ jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0]
+ data = json.loads(jsond)
+ return url, data
+
+
+def format_bytes(bytes):
+ if bytes is None:
+ return 'N/A'
+ if type(bytes) is str:
+ bytes = float(bytes)
+ if bytes == 0.0:
+ exponent = 0
+ else:
+ exponent = int(math.log(bytes, 1024.0))
+ suffix = ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB'][exponent]
+ converted = float(bytes) / float(1024 ** exponent)
+ return '%.2f%s' % (converted, suffix)
+
+
+def lookup_unit_table(unit_table, s):
+ units_re = '|'.join(re.escape(u) for u in unit_table)
+ m = re.match(
+ r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)\b' % units_re, s)
+ if not m:
+ return None
+ num_str = m.group('num').replace(',', '.')
+ mult = unit_table[m.group('unit')]
+ return int(float(num_str) * mult)
+
+
+def parse_filesize(s):
+ if s is None:
+ return None
+
+ # The lower-case forms are of course incorrect and unofficial,
+ # but we support those too
+ _UNIT_TABLE = {
+ 'B': 1,
+ 'b': 1,
+ 'bytes': 1,
+ 'KiB': 1024,
+ 'KB': 1000,
+ 'kB': 1024,
+ 'Kb': 1000,
+ 'kb': 1000,
+ 'kilobytes': 1000,
+ 'kibibytes': 1024,
+ 'MiB': 1024 ** 2,
+ 'MB': 1000 ** 2,
+ 'mB': 1024 ** 2,
+ 'Mb': 1000 ** 2,
+ 'mb': 1000 ** 2,
+ 'megabytes': 1000 ** 2,
+ 'mebibytes': 1024 ** 2,
+ 'GiB': 1024 ** 3,
+ 'GB': 1000 ** 3,
+ 'gB': 1024 ** 3,
+ 'Gb': 1000 ** 3,
+ 'gb': 1000 ** 3,
+ 'gigabytes': 1000 ** 3,
+ 'gibibytes': 1024 ** 3,
+ 'TiB': 1024 ** 4,
+ 'TB': 1000 ** 4,
+ 'tB': 1024 ** 4,
+ 'Tb': 1000 ** 4,
+ 'tb': 1000 ** 4,
+ 'terabytes': 1000 ** 4,
+ 'tebibytes': 1024 ** 4,
+ 'PiB': 1024 ** 5,
+ 'PB': 1000 ** 5,
+ 'pB': 1024 ** 5,
+ 'Pb': 1000 ** 5,
+ 'pb': 1000 ** 5,
+ 'petabytes': 1000 ** 5,
+ 'pebibytes': 1024 ** 5,
+ 'EiB': 1024 ** 6,
+ 'EB': 1000 ** 6,
+ 'eB': 1024 ** 6,
+ 'Eb': 1000 ** 6,
+ 'eb': 1000 ** 6,
+ 'exabytes': 1000 ** 6,
+ 'exbibytes': 1024 ** 6,
+ 'ZiB': 1024 ** 7,
+ 'ZB': 1000 ** 7,
+ 'zB': 1024 ** 7,
+ 'Zb': 1000 ** 7,
+ 'zb': 1000 ** 7,
+ 'zettabytes': 1000 ** 7,
+ 'zebibytes': 1024 ** 7,
+ 'YiB': 1024 ** 8,
+ 'YB': 1000 ** 8,
+ 'yB': 1024 ** 8,
+ 'Yb': 1000 ** 8,
+ 'yb': 1000 ** 8,
+ 'yottabytes': 1000 ** 8,
+ 'yobibytes': 1024 ** 8,
+ }
+
+ return lookup_unit_table(_UNIT_TABLE, s)
+
+
+def parse_count(s):
+ if s is None:
+ return None
+
+ s = s.strip()
+
+ if re.match(r'^[\d,.]+$', s):
+ return str_to_int(s)
+
+ _UNIT_TABLE = {
+ 'k': 1000,
+ 'K': 1000,
+ 'm': 1000 ** 2,
+ 'M': 1000 ** 2,
+ 'kk': 1000 ** 2,
+ 'KK': 1000 ** 2,
+ }
+
+ return lookup_unit_table(_UNIT_TABLE, s)
+
+
+def month_by_name(name, lang='en'):
+ """ Return the number of a month by (locale-independently) English name """
+
+ month_names = MONTH_NAMES.get(lang, MONTH_NAMES['en'])
+
+ try:
+ return month_names.index(name) + 1
+ except ValueError:
+ return None
+
+
+def month_by_abbreviation(abbrev):
+ """ Return the number of a month by (locale-independently) English
+ abbreviations """
+
+ try:
+ return [s[:3] for s in ENGLISH_MONTH_NAMES].index(abbrev) + 1
+ except ValueError:
+ return None
+
+
+def fix_xml_ampersands(xml_str):
+ """Replace all the '&' by '&' in XML"""
+ return re.sub(
+ r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
+ '&',
+ xml_str)
+
+
+def setproctitle(title):
+ assert isinstance(title, compat_str)
+
+ # ctypes in Jython is not complete
+ # http://bugs.jython.org/issue2148
+ if sys.platform.startswith('java'):
+ return
+
+ try:
+ libc = ctypes.cdll.LoadLibrary('libc.so.6')
+ except OSError:
+ return
+ title_bytes = title.encode('utf-8')
+ buf = ctypes.create_string_buffer(len(title_bytes))
+ buf.value = title_bytes
+ try:
+ libc.prctl(15, buf, 0, 0, 0)
+ except AttributeError:
+ return # Strange libc, just skip this
+
+
+def remove_start(s, start):
+ return s[len(start):] if s is not None and s.startswith(start) else s
+
+
+def remove_end(s, end):
+ return s[:-len(end)] if s is not None and s.endswith(end) else s
+
+
+def remove_quotes(s):
+ if s is None or len(s) < 2:
+ return s
+ for quote in ('"', "'", ):
+ if s[0] == quote and s[-1] == quote:
+ return s[1:-1]
+ return s
+
+
+def url_basename(url):
+ path = compat_urlparse.urlparse(url).path
+ return path.strip('/').split('/')[-1]
+
+
+def base_url(url):
+ return re.match(r'https?://[^?#&]+/', url).group()
+
+
+def urljoin(base, path):
+ if not isinstance(path, compat_str) or not path:
+ return None
+ if re.match(r'^(?:https?:)?//', path):
+ return path
+ if not isinstance(base, compat_str) or not re.match(r'^(?:https?:)?//', base):
+ return None
+ return compat_urlparse.urljoin(base, path)
+
+
+class HEADRequest(compat_urllib_request.Request):
+ def get_method(self):
+ return 'HEAD'
+
+
+class PUTRequest(compat_urllib_request.Request):
+ def get_method(self):
+ return 'PUT'
+
+
+def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
+ if get_attr:
+ if v is not None:
+ v = getattr(v, get_attr, None)
+ if v == '':
+ v = None
+ if v is None:
+ return default
+ try:
+ return int(v) * invscale // scale
+ except ValueError:
+ return default
+
+
+def str_or_none(v, default=None):
+ return default if v is None else compat_str(v)
+
+
+def str_to_int(int_str):
+ """ A more relaxed version of int_or_none """
+ if int_str is None:
+ return None
+ int_str = re.sub(r'[,\.\+]', '', int_str)
+ return int(int_str)
+
+
+def float_or_none(v, scale=1, invscale=1, default=None):
+ if v is None:
+ return default
+ try:
+ return float(v) * invscale / scale
+ except ValueError:
+ return default
+
+
+def strip_or_none(v):
+ return None if v is None else v.strip()
+
+
+def parse_duration(s):
+ if not isinstance(s, compat_basestring):
+ return None
+
+ s = s.strip()
+
+ days, hours, mins, secs, ms = [None] * 5
+ m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?Z?$', s)
+ if m:
+ days, hours, mins, secs, ms = m.groups()
+ else:
+ m = re.match(
+ r'''(?ix)(?:P?T)?
+ (?:
+ (?P<days>[0-9]+)\s*d(?:ays?)?\s*
+ )?
+ (?:
+ (?P<hours>[0-9]+)\s*h(?:ours?)?\s*
+ )?
+ (?:
+ (?P<mins>[0-9]+)\s*m(?:in(?:ute)?s?)?\s*
+ )?
+ (?:
+ (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
+ )?Z?$''', s)
+ if m:
+ days, hours, mins, secs, ms = m.groups()
+ else:
+ m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)Z?$', s)
+ if m:
+ hours, mins = m.groups()
+ else:
+ return None
+
+ duration = 0
+ if secs:
+ duration += float(secs)
+ if mins:
+ duration += float(mins) * 60
+ if hours:
+ duration += float(hours) * 60 * 60
+ if days:
+ duration += float(days) * 24 * 60 * 60
+ if ms:
+ duration += float(ms)
+ return duration
+
+
+def prepend_extension(filename, ext, expected_real_ext=None):
+ name, real_ext = os.path.splitext(filename)
+ return (
+ '{0}.{1}{2}'.format(name, ext, real_ext)
+ if not expected_real_ext or real_ext[1:] == expected_real_ext
+ else '{0}.{1}'.format(filename, ext))
+
+
+def replace_extension(filename, ext, expected_real_ext=None):
+ name, real_ext = os.path.splitext(filename)
+ return '{0}.{1}'.format(
+ name if not expected_real_ext or real_ext[1:] == expected_real_ext else filename,
+ ext)
+
+
+def check_executable(exe, args=[]):
+ """ Checks if the given binary is installed somewhere in PATH, and returns its name.
+ args can be a list of arguments for a short output (like -version) """
+ try:
+ subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
+ except OSError:
+ return False
+ return exe
+
+
+def get_exe_version(exe, args=['--version'],
+ version_re=None, unrecognized='present'):
+ """ Returns the version of the specified executable,
+ or False if the executable is not present """
+ try:
+ # STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers
+ # SIGTTOU if youtube-dl is run in the background.
+ # See https://github.com/rg3/youtube-dl/issues/955#issuecomment-209789656
+ out, _ = subprocess.Popen(
+ [encodeArgument(exe)] + args,
+ stdin=subprocess.PIPE,
+ stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
+ except OSError:
+ return False
+ if isinstance(out, bytes): # Python 2.x
+ out = out.decode('ascii', 'ignore')
+ return detect_exe_version(out, version_re, unrecognized)
+
+
+def detect_exe_version(output, version_re=None, unrecognized='present'):
+ assert isinstance(output, compat_str)
+ if version_re is None:
+ version_re = r'version\s+([-0-9._a-zA-Z]+)'
+ m = re.search(version_re, output)
+ if m:
+ return m.group(1)
+ else:
+ return unrecognized
+
+
+class PagedList(object):
+ def __len__(self):
+ # This is only useful for tests
+ return len(self.getslice())
+
+
+class OnDemandPagedList(PagedList):
+ def __init__(self, pagefunc, pagesize, use_cache=False):
+ self._pagefunc = pagefunc
+ self._pagesize = pagesize
+ self._use_cache = use_cache
+ if use_cache:
+ self._cache = {}
+
+ def getslice(self, start=0, end=None):
+ res = []
+ for pagenum in itertools.count(start // self._pagesize):
+ firstid = pagenum * self._pagesize
+ nextfirstid = pagenum * self._pagesize + self._pagesize
+ if start >= nextfirstid:
+ continue
+
+ page_results = None
+ if self._use_cache:
+ page_results = self._cache.get(pagenum)
+ if page_results is None:
+ page_results = list(self._pagefunc(pagenum))
+ if self._use_cache:
+ self._cache[pagenum] = page_results
+
+ startv = (
+ start % self._pagesize
+ if firstid <= start < nextfirstid
+ else 0)
+
+ endv = (
+ ((end - 1) % self._pagesize) + 1
+ if (end is not None and firstid <= end <= nextfirstid)
+ else None)
+
+ if startv != 0 or endv is not None:
+ page_results = page_results[startv:endv]
+ res.extend(page_results)
+
+ # A little optimization - if current page is not "full", ie. does
+ # not contain page_size videos then we can assume that this page
+ # is the last one - there are no more ids on further pages -
+ # i.e. no need to query again.
+ if len(page_results) + startv < self._pagesize:
+ break
+
+ # If we got the whole page, but the next page is not interesting,
+ # break out early as well
+ if end == nextfirstid:
+ break
+ return res
+
+
+class InAdvancePagedList(PagedList):
+ def __init__(self, pagefunc, pagecount, pagesize):
+ self._pagefunc = pagefunc
+ self._pagecount = pagecount
+ self._pagesize = pagesize
+
+ def getslice(self, start=0, end=None):
+ res = []
+ start_page = start // self._pagesize
+ end_page = (
+ self._pagecount if end is None else (end // self._pagesize + 1))
+ skip_elems = start - start_page * self._pagesize
+ only_more = None if end is None else end - start
+ for pagenum in range(start_page, end_page):
+ page = list(self._pagefunc(pagenum))
+ if skip_elems:
+ page = page[skip_elems:]
+ skip_elems = None
+ if only_more is not None:
+ if len(page) < only_more:
+ only_more -= len(page)
+ else:
+ page = page[:only_more]
+ res.extend(page)
+ break
+ res.extend(page)
+ return res
+
+
+def uppercase_escape(s):
+ unicode_escape = codecs.getdecoder('unicode_escape')
+ return re.sub(
+ 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 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):
+ try:
+ v = getter(src)
+ except (AttributeError, KeyError, TypeError, IndexError):
+ pass
+ else:
+ if expected_type is None or isinstance(v, expected_type):
+ return v
+
+
+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]
+ return TV_PARENTAL_GUIDELINES.get(s)
+
+
+def strip_jsonp(code):
+ return re.sub(
+ r'(?s)^[a-zA-Z0-9_.$]+\s*\(\s*(.*)\);?\s*?(?://[^\n]*)*$', r'\1', code)
+
+
+def js_to_json(code):
+ COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*'
+ SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE)
+ INTEGER_TABLE = (
+ (r'(?s)^(0[xX][0-9a-fA-F]+){skip}:?$'.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}[\]}}])|
+ [a-zA-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',
+ 'srt': 'srt',
+ 'ttaf+xml': 'dfxp',
+ 'ttml+xml': 'ttml',
+ 'vtt': 'vtt',
+ 'x-flv': 'flv',
+ 'x-mp4-fragmented': 'mp4',
+ 'x-ms-wmv': 'wmv',
+ 'mpegurl': 'm3u8',
+ 'x-mpegurl': 'm3u8',
+ 'vnd.apple.mpegurl': 'm3u8',
+ 'dash+xml': 'mpd',
+ 'f4m': 'f4m',
+ 'f4m+xml': 'f4m',
+ 'hds+xml': 'f4m',
+ 'vnd.ms-sstr+xml': 'ism',
+ 'quicktime': 'mov',
+ }.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'):
+ if not vcodec:
+ vcodec = full_codec
+ elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3'):
+ if not acodec:
+ acodec = full_codec
+ else:
+ write_string('WARNING: Unknown codec %s' % 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<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('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('strval') or m.group('intval')
+ 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 not None,
+ '!': lambda v: 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):
+ _x = functools.partial(xpath_with_ns, ns_map={
+ 'ttml': 'http://www.w3.org/ns/ttml',
+ 'ttaf1': 'http://www.w3.org/2006/10/ttaf1',
+ 'ttaf1_0604': 'http://www.w3.org/2006/04/ttaf1',
+ })
+
+ class TTMLPElementParser(object):
+ out = ''
+
+ def start(self, tag, attrib):
+ if tag in (_x('ttml:br'), _x('ttaf1:br'), 'br'):
+ self.out += '\n'
+
+ def end(self, tag):
+ pass
+
+ 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()
+
+ dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
+ out = []
+ paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall(_x('.//ttaf1_0604:p')) or dfxp.findall('.//p')
+
+ if not paras:
+ raise ValueError('Invalid dfxp/TTML subtitle')
+
+ 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)
+ 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 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)
+
+
+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 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.")
Rapsys Git / youtubedl / blobdiff