#!/usr/bin/env python3
-# coding: utf-8
-
-from __future__ import absolute_import, unicode_literals
-
import collections
import contextlib
import datetime
import operator
import os
import platform
+import random
import re
import shutil
import subprocess
import time
import tokenize
import traceback
-import random
import unicodedata
import urllib.request
-
from enum import Enum
from string import ascii_letters
+from .cache import Cache
from .compat import (
compat_brotli,
compat_get_terminal_size,
windows_enable_vt_mode,
)
from .cookies import load_cookies
+from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
+from .downloader.rtmp import rtmpdump_version
+from .extractor import _LAZY_LOADER
+from .extractor import _PLUGIN_CLASSES as plugin_extractors
+from .extractor import gen_extractor_classes, get_info_extractor
+from .extractor.openload import PhantomJSwrapper
+from .minicurses import format_text
+from .postprocessor import _PLUGIN_CLASSES as plugin_postprocessors
+from .postprocessor import (
+ EmbedThumbnailPP,
+ FFmpegFixupDuplicateMoovPP,
+ FFmpegFixupDurationPP,
+ FFmpegFixupM3u8PP,
+ FFmpegFixupM4aPP,
+ FFmpegFixupStretchedPP,
+ FFmpegFixupTimestampPP,
+ FFmpegMergerPP,
+ FFmpegPostProcessor,
+ MoveFilesAfterDownloadPP,
+ get_postprocessor,
+)
+from .update import detect_variant
from .utils import (
+ DEFAULT_OUTTMPL,
+ LINK_TEMPLATES,
+ NO_DEFAULT,
+ OUTTMPL_TYPES,
+ POSTPROCESS_WHEN,
+ STR_FORMAT_RE_TMPL,
+ STR_FORMAT_TYPES,
+ ContentTooShortError,
+ DateRange,
+ DownloadCancelled,
+ DownloadError,
+ EntryNotInPlaylist,
+ ExistingVideoReached,
+ ExtractorError,
+ GeoRestrictedError,
+ HEADRequest,
+ InAdvancePagedList,
+ ISO3166Utils,
+ LazyList,
+ MaxDownloadsReached,
+ PagedList,
+ PerRequestProxyHandler,
+ Popen,
+ PostProcessingError,
+ ReExtractInfo,
+ RejectedVideoReached,
+ SameFileError,
+ UnavailableVideoError,
+ YoutubeDLCookieProcessor,
+ YoutubeDLHandler,
+ YoutubeDLRedirectHandler,
age_restricted,
args_to_str,
- ContentTooShortError,
date_from_str,
- DateRange,
- DEFAULT_OUTTMPL,
determine_ext,
determine_protocol,
- DownloadCancelled,
- DownloadError,
encode_compat_str,
encodeFilename,
- EntryNotInPlaylist,
error_to_compat_str,
- ExistingVideoReached,
expand_path,
- ExtractorError,
filter_dict,
float_or_none,
format_bytes,
- format_field,
format_decimal_suffix,
+ format_field,
formatSeconds,
- GeoRestrictedError,
get_domain,
has_certifi,
- HEADRequest,
- InAdvancePagedList,
int_or_none,
iri_to_uri,
- ISO3166Utils,
join_nonempty,
- LazyList,
- LINK_TEMPLATES,
locked_file,
make_dir,
make_HTTPS_handler,
- MaxDownloadsReached,
merge_headers,
network_exceptions,
- NO_DEFAULT,
number_of_digits,
orderedSet,
- OUTTMPL_TYPES,
- PagedList,
parse_filesize,
- PerRequestProxyHandler,
platform_name,
- Popen,
- POSTPROCESS_WHEN,
- PostProcessingError,
preferredencoding,
prepend_extension,
- ReExtractInfo,
register_socks_protocols,
- RejectedVideoReached,
remove_terminal_sequences,
render_table,
replace_extension,
- SameFileError,
sanitize_filename,
sanitize_path,
sanitize_url,
sanitized_Request,
std_headers,
- STR_FORMAT_RE_TMPL,
- STR_FORMAT_TYPES,
str_or_none,
strftime_or_none,
subtitles_filename,
to_high_limit_path,
traverse_obj,
try_get,
- UnavailableVideoError,
url_basename,
variadic,
version_tuple,
write_json_file,
write_string,
- YoutubeDLCookieProcessor,
- YoutubeDLHandler,
- YoutubeDLRedirectHandler,
-)
-from .cache import Cache
-from .minicurses import format_text
-from .extractor import (
- gen_extractor_classes,
- get_info_extractor,
- _LAZY_LOADER,
- _PLUGIN_CLASSES as plugin_extractors
-)
-from .extractor.openload import PhantomJSwrapper
-from .downloader import (
- FFmpegFD,
- get_suitable_downloader,
- shorten_protocol_name
-)
-from .downloader.rtmp import rtmpdump_version
-from .postprocessor import (
- get_postprocessor,
- EmbedThumbnailPP,
- FFmpegFixupDuplicateMoovPP,
- FFmpegFixupDurationPP,
- FFmpegFixupM3u8PP,
- FFmpegFixupM4aPP,
- FFmpegFixupStretchedPP,
- FFmpegFixupTimestampPP,
- FFmpegMergerPP,
- FFmpegPostProcessor,
- MoveFilesAfterDownloadPP,
- _PLUGIN_CLASSES as plugin_postprocessors
)
-from .update import detect_variant
-from .version import __version__, RELEASE_GIT_HEAD
+from .version import RELEASE_GIT_HEAD, __version__
if compat_os_name == 'nt':
import ctypes
-class YoutubeDL(object):
+class YoutubeDL:
"""YoutubeDL class.
YoutubeDL objects are the ones responsible of downloading the
care about HLS. (only for youtube)
"""
- _NUMERIC_FIELDS = set((
+ _NUMERIC_FIELDS = {
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
'timestamp', 'release_timestamp',
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
'start_time', 'end_time',
'chapter_number', 'season_number', 'episode_number',
'track_number', 'disc_number', 'release_year',
- ))
+ }
_format_fields = {
# NB: Keep in sync with the docstring of extractor/common.py
def check_deprecated(param, option, suggestion):
if self.params.get(param) is not None:
- self.report_warning('%s is deprecated. Use %s instead' % (option, suggestion))
+ self.report_warning(f'{option} is deprecated. Use {suggestion} instead')
return True
return False
with locked_file(fn, 'r', encoding='utf-8') as archive_file:
for line in archive_file:
self.archive.add(line.strip())
- except IOError as ioe:
+ except OSError as ioe:
if ioe.errno != errno.ENOENT:
raise
return False
SUPPRESS = 'light black'
def _format_text(self, handle, allow_colors, text, f, fallback=None, *, test_encoding=False):
+ text = str(text)
if test_encoding:
original_text = text
# handle.encoding can be None. See https://github.com/yt-dlp/yt-dlp/issues/2711
text = text.encode(encoding, 'ignore').decode(encoding)
if fallback is not None and text != original_text:
text = fallback
- if isinstance(f, self.Styles):
+ if isinstance(f, Enum):
f = f.value
return format_text(text, f) if allow_colors else text if fallback is None else fallback
outtmpl_dict.update({
k: sanitize(v) for k, v in DEFAULT_OUTTMPL.items()
if outtmpl_dict.get(k) is None})
- for key, val in outtmpl_dict.items():
+ for _, val in outtmpl_dict.items():
if isinstance(val, bytes):
- self.report_warning(
- 'Parameter outtmpl is bytes, but should be a unicode string. '
- 'Put from __future__ import unicode_literals at the top of your code file or consider switching to Python 3.x.')
+ self.report_warning('Parameter outtmpl is bytes, but should be a unicode string')
return outtmpl_dict
def get_output_path(self, dir_type='', filename=None):
# '%%' intact for template dict substitution step. Working around
# with boundary-alike separator hack.
sep = ''.join([random.choice(ascii_letters) for _ in range(32)])
- outtmpl = outtmpl.replace('%%', '%{0}%'.format(sep)).replace('$$', '${0}$'.format(sep))
+ outtmpl = outtmpl.replace('%%', f'%{sep}%').replace('$$', f'${sep}$')
# outtmpl should be expand_path'ed before template dict substitution
# because meta fields may contain env variables we don't want to
fmt = outer_mobj.group('format')
if fmt == 's' and value is not None and key in field_size_compat_map.keys():
- fmt = '0{:d}d'.format(field_size_compat_map[key])
+ fmt = f'0{field_size_compat_map[key]:d}d'
value = default if value is None else value if replacement is None else replacement
value = map(str, variadic(value) if '#' in flags else [value])
value, fmt = ' '.join(map(compat_shlex_quote, value)), str_fmt
elif fmt[-1] == 'B': # bytes
- value = f'%{str_fmt}'.encode('utf-8') % str(value).encode('utf-8')
+ value = f'%{str_fmt}'.encode() % str(value).encode('utf-8')
value, fmt = value.decode('utf-8', 'ignore'), 's'
elif fmt[-1] == 'U': # unicode normalized
value, fmt = unicodedata.normalize(
if date is not None:
dateRange = self.params.get('daterange', DateRange())
if date not in dateRange:
- return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
+ return f'{date_from_str(date).isoformat()} upload date is not in range {dateRange}'
view_count = info_dict.get('view_count')
if view_count is not None:
min_views = self.params.get('min_views')
entries.append(entry)
try:
if entry is not None:
+ # TODO: Add auto-generated fields
self._match_entry(entry, incomplete=True, silent=True)
except (ExistingVideoReached, RejectedVideoReached):
broken = True
x_forwarded_for = ie_result.get('__x_forwarded_for_ip')
- self.to_screen('[%s] playlist %s: %s' % (ie_result['extractor'], playlist, msg % n_entries))
+ self.to_screen(f'[{ie_result["extractor"]}] playlist {playlist}: {msg % n_entries}')
failures = 0
max_failures = self.params.get('skip_playlist_after_errors') or float('inf')
for i, entry_tuple in enumerate(entries, 1):
playlist_index, entry = entry_tuple
if 'playlist-index' in self.params.get('compat_opts', []):
playlist_index = playlistitems[i - 1] if playlistitems else i + playliststart - 1
- self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
+ self.to_screen(f'[download] Downloading video {i} of {n_entries}')
# This __x_forwarded_for_ip thing is a bit ugly but requires
# minimal changes
if x_forwarded_for:
def syntax_error(note, start):
message = (
'Invalid format specification: '
- '{0}\n\t{1}\n\t{2}^'.format(note, format_spec, ' ' * start[1]))
+ '{}\n\t{}\n\t{}^'.format(note, format_spec, ' ' * start[1]))
return SyntaxError(message)
PICKFIRST = 'PICKFIRST'
raise syntax_error('Expected a selector', start)
current_selector = FormatSelector(MERGE, (selector_1, selector_2), [])
else:
- raise syntax_error('Operator not recognized: "{0}"'.format(string), start)
+ raise syntax_error(f'Operator not recognized: "{string}"', start)
elif type == tokenize.ENDMARKER:
break
if current_selector:
except tokenize.TokenError:
raise syntax_error('Missing closing/opening brackets or parenthesis', (0, len(format_spec)))
- class TokenIterator(object):
+ class TokenIterator:
def __init__(self, tokens):
self.tokens = tokens
self.counter = 0
if max_downloads_reached:
break
- write_archive = set(f.get('__write_download_archive', False) for f in formats_to_download)
+ write_archive = {f.get('__write_download_archive', False) for f in formats_to_download}
assert write_archive.issubset({True, False, 'ignore'})
if True in write_archive and False not in write_archive:
self.record_download_archive(info_dict)
for lang in requested_langs:
formats = available_subs.get(lang)
if formats is None:
- self.report_warning('%s subtitles not available for %s' % (lang, video_id))
+ self.report_warning(f'{lang} subtitles not available for {video_id}')
continue
for ext in formats_preference:
if ext == 'best':
tmpl = format_tmpl(tmpl)
self.to_screen(f'[info] Writing {tmpl!r} to: {filename}')
if self._ensure_dir_exists(filename):
- with io.open(filename, 'a', encoding='utf-8') as f:
+ with open(filename, 'a', encoding='utf-8') as f:
f.write(self.evaluate_outtmpl(tmpl, info_copy) + '\n')
def __forced_printings(self, info_dict, filename, incomplete):
else:
try:
self.to_screen('[info] Writing video annotations to: ' + annofn)
- with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
+ with open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
annofile.write(info_dict['annotations'])
except (KeyError, TypeError):
self.report_warning('There are no annotations to write.')
- except (OSError, IOError):
+ except OSError:
self.report_error('Cannot write annotations file: ' + annofn)
return
return True
try:
self.to_screen(f'[info] Writing internet shortcut (.{link_type}) to: {linkfn}')
- with io.open(encodeFilename(to_high_limit_path(linkfn)), 'w', encoding='utf-8',
- newline='\r\n' if link_type == 'url' else '\n') as linkfile:
+ with open(encodeFilename(to_high_limit_path(linkfn)), 'w', encoding='utf-8',
+ newline='\r\n' if link_type == 'url' else '\n') as linkfile:
template_vars = {'url': url}
if link_type == 'desktop':
template_vars['filename'] = linkfn[:-(len(link_type) + 1)]
linkfile.write(LINK_TEMPLATES[link_type] % template_vars)
- except (OSError, IOError):
+ except OSError:
self.report_error(f'Cannot write internet shortcut {linkfn}')
return False
return True
return False
# Check extension
- exts = set(format.get('ext') for format in formats)
+ exts = {format.get('ext') for format in formats}
COMPATIBLE_EXTS = (
- set(('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'ismv', 'isma')),
- set(('webm',)),
+ {'mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'ismv', 'isma'},
+ {'webm'},
)
for ext_sets in COMPATIBLE_EXTS:
if ext_sets.issuperset(exts):
os.path.splitext(filename)[0]
if filename_real_ext in (old_ext, new_ext)
else filename)
- return '%s.%s' % (filename_wo_ext, ext)
+ return f'{filename_wo_ext}.{ext}'
# Ensure filename always has a correct extension for successful merge
full_filename = correct_ext(full_filename)
except network_exceptions as err:
self.report_error('unable to download video data: %s' % error_to_compat_str(err))
return
- except (OSError, IOError) as err:
+ except OSError as err:
raise UnavailableVideoError(err)
except (ContentTooShortError, ) as err:
- self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
+ self.report_error(f'content too short (expected {err.expected} bytes and served {err.downloaded})')
return
if success and full_filename != '-':
self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
try:
os.remove(encodeFilename(old_filename))
- except (IOError, OSError):
+ except OSError:
self.report_warning('Unable to remove downloaded original file')
if old_filename in infodict['__files_to_move']:
del infodict['__files_to_move'][old_filename]
break
else:
return
- return '%s %s' % (extractor.lower(), video_id)
+ return f'{extractor.lower()} {video_id}'
def in_download_archive(self, info_dict):
fn = self.params.get('download_archive')
) or 'none'
write_debug('exe versions: %s' % exe_str)
+ from .cookies import SECRETSTORAGE_AVAILABLE, SQLITE_AVAILABLE
from .downloader.websocket import has_websockets
from .postprocessor.embedthumbnail import has_mutagen
- from .cookies import SQLITE_AVAILABLE, SECRETSTORAGE_AVAILABLE
lib_str = join_nonempty(
compat_brotli and compat_brotli.__name__,
try:
write_json_file(self.sanitize_info(ie_result, self.params.get('clean_infojson', True)), infofn)
return True
- except (OSError, IOError):
+ except OSError:
self.report_error(f'Cannot write {label} metadata to JSON file {infofn}')
return None
else:
try:
self.to_screen(f'[info] Writing {label} description to: {descfn}')
- with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
+ with open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(ie_result['description'])
- except (OSError, IOError):
+ except OSError:
self.report_error(f'Cannot write {label} description file {descfn}')
return None
return True
try:
# Use newline='' to prevent conversion of newline characters
# See https://github.com/ytdl-org/youtube-dl/issues/10268
- with io.open(sub_filename, 'w', encoding='utf-8', newline='') as subfile:
+ with open(sub_filename, 'w', encoding='utf-8', newline='') as subfile:
subfile.write(sub_info['data'])
sub_info['filepath'] = sub_filename
ret.append((sub_filename, sub_filename_final))
continue
- except (OSError, IOError):
+ except OSError:
self.report_error(f'Cannot write video subtitles file {sub_filename}')
return None
projects / yt-dlp.git / blobdiff