import random
import re
import shutil
+import string
import subprocess
import sys
import tempfile
import traceback
import unicodedata
import urllib.request
-from string import Formatter, ascii_letters
from .cache import Cache
from .compat import compat_os_name, compat_shlex_quote
parse_filesize,
preferredencoding,
prepend_extension,
- register_socks_protocols,
remove_terminal_sequences,
render_table,
replace_extension,
ap_username: Multiple-system operator account username.
ap_password: Multiple-system operator account password.
usenetrc: Use netrc for authentication instead.
+ netrc_location: Location of the netrc file. Defaults to ~/.netrc.
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
no_warnings: Do not print out anything for warnings.
when=when)
self._setup_opener()
- register_socks_protocols()
def preload_download_archive(fn):
"""Preload the archive, if any is specified"""
# correspondingly that is not what we want since we need to keep
# '%%' intact for template dict substitution step. Working around
# with boundary-alike separator hack.
- sep = ''.join(random.choices(ascii_letters, k=32))
+ sep = ''.join(random.choices(string.ascii_letters, k=32))
outtmpl = outtmpl.replace('%%', f'%{sep}%').replace('$$', f'${sep}$')
# outtmpl should be expand_path'ed before template dict substitution
return list(obj)
return repr(obj)
- class _ReplacementFormatter(Formatter):
+ class _ReplacementFormatter(string.Formatter):
def get_field(self, field_name, args, kwargs):
if field_name.isdigit():
return args[0], -1
self.add_extra_info(info_copy, extra_info)
info_copy, _ = self.pre_process(info_copy)
self._fill_common_fields(info_copy, False)
- self.__forced_printings(info_copy, self.prepare_filename(info_copy), incomplete=True)
+ self.__forced_printings(info_copy)
self._raise_pending_errors(info_copy)
if self.params.get('force_write_download_archive', False):
self.record_download_archive(info_copy)
def _parse_filter(tokens):
filter_parts = []
- for type, string, start, _, _ in tokens:
- if type == tokenize.OP and string == ']':
+ for type, string_, start, _, _ in tokens:
+ if type == tokenize.OP and string_ == ']':
return ''.join(filter_parts)
else:
- filter_parts.append(string)
+ filter_parts.append(string_)
def _remove_unused_ops(tokens):
# Remove operators that we don't use and join them with the surrounding strings.
# E.g. 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
ALLOWED_OPS = ('/', '+', ',', '(', ')')
last_string, last_start, last_end, last_line = None, None, None, None
- for type, string, start, end, line in tokens:
- if type == tokenize.OP and string == '[':
+ for type, string_, start, end, line in tokens:
+ if type == tokenize.OP and string_ == '[':
if last_string:
yield tokenize.NAME, last_string, last_start, last_end, last_line
last_string = None
- yield type, string, start, end, line
+ yield type, string_, start, end, line
# everything inside brackets will be handled by _parse_filter
- for type, string, start, end, line in tokens:
- yield type, string, start, end, line
- if type == tokenize.OP and string == ']':
+ for type, string_, start, end, line in tokens:
+ yield type, string_, start, end, line
+ if type == tokenize.OP and string_ == ']':
break
- elif type == tokenize.OP and string in ALLOWED_OPS:
+ elif type == tokenize.OP and string_ in ALLOWED_OPS:
if last_string:
yield tokenize.NAME, last_string, last_start, last_end, last_line
last_string = None
- yield type, string, start, end, line
+ yield type, string_, start, end, line
elif type in [tokenize.NAME, tokenize.NUMBER, tokenize.OP]:
if not last_string:
- last_string = string
+ last_string = string_
last_start = start
last_end = end
else:
- last_string += string
+ last_string += string_
if last_string:
yield tokenize.NAME, last_string, last_start, last_end, last_line
def _parse_format_selection(tokens, inside_merge=False, inside_choice=False, inside_group=False):
selectors = []
current_selector = None
- for type, string, start, _, _ in tokens:
+ for type, string_, start, _, _ in tokens:
# ENCODING is only defined in python 3.x
if type == getattr(tokenize, 'ENCODING', None):
continue
elif type in [tokenize.NAME, tokenize.NUMBER]:
- current_selector = FormatSelector(SINGLE, string, [])
+ current_selector = FormatSelector(SINGLE, string_, [])
elif type == tokenize.OP:
- if string == ')':
+ if string_ == ')':
if not inside_group:
# ')' will be handled by the parentheses group
tokens.restore_last_token()
break
- elif inside_merge and string in ['/', ',']:
+ elif inside_merge and string_ in ['/', ',']:
tokens.restore_last_token()
break
- elif inside_choice and string == ',':
+ elif inside_choice and string_ == ',':
tokens.restore_last_token()
break
- elif string == ',':
+ elif string_ == ',':
if not current_selector:
raise syntax_error('"," must follow a format selector', start)
selectors.append(current_selector)
current_selector = None
- elif string == '/':
+ elif string_ == '/':
if not current_selector:
raise syntax_error('"/" must follow a format selector', start)
first_choice = current_selector
second_choice = _parse_format_selection(tokens, inside_choice=True)
current_selector = FormatSelector(PICKFIRST, (first_choice, second_choice), [])
- elif string == '[':
+ elif string_ == '[':
if not current_selector:
current_selector = FormatSelector(SINGLE, 'best', [])
format_filter = _parse_filter(tokens)
current_selector.filters.append(format_filter)
- elif string == '(':
+ elif string_ == '(':
if current_selector:
raise syntax_error('Unexpected "("', start)
group = _parse_format_selection(tokens, inside_group=True)
current_selector = FormatSelector(GROUP, group, [])
- elif string == '+':
+ elif string_ == '+':
if not current_selector:
raise syntax_error('Unexpected "+"', start)
selector_1 = current_selector
raise syntax_error('Expected a selector', start)
current_selector = FormatSelector(MERGE, (selector_1, selector_2), [])
else:
- raise syntax_error(f'Operator not recognized: "{string}"', start)
+ raise syntax_error(f'Operator not recognized: "{string_}"', start)
elif type == tokenize.ENDMARKER:
break
if current_selector:
self.list_formats(info_dict)
if list_only:
# Without this printing, -F --print-json will not work
- self.__forced_printings(info_dict, self.prepare_filename(info_dict), incomplete=True)
+ self.__forced_printings(info_dict)
return info_dict
format_selector = self.format_selector
if info_dict is None:
return
info_copy = info_dict.copy()
+ info_copy.setdefault('filename', self.prepare_filename(info_dict))
+ if info_dict.get('requested_formats') is not None:
+ # For RTMP URLs, also include the playpath
+ info_copy['urls'] = '\n'.join(f['url'] + f.get('play_path', '') for f in info_dict['requested_formats'])
+ elif info_dict.get('url'):
+ info_copy['urls'] = info_dict['url'] + info_dict.get('play_path', '')
info_copy['formats_table'] = self.render_formats_table(info_dict)
info_copy['thumbnails_table'] = self.render_thumbnails_table(info_dict)
info_copy['subtitles_table'] = self.render_subtitles_table(info_dict.get('id'), info_dict.get('subtitles'))
fmt = '%({})s'
if tmpl.startswith('{'):
- tmpl = f'.{tmpl}'
+ tmpl, fmt = f'.{tmpl}', '%({})j'
if tmpl.endswith('='):
tmpl, fmt = tmpl[:-1], '{0} = %({0})#j'
return '\n'.join(map(fmt.format, [tmpl] if mobj.group('dict') else tmpl.split(',')))
with open(filename, 'a', encoding='utf-8', newline='') as f:
f.write(self.evaluate_outtmpl(tmpl, info_copy) + os.linesep)
- def __forced_printings(self, info_dict, filename, incomplete):
- def print_mandatory(field, actual_field=None):
- if actual_field is None:
- actual_field = field
- if (self.params.get('force%s' % field, False)
- and (not incomplete or info_dict.get(actual_field) is not None)):
- self.to_stdout(info_dict[actual_field])
-
- def print_optional(field):
- if (self.params.get('force%s' % field, False)
- and info_dict.get(field) is not None):
- self.to_stdout(info_dict[field])
-
- info_dict = info_dict.copy()
- if filename is not None:
- info_dict['filename'] = filename
- if info_dict.get('requested_formats') is not None:
- # For RTMP URLs, also include the playpath
- info_dict['urls'] = '\n'.join(f['url'] + f.get('play_path', '') for f in info_dict['requested_formats'])
- elif info_dict.get('url'):
- info_dict['urls'] = info_dict['url'] + info_dict.get('play_path', '')
+ return info_copy
+ def __forced_printings(self, info_dict, filename=None, incomplete=True):
if (self.params.get('forcejson')
or self.params['forceprint'].get('video')
or self.params['print_to_file'].get('video')):
self.post_extract(info_dict)
- self._forceprint('video', info_dict)
-
- print_mandatory('title')
- print_mandatory('id')
- print_mandatory('url', 'urls')
- print_optional('thumbnail')
- print_optional('description')
- print_optional('filename')
- if self.params.get('forceduration') and info_dict.get('duration') is not None:
- self.to_stdout(formatSeconds(info_dict['duration']))
- print_mandatory('format')
+ if filename:
+ info_dict['filename'] = filename
+ info_copy = self._forceprint('video', info_dict)
+
+ def print_field(field, actual_field=None, optional=False):
+ if actual_field is None:
+ actual_field = field
+ if self.params.get(f'force{field}') and (
+ info_copy.get(field) is not None or (not optional and not incomplete)):
+ self.to_stdout(info_copy[actual_field])
+
+ print_field('title')
+ print_field('id')
+ print_field('url', 'urls')
+ print_field('thumbnail', optional=True)
+ print_field('description', optional=True)
+ if filename:
+ print_field('filename')
+ if self.params.get('forceduration') and info_copy.get('duration') is not None:
+ self.to_stdout(formatSeconds(info_copy['duration']))
+ print_field('format')
if self.params.get('forcejson'):
self.to_stdout(json.dumps(self.sanitize_info(info_dict)))
if remove_private_keys:
reject = lambda k, v: v is None or k.startswith('__') or k in {
'requested_downloads', 'requested_formats', 'requested_subtitles', 'requested_entries',
- 'entries', 'filepath', '_filename', 'infojson_filename', 'original_url', 'playlist_autonumber',
- '_format_sort_fields',
+ 'entries', 'filepath', '_filename', 'filename', 'infojson_filename', 'original_url',
+ 'playlist_autonumber', '_format_sort_fields',
}
else:
reject = lambda k, v: False
# that way it will silently go on when used with unsupporting IE
return ret
elif not subtitles:
- self.to_screen('[info] There\'s no subtitles for the requested languages')
+ self.to_screen('[info] There are no subtitles for the requested languages')
return ret
sub_filename_base = self.prepare_filename(info_dict, 'subtitle')
if not sub_filename_base:
if write_all or self.params.get('writethumbnail', False):
thumbnails = info_dict.get('thumbnails') or []
if not thumbnails:
- self.to_screen(f'[info] There\'s no {label} thumbnails to download')
+ self.to_screen(f'[info] There are no {label} thumbnails to download')
return ret
multiple = write_all and len(thumbnails) > 1
projects / yt-dlp.git / blobdiff