mirror of https://github.com/yt-dlp/yt-dlp.git
[skip travis] adding automerge support
basically copying content of youtube_dl folder to youtube_dlc and excluding the youtube_dl folder when compiling
This commit is contained in:
Unknown
parent
4cd6add62b
commit
3ca3f77f9c
|
|
@ -35,4 +35,7 @@ jobs:
|
|||
- env: JYTHON=true; YTDL_TEST_SET=core
|
||||
before_install:
|
||||
- if [ "$JYTHON" == "true" ]; then ./devscripts/install_jython.sh; export PATH="$HOME/jython/bin:$PATH"; fi
|
||||
before_script:
|
||||
- rm -rf /youtube_dlc/*
|
||||
- cp /youtube_dl/* /youtube_dlc
|
||||
script: ./devscripts/run_tests.sh
|
||||
|
|
|
|||
2
setup.py
2
setup.py
|
|
@ -67,7 +67,7 @@ setup(
|
|||
long_description=LONG_DESCRIPTION,
|
||||
# long_description_content_type="text/markdown",
|
||||
url="https://github.com/blackjack4494/youtube-dlc",
|
||||
packages=find_packages(),
|
||||
packages=find_packages(exclude=("youtube_dl",)),
|
||||
#packages=[
|
||||
# 'youtube_dlc',
|
||||
# 'youtube_dlc.extractor', 'youtube_dlc.downloader',
|
||||
|
|
|
|||
|
|
@ -0,0 +1,33 @@
|
|||
# -*- mode: python ; coding: utf-8 -*-
|
||||
|
||||
block_cipher = None
|
||||
|
||||
|
||||
a = Analysis(['youtube_dlc\\__main__.py'],
|
||||
pathex=['D:\\gitkraken\\youtube-dl'],
|
||||
binaries=[],
|
||||
datas=[],
|
||||
hiddenimports=[],
|
||||
hookspath=[],
|
||||
runtime_hooks=[],
|
||||
excludes=[],
|
||||
win_no_prefer_redirects=False,
|
||||
win_private_assemblies=False,
|
||||
cipher=block_cipher,
|
||||
noarchive=False)
|
||||
pyz = PYZ(a.pure, a.zipped_data,
|
||||
cipher=block_cipher)
|
||||
exe = EXE(pyz,
|
||||
a.scripts,
|
||||
a.binaries,
|
||||
a.zipfiles,
|
||||
a.datas,
|
||||
[],
|
||||
name='youtube-dlc',
|
||||
debug=False,
|
||||
bootloader_ignore_signals=False,
|
||||
strip=False,
|
||||
upx=True,
|
||||
upx_exclude=[],
|
||||
runtime_tmpdir=None,
|
||||
console=True )
|
||||
|
|
@ -0,0 +1,2417 @@
|
|||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
|
||||
from __future__ import absolute_import, unicode_literals
|
||||
|
||||
import collections
|
||||
import contextlib
|
||||
import copy
|
||||
import datetime
|
||||
import errno
|
||||
import fileinput
|
||||
import io
|
||||
import itertools
|
||||
import json
|
||||
import locale
|
||||
import operator
|
||||
import os
|
||||
import platform
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
import socket
|
||||
import sys
|
||||
import time
|
||||
import tokenize
|
||||
import traceback
|
||||
import random
|
||||
|
||||
from string import ascii_letters
|
||||
|
||||
from .compat import (
|
||||
compat_basestring,
|
||||
compat_cookiejar,
|
||||
compat_get_terminal_size,
|
||||
compat_http_client,
|
||||
compat_kwargs,
|
||||
compat_numeric_types,
|
||||
compat_os_name,
|
||||
compat_str,
|
||||
compat_tokenize_tokenize,
|
||||
compat_urllib_error,
|
||||
compat_urllib_request,
|
||||
compat_urllib_request_DataHandler,
|
||||
)
|
||||
from .utils import (
|
||||
age_restricted,
|
||||
args_to_str,
|
||||
ContentTooShortError,
|
||||
date_from_str,
|
||||
DateRange,
|
||||
DEFAULT_OUTTMPL,
|
||||
determine_ext,
|
||||
determine_protocol,
|
||||
DownloadError,
|
||||
encode_compat_str,
|
||||
encodeFilename,
|
||||
error_to_compat_str,
|
||||
expand_path,
|
||||
ExtractorError,
|
||||
format_bytes,
|
||||
formatSeconds,
|
||||
GeoRestrictedError,
|
||||
int_or_none,
|
||||
ISO3166Utils,
|
||||
locked_file,
|
||||
make_HTTPS_handler,
|
||||
MaxDownloadsReached,
|
||||
orderedSet,
|
||||
PagedList,
|
||||
parse_filesize,
|
||||
PerRequestProxyHandler,
|
||||
platform_name,
|
||||
PostProcessingError,
|
||||
preferredencoding,
|
||||
prepend_extension,
|
||||
register_socks_protocols,
|
||||
render_table,
|
||||
replace_extension,
|
||||
SameFileError,
|
||||
sanitize_filename,
|
||||
sanitize_path,
|
||||
sanitize_url,
|
||||
sanitized_Request,
|
||||
std_headers,
|
||||
str_or_none,
|
||||
subtitles_filename,
|
||||
UnavailableVideoError,
|
||||
url_basename,
|
||||
version_tuple,
|
||||
write_json_file,
|
||||
write_string,
|
||||
YoutubeDLCookieJar,
|
||||
YoutubeDLCookieProcessor,
|
||||
YoutubeDLHandler,
|
||||
YoutubeDLRedirectHandler,
|
||||
)
|
||||
from .cache import Cache
|
||||
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
|
||||
from .extractor.openload import PhantomJSwrapper
|
||||
from .downloader import get_suitable_downloader
|
||||
from .downloader.rtmp import rtmpdump_version
|
||||
from .postprocessor import (
|
||||
FFmpegFixupM3u8PP,
|
||||
FFmpegFixupM4aPP,
|
||||
FFmpegFixupStretchedPP,
|
||||
FFmpegMergerPP,
|
||||
FFmpegPostProcessor,
|
||||
get_postprocessor,
|
||||
)
|
||||
from .version import __version__
|
||||
|
||||
if compat_os_name == 'nt':
|
||||
import ctypes
|
||||
|
||||
|
||||
class YoutubeDL(object):
|
||||
"""YoutubeDL class.
|
||||
|
||||
YoutubeDL objects are the ones responsible of downloading the
|
||||
actual video file and writing it to disk if the user has requested
|
||||
it, among some other tasks. In most cases there should be one per
|
||||
program. As, given a video URL, the downloader doesn't know how to
|
||||
extract all the needed information, task that InfoExtractors do, it
|
||||
has to pass the URL to one of them.
|
||||
|
||||
For this, YoutubeDL objects have a method that allows
|
||||
InfoExtractors to be registered in a given order. When it is passed
|
||||
a URL, the YoutubeDL object handles it to the first InfoExtractor it
|
||||
finds that reports being able to handle it. The InfoExtractor extracts
|
||||
all the information about the video or videos the URL refers to, and
|
||||
YoutubeDL process the extracted information, possibly using a File
|
||||
Downloader to download the video.
|
||||
|
||||
YoutubeDL objects accept a lot of parameters. In order not to saturate
|
||||
the object constructor with arguments, it receives a dictionary of
|
||||
options instead. These options are available through the params
|
||||
attribute for the InfoExtractors to use. The YoutubeDL also
|
||||
registers itself as the downloader in charge for the InfoExtractors
|
||||
that are added to it, so this is a "mutual registration".
|
||||
|
||||
Available options:
|
||||
|
||||
username: Username for authentication purposes.
|
||||
password: Password for authentication purposes.
|
||||
videopassword: Password for accessing a video.
|
||||
ap_mso: Adobe Pass multiple-system operator identifier.
|
||||
ap_username: Multiple-system operator account username.
|
||||
ap_password: Multiple-system operator account password.
|
||||
usenetrc: Use netrc for authentication instead.
|
||||
verbose: Print additional info to stdout.
|
||||
quiet: Do not print messages to stdout.
|
||||
no_warnings: Do not print out anything for warnings.
|
||||
forceurl: Force printing final URL.
|
||||
forcetitle: Force printing title.
|
||||
forceid: Force printing ID.
|
||||
forcethumbnail: Force printing thumbnail URL.
|
||||
forcedescription: Force printing description.
|
||||
forcefilename: Force printing final filename.
|
||||
forceduration: Force printing duration.
|
||||
forcejson: Force printing info_dict as JSON.
|
||||
dump_single_json: Force printing the info_dict of the whole playlist
|
||||
(or video) as a single JSON line.
|
||||
simulate: Do not download the video files.
|
||||
format: Video format code. See options.py for more information.
|
||||
outtmpl: Template for output names.
|
||||
restrictfilenames: Do not allow "&" and spaces in file names
|
||||
ignoreerrors: Do not stop on download errors.
|
||||
force_generic_extractor: Force downloader to use the generic extractor
|
||||
nooverwrites: Prevent overwriting files.
|
||||
playliststart: Playlist item to start at.
|
||||
playlistend: Playlist item to end at.
|
||||
playlist_items: Specific indices of playlist to download.
|
||||
playlistreverse: Download playlist items in reverse order.
|
||||
playlistrandom: Download playlist items in random order.
|
||||
matchtitle: Download only matching titles.
|
||||
rejecttitle: Reject downloads for matching titles.
|
||||
logger: Log messages to a logging.Logger instance.
|
||||
logtostderr: Log messages to stderr instead of stdout.
|
||||
writedescription: Write the video description to a .description file
|
||||
writeinfojson: Write the video description to a .info.json file
|
||||
writeannotations: Write the video annotations to a .annotations.xml file
|
||||
writethumbnail: Write the thumbnail image to a file
|
||||
write_all_thumbnails: Write all thumbnail formats to files
|
||||
writesubtitles: Write the video subtitles to a file
|
||||
writeautomaticsub: Write the automatically generated subtitles to a file
|
||||
allsubtitles: Downloads all the subtitles of the video
|
||||
(requires writesubtitles or writeautomaticsub)
|
||||
listsubtitles: Lists all available subtitles for the video
|
||||
subtitlesformat: The format code for subtitles
|
||||
subtitleslangs: List of languages of the subtitles to download
|
||||
keepvideo: Keep the video file after post-processing
|
||||
daterange: A DateRange object, download only if the upload_date is in the range.
|
||||
skip_download: Skip the actual download of the video file
|
||||
cachedir: Location of the cache files in the filesystem.
|
||||
False to disable filesystem cache.
|
||||
noplaylist: Download single video instead of a playlist if in doubt.
|
||||
age_limit: An integer representing the user's age in years.
|
||||
Unsuitable videos for the given age are skipped.
|
||||
min_views: An integer representing the minimum view count the video
|
||||
must have in order to not be skipped.
|
||||
Videos without view count information are always
|
||||
downloaded. None for no limit.
|
||||
max_views: An integer representing the maximum view count.
|
||||
Videos that are more popular than that are not
|
||||
downloaded.
|
||||
Videos without view count information are always
|
||||
downloaded. None for no limit.
|
||||
download_archive: File name of a file where all downloads are recorded.
|
||||
Videos already present in the file are not downloaded
|
||||
again.
|
||||
cookiefile: File name where cookies should be read from and dumped to.
|
||||
nocheckcertificate:Do not verify SSL certificates
|
||||
prefer_insecure: Use HTTP instead of HTTPS to retrieve information.
|
||||
At the moment, this is only supported by YouTube.
|
||||
proxy: URL of the proxy server to use
|
||||
geo_verification_proxy: URL of the proxy to use for IP address verification
|
||||
on geo-restricted sites.
|
||||
socket_timeout: Time to wait for unresponsive hosts, in seconds
|
||||
bidi_workaround: Work around buggy terminals without bidirectional text
|
||||
support, using fridibi
|
||||
debug_printtraffic:Print out sent and received HTTP traffic
|
||||
include_ads: Download ads as well
|
||||
default_search: Prepend this string if an input url is not valid.
|
||||
'auto' for elaborate guessing
|
||||
encoding: Use this encoding instead of the system-specified.
|
||||
extract_flat: Do not resolve URLs, return the immediate result.
|
||||
Pass in 'in_playlist' to only show this behavior for
|
||||
playlist items.
|
||||
postprocessors: A list of dictionaries, each with an entry
|
||||
* key: The name of the postprocessor. See
|
||||
youtube_dlc/postprocessor/__init__.py for a list.
|
||||
as well as any further keyword arguments for the
|
||||
postprocessor.
|
||||
progress_hooks: A list of functions that get called on download
|
||||
progress, with a dictionary with the entries
|
||||
* status: One of "downloading", "error", or "finished".
|
||||
Check this first and ignore unknown values.
|
||||
|
||||
If status is one of "downloading", or "finished", the
|
||||
following properties may also be present:
|
||||
* filename: The final filename (always present)
|
||||
* tmpfilename: The filename we're currently writing to
|
||||
* downloaded_bytes: Bytes on disk
|
||||
* total_bytes: Size of the whole file, None if unknown
|
||||
* total_bytes_estimate: Guess of the eventual file size,
|
||||
None if unavailable.
|
||||
* elapsed: The number of seconds since download started.
|
||||
* eta: The estimated time in seconds, None if unknown
|
||||
* speed: The download speed in bytes/second, None if
|
||||
unknown
|
||||
* fragment_index: The counter of the currently
|
||||
downloaded video fragment.
|
||||
* fragment_count: The number of fragments (= individual
|
||||
files that will be merged)
|
||||
|
||||
Progress hooks are guaranteed to be called at least once
|
||||
(with status "finished") if the download is successful.
|
||||
merge_output_format: Extension to use when merging formats.
|
||||
fixup: Automatically correct known faults of the file.
|
||||
One of:
|
||||
- "never": do nothing
|
||||
- "warn": only emit a warning
|
||||
- "detect_or_warn": check whether we can do anything
|
||||
about it, warn otherwise (default)
|
||||
source_address: Client-side IP address to bind to.
|
||||
call_home: Boolean, true iff we are allowed to contact the
|
||||
youtube-dlc servers for debugging.
|
||||
sleep_interval: Number of seconds to sleep before each download when
|
||||
used alone or a lower bound of a range for randomized
|
||||
sleep before each download (minimum possible number
|
||||
of seconds to sleep) when used along with
|
||||
max_sleep_interval.
|
||||
max_sleep_interval:Upper bound of a range for randomized sleep before each
|
||||
download (maximum possible number of seconds to sleep).
|
||||
Must only be used along with sleep_interval.
|
||||
Actual sleep time will be a random float from range
|
||||
[sleep_interval; max_sleep_interval].
|
||||
listformats: Print an overview of available video formats and exit.
|
||||
list_thumbnails: Print a table of all thumbnails and exit.
|
||||
match_filter: A function that gets called with the info_dict of
|
||||
every video.
|
||||
If it returns a message, the video is ignored.
|
||||
If it returns None, the video is downloaded.
|
||||
match_filter_func in utils.py is one example for this.
|
||||
no_color: Do not emit color codes in output.
|
||||
geo_bypass: Bypass geographic restriction via faking X-Forwarded-For
|
||||
HTTP header
|
||||
geo_bypass_country:
|
||||
Two-letter ISO 3166-2 country code that will be used for
|
||||
explicit geographic restriction bypassing via faking
|
||||
X-Forwarded-For HTTP header
|
||||
geo_bypass_ip_block:
|
||||
IP range in CIDR notation that will be used similarly to
|
||||
geo_bypass_country
|
||||
|
||||
The following options determine which downloader is picked:
|
||||
external_downloader: Executable of the external downloader to call.
|
||||
None or unset for standard (built-in) downloader.
|
||||
hls_prefer_native: Use the native HLS downloader instead of ffmpeg/avconv
|
||||
if True, otherwise use ffmpeg/avconv if False, otherwise
|
||||
use downloader suggested by extractor if None.
|
||||
|
||||
The following parameters are not used by YoutubeDL itself, they are used by
|
||||
the downloader (see youtube_dlc/downloader/common.py):
|
||||
nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
|
||||
noresizebuffer, retries, continuedl, noprogress, consoletitle,
|
||||
xattr_set_filesize, external_downloader_args, hls_use_mpegts,
|
||||
http_chunk_size.
|
||||
|
||||
The following options are used by the post processors:
|
||||
prefer_ffmpeg: If False, use avconv instead of ffmpeg if both are available,
|
||||
otherwise prefer ffmpeg.
|
||||
ffmpeg_location: Location of the ffmpeg/avconv binary; either the path
|
||||
to the binary or its containing directory.
|
||||
postprocessor_args: A list of additional command-line arguments for the
|
||||
postprocessor.
|
||||
|
||||
The following options are used by the Youtube extractor:
|
||||
youtube_include_dash_manifest: If True (default), DASH manifests and related
|
||||
data will be downloaded and processed by extractor.
|
||||
You can reduce network I/O by disabling it if you don't
|
||||
care about DASH.
|
||||
"""
|
||||
|
||||
_NUMERIC_FIELDS = set((
|
||||
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
|
||||
'timestamp', 'upload_year', 'upload_month', 'upload_day',
|
||||
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
|
||||
'average_rating', 'comment_count', 'age_limit',
|
||||
'start_time', 'end_time',
|
||||
'chapter_number', 'season_number', 'episode_number',
|
||||
'track_number', 'disc_number', 'release_year',
|
||||
'playlist_index',
|
||||
))
|
||||
|
||||
params = None
|
||||
_ies = []
|
||||
_pps = []
|
||||
_download_retcode = None
|
||||
_num_downloads = None
|
||||
_screen_file = None
|
||||
|
||||
def __init__(self, params=None, auto_init=True):
|
||||
"""Create a FileDownloader object with the given options."""
|
||||
if params is None:
|
||||
params = {}
|
||||
self._ies = []
|
||||
self._ies_instances = {}
|
||||
self._pps = []
|
||||
self._progress_hooks = []
|
||||
self._download_retcode = 0
|
||||
self._num_downloads = 0
|
||||
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
|
||||
self._err_file = sys.stderr
|
||||
self.params = {
|
||||
# Default parameters
|
||||
'nocheckcertificate': False,
|
||||
}
|
||||
self.params.update(params)
|
||||
self.cache = Cache(self)
|
||||
|
||||
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))
|
||||
return True
|
||||
return False
|
||||
|
||||
if check_deprecated('cn_verification_proxy', '--cn-verification-proxy', '--geo-verification-proxy'):
|
||||
if self.params.get('geo_verification_proxy') is None:
|
||||
self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
|
||||
|
||||
check_deprecated('autonumber_size', '--autonumber-size', 'output template with %(autonumber)0Nd, where N in the number of digits')
|
||||
check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
|
||||
check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
|
||||
|
||||
if params.get('bidi_workaround', False):
|
||||
try:
|
||||
import pty
|
||||
master, slave = pty.openpty()
|
||||
width = compat_get_terminal_size().columns
|
||||
if width is None:
|
||||
width_args = []
|
||||
else:
|
||||
width_args = ['-w', str(width)]
|
||||
sp_kwargs = dict(
|
||||
stdin=subprocess.PIPE,
|
||||
stdout=slave,
|
||||
stderr=self._err_file)
|
||||
try:
|
||||
self._output_process = subprocess.Popen(
|
||||
['bidiv'] + width_args, **sp_kwargs
|
||||
)
|
||||
except OSError:
|
||||
self._output_process = subprocess.Popen(
|
||||
['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs)
|
||||
self._output_channel = os.fdopen(master, 'rb')
|
||||
except OSError as ose:
|
||||
if ose.errno == errno.ENOENT:
|
||||
self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.')
|
||||
else:
|
||||
raise
|
||||
|
||||
if (sys.platform != 'win32'
|
||||
and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
|
||||
and not params.get('restrictfilenames', False)):
|
||||
# Unicode filesystem API will throw errors (#1474, #13027)
|
||||
self.report_warning(
|
||||
'Assuming --restrict-filenames since file system encoding '
|
||||
'cannot encode all characters. '
|
||||
'Set the LC_ALL environment variable to fix this.')
|
||||
self.params['restrictfilenames'] = True
|
||||
|
||||
if isinstance(params.get('outtmpl'), bytes):
|
||||
self.report_warning(
|
||||
'Parameter outtmpl is bytes, but should be a unicode string. '
|
||||
'Put from __future__ import unicode_literals at the top of your code file or consider switching to Python 3.x.')
|
||||
|
||||
self._setup_opener()
|
||||
|
||||
if auto_init:
|
||||
self.print_debug_header()
|
||||
self.add_default_info_extractors()
|
||||
|
||||
for pp_def_raw in self.params.get('postprocessors', []):
|
||||
pp_class = get_postprocessor(pp_def_raw['key'])
|
||||
pp_def = dict(pp_def_raw)
|
||||
del pp_def['key']
|
||||
pp = pp_class(self, **compat_kwargs(pp_def))
|
||||
self.add_post_processor(pp)
|
||||
|
||||
for ph in self.params.get('progress_hooks', []):
|
||||
self.add_progress_hook(ph)
|
||||
|
||||
register_socks_protocols()
|
||||
|
||||
def warn_if_short_id(self, argv):
|
||||
# short YouTube ID starting with dash?
|
||||
idxs = [
|
||||
i for i, a in enumerate(argv)
|
||||
if re.match(r'^-[0-9A-Za-z_-]{10}$', a)]
|
||||
if idxs:
|
||||
correct_argv = (
|
||||
['youtube-dlc']
|
||||
+ [a for i, a in enumerate(argv) if i not in idxs]
|
||||
+ ['--'] + [argv[i] for i in idxs]
|
||||
)
|
||||
self.report_warning(
|
||||
'Long argument string detected. '
|
||||
'Use -- to separate parameters and URLs, like this:\n%s\n' %
|
||||
args_to_str(correct_argv))
|
||||
|
||||
def add_info_extractor(self, ie):
|
||||
"""Add an InfoExtractor object to the end of the list."""
|
||||
self._ies.append(ie)
|
||||
if not isinstance(ie, type):
|
||||
self._ies_instances[ie.ie_key()] = ie
|
||||
ie.set_downloader(self)
|
||||
|
||||
def get_info_extractor(self, ie_key):
|
||||
"""
|
||||
Get an instance of an IE with name ie_key, it will try to get one from
|
||||
the _ies list, if there's no instance it will create a new one and add
|
||||
it to the extractor list.
|
||||
"""
|
||||
ie = self._ies_instances.get(ie_key)
|
||||
if ie is None:
|
||||
ie = get_info_extractor(ie_key)()
|
||||
self.add_info_extractor(ie)
|
||||
return ie
|
||||
|
||||
def add_default_info_extractors(self):
|
||||
"""
|
||||
Add the InfoExtractors returned by gen_extractors to the end of the list
|
||||
"""
|
||||
for ie in gen_extractor_classes():
|
||||
self.add_info_extractor(ie)
|
||||
|
||||
def add_post_processor(self, pp):
|
||||
"""Add a PostProcessor object to the end of the chain."""
|
||||
self._pps.append(pp)
|
||||
pp.set_downloader(self)
|
||||
|
||||
def add_progress_hook(self, ph):
|
||||
"""Add the progress hook (currently only for the file downloader)"""
|
||||
self._progress_hooks.append(ph)
|
||||
|
||||
def _bidi_workaround(self, message):
|
||||
if not hasattr(self, '_output_channel'):
|
||||
return message
|
||||
|
||||
assert hasattr(self, '_output_process')
|
||||
assert isinstance(message, compat_str)
|
||||
line_count = message.count('\n') + 1
|
||||
self._output_process.stdin.write((message + '\n').encode('utf-8'))
|
||||
self._output_process.stdin.flush()
|
||||
res = ''.join(self._output_channel.readline().decode('utf-8')
|
||||
for _ in range(line_count))
|
||||
return res[:-len('\n')]
|
||||
|
||||
def to_screen(self, message, skip_eol=False):
|
||||
"""Print message to stdout if not in quiet mode."""
|
||||
return self.to_stdout(message, skip_eol, check_quiet=True)
|
||||
|
||||
def _write_string(self, s, out=None):
|
||||
write_string(s, out=out, encoding=self.params.get('encoding'))
|
||||
|
||||
def to_stdout(self, message, skip_eol=False, check_quiet=False):
|
||||
"""Print message to stdout if not in quiet mode."""
|
||||
if self.params.get('logger'):
|
||||
self.params['logger'].debug(message)
|
||||
elif not check_quiet or not self.params.get('quiet', False):
|
||||
message = self._bidi_workaround(message)
|
||||
terminator = ['\n', ''][skip_eol]
|
||||
output = message + terminator
|
||||
|
||||
self._write_string(output, self._screen_file)
|
||||
|
||||
def to_stderr(self, message):
|
||||
"""Print message to stderr."""
|
||||
assert isinstance(message, compat_str)
|
||||
if self.params.get('logger'):
|
||||
self.params['logger'].error(message)
|
||||
else:
|
||||
message = self._bidi_workaround(message)
|
||||
output = message + '\n'
|
||||
self._write_string(output, self._err_file)
|
||||
|
||||
def to_console_title(self, message):
|
||||
if not self.params.get('consoletitle', False):
|
||||
return
|
||||
if compat_os_name == 'nt':
|
||||
if ctypes.windll.kernel32.GetConsoleWindow():
|
||||
# c_wchar_p() might not be necessary if `message` is
|
||||
# already of type unicode()
|
||||
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
|
||||
elif 'TERM' in os.environ:
|
||||
self._write_string('\033]0;%s\007' % message, self._screen_file)
|
||||
|
||||
def save_console_title(self):
|
||||
if not self.params.get('consoletitle', False):
|
||||
return
|
||||
if self.params.get('simulate', False):
|
||||
return
|
||||
if compat_os_name != 'nt' and 'TERM' in os.environ:
|
||||
# Save the title on stack
|
||||
self._write_string('\033[22;0t', self._screen_file)
|
||||
|
||||
def restore_console_title(self):
|
||||
if not self.params.get('consoletitle', False):
|
||||
return
|
||||
if self.params.get('simulate', False):
|
||||
return
|
||||
if compat_os_name != 'nt' and 'TERM' in os.environ:
|
||||
# Restore the title from stack
|
||||
self._write_string('\033[23;0t', self._screen_file)
|
||||
|
||||
def __enter__(self):
|
||||
self.save_console_title()
|
||||
return self
|
||||
|
||||
def __exit__(self, *args):
|
||||
self.restore_console_title()
|
||||
|
||||
if self.params.get('cookiefile') is not None:
|
||||
self.cookiejar.save(ignore_discard=True, ignore_expires=True)
|
||||
|
||||
def trouble(self, message=None, tb=None):
|
||||
"""Determine action to take when a download problem appears.
|
||||
|
||||
Depending on if the downloader has been configured to ignore
|
||||
download errors or not, this method may throw an exception or
|
||||
not when errors are found, after printing the message.
|
||||
|
||||
tb, if given, is additional traceback information.
|
||||
"""
|
||||
if message is not None:
|
||||
self.to_stderr(message)
|
||||
if self.params.get('verbose'):
|
||||
if tb is None:
|
||||
if sys.exc_info()[0]: # if .trouble has been called from an except block
|
||||
tb = ''
|
||||
if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
|
||||
tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
|
||||
tb += encode_compat_str(traceback.format_exc())
|
||||
else:
|
||||
tb_data = traceback.format_list(traceback.extract_stack())
|
||||
tb = ''.join(tb_data)
|
||||
self.to_stderr(tb)
|
||||
if not self.params.get('ignoreerrors', False):
|
||||
if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
|
||||
exc_info = sys.exc_info()[1].exc_info
|
||||
else:
|
||||
exc_info = sys.exc_info()
|
||||
raise DownloadError(message, exc_info)
|
||||
self._download_retcode = 1
|
||||
|
||||
def report_warning(self, message):
|
||||
'''
|
||||
Print the message to stderr, it will be prefixed with 'WARNING:'
|
||||
If stderr is a tty file the 'WARNING:' will be colored
|
||||
'''
|
||||
if self.params.get('logger') is not None:
|
||||
self.params['logger'].warning(message)
|
||||
else:
|
||||
if self.params.get('no_warnings'):
|
||||
return
|
||||
if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
|
||||
_msg_header = '\033[0;33mWARNING:\033[0m'
|
||||
else:
|
||||
_msg_header = 'WARNING:'
|
||||
warning_message = '%s %s' % (_msg_header, message)
|
||||
self.to_stderr(warning_message)
|
||||
|
||||
def report_error(self, message, tb=None):
|
||||
'''
|
||||
Do the same as trouble, but prefixes the message with 'ERROR:', colored
|
||||
in red if stderr is a tty file.
|
||||
'''
|
||||
if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
|
||||
_msg_header = '\033[0;31mERROR:\033[0m'
|
||||
else:
|
||||
_msg_header = 'ERROR:'
|
||||
error_message = '%s %s' % (_msg_header, message)
|
||||
self.trouble(error_message, tb)
|
||||
|
||||
def report_file_already_downloaded(self, file_name):
|
||||
"""Report file has already been fully downloaded."""
|
||||
try:
|
||||
self.to_screen('[download] %s has already been downloaded' % file_name)
|
||||
except UnicodeEncodeError:
|
||||
self.to_screen('[download] The file has already been downloaded')
|
||||
|
||||
def prepare_filename(self, info_dict):
|
||||
"""Generate the output filename."""
|
||||
try:
|
||||
template_dict = dict(info_dict)
|
||||
|
||||
template_dict['epoch'] = int(time.time())
|
||||
autonumber_size = self.params.get('autonumber_size')
|
||||
if autonumber_size is None:
|
||||
autonumber_size = 5
|
||||
template_dict['autonumber'] = self.params.get('autonumber_start', 1) - 1 + self._num_downloads
|
||||
if template_dict.get('resolution') is None:
|
||||
if template_dict.get('width') and template_dict.get('height'):
|
||||
template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
|
||||
elif template_dict.get('height'):
|
||||
template_dict['resolution'] = '%sp' % template_dict['height']
|
||||
elif template_dict.get('width'):
|
||||
template_dict['resolution'] = '%dx?' % template_dict['width']
|
||||
|
||||
sanitize = lambda k, v: sanitize_filename(
|
||||
compat_str(v),
|
||||
restricted=self.params.get('restrictfilenames'),
|
||||
is_id=(k == 'id' or k.endswith('_id')))
|
||||
template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
|
||||
for k, v in template_dict.items()
|
||||
if v is not None and not isinstance(v, (list, tuple, dict)))
|
||||
template_dict = collections.defaultdict(lambda: 'NA', template_dict)
|
||||
|
||||
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
|
||||
|
||||
# For fields playlist_index and autonumber convert all occurrences
|
||||
# of %(field)s to %(field)0Nd for backward compatibility
|
||||
field_size_compat_map = {
|
||||
'playlist_index': len(str(template_dict['n_entries'])),
|
||||
'autonumber': autonumber_size,
|
||||
}
|
||||
FIELD_SIZE_COMPAT_RE = r'(?<!%)%\((?P<field>autonumber|playlist_index)\)s'
|
||||
mobj = re.search(FIELD_SIZE_COMPAT_RE, outtmpl)
|
||||
if mobj:
|
||||
outtmpl = re.sub(
|
||||
FIELD_SIZE_COMPAT_RE,
|
||||
r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
|
||||
outtmpl)
|
||||
|
||||
# Missing numeric fields used together with integer presentation types
|
||||
# in format specification will break the argument substitution since
|
||||
# string 'NA' is returned for missing fields. We will patch output
|
||||
# template for missing fields to meet string presentation type.
|
||||
for numeric_field in self._NUMERIC_FIELDS:
|
||||
if numeric_field not in template_dict:
|
||||
# As of [1] format syntax is:
|
||||
# %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
|
||||
# 1. https://docs.python.org/2/library/stdtypes.html#string-formatting
|
||||
FORMAT_RE = r'''(?x)
|
||||
(?<!%)
|
||||
%
|
||||
\({0}\) # mapping key
|
||||
(?:[#0\-+ ]+)? # conversion flags (optional)
|
||||
(?:\d+)? # minimum field width (optional)
|
||||
(?:\.\d+)? # precision (optional)
|
||||
[hlL]? # length modifier (optional)
|
||||
[diouxXeEfFgGcrs%] # conversion type
|
||||
'''
|
||||
outtmpl = re.sub(
|
||||
FORMAT_RE.format(numeric_field),
|
||||
r'%({0})s'.format(numeric_field), outtmpl)
|
||||
|
||||
# expand_path translates '%%' into '%' and '$$' into '$'
|
||||
# correspondingly that is not what we want since we need to keep
|
||||
# '%%' intact for template dict substitution step. Working around
|
||||
# with boundary-alike separator hack.
|
||||
sep = ''.join([random.choice(ascii_letters) for _ in range(32)])
|
||||
outtmpl = outtmpl.replace('%%', '%{0}%'.format(sep)).replace('$$', '${0}$'.format(sep))
|
||||
|
||||
# outtmpl should be expand_path'ed before template dict substitution
|
||||
# because meta fields may contain env variables we don't want to
|
||||
# be expanded. For example, for outtmpl "%(title)s.%(ext)s" and
|
||||
# title "Hello $PATH", we don't want `$PATH` to be expanded.
|
||||
filename = expand_path(outtmpl).replace(sep, '') % template_dict
|
||||
|
||||
# Temporary fix for #4787
|
||||
# 'Treat' all problem characters by passing filename through preferredencoding
|
||||
# to workaround encoding issues with subprocess on python2 @ Windows
|
||||
if sys.version_info < (3, 0) and sys.platform == 'win32':
|
||||
filename = encodeFilename(filename, True).decode(preferredencoding())
|
||||
return sanitize_path(filename)
|
||||
except ValueError as err:
|
||||
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
|
||||
return None
|
||||
|
||||
def _match_entry(self, info_dict, incomplete):
|
||||
""" Returns None iff the file should be downloaded """
|
||||
|
||||
video_title = info_dict.get('title', info_dict.get('id', 'video'))
|
||||
if 'title' in info_dict:
|
||||
# This can happen when we're just evaluating the playlist
|
||||
title = info_dict['title']
|
||||
matchtitle = self.params.get('matchtitle', False)
|
||||
if matchtitle:
|
||||
if not re.search(matchtitle, title, re.IGNORECASE):
|
||||
return '"' + title + '" title did not match pattern "' + matchtitle + '"'
|
||||
rejecttitle = self.params.get('rejecttitle', False)
|
||||
if rejecttitle:
|
||||
if re.search(rejecttitle, title, re.IGNORECASE):
|
||||
return '"' + title + '" title matched reject pattern "' + rejecttitle + '"'
|
||||
date = info_dict.get('upload_date')
|
||||
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)
|
||||
view_count = info_dict.get('view_count')
|
||||
if view_count is not None:
|
||||
min_views = self.params.get('min_views')
|
||||
if min_views is not None and view_count < min_views:
|
||||
return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views)
|
||||
max_views = self.params.get('max_views')
|
||||
if max_views is not None and view_count > max_views:
|
||||
return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
|
||||
if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
|
||||
return 'Skipping "%s" because it is age restricted' % video_title
|
||||
if self.in_download_archive(info_dict):
|
||||
return '%s has already been recorded in archive' % video_title
|
||||
|
||||
if not incomplete:
|
||||
match_filter = self.params.get('match_filter')
|
||||
if match_filter is not None:
|
||||
ret = match_filter(info_dict)
|
||||
if ret is not None:
|
||||
return ret
|
||||
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def add_extra_info(info_dict, extra_info):
|
||||
'''Set the keys from extra_info in info dict if they are missing'''
|
||||
for key, value in extra_info.items():
|
||||
info_dict.setdefault(key, value)
|
||||
|
||||
def extract_info(self, url, download=True, ie_key=None, extra_info={},
|
||||
process=True, force_generic_extractor=False):
|
||||
'''
|
||||
Returns a list with a dictionary for each video we find.
|
||||
If 'download', also downloads the videos.
|
||||
extra_info is a dict containing the extra values to add to each result
|
||||
'''
|
||||
|
||||
if not ie_key and force_generic_extractor:
|
||||
ie_key = 'Generic'
|
||||
|
||||
if ie_key:
|
||||
ies = [self.get_info_extractor(ie_key)]
|
||||
else:
|
||||
ies = self._ies
|
||||
|
||||
for ie in ies:
|
||||
if not ie.suitable(url):
|
||||
continue
|
||||
|
||||
ie = self.get_info_extractor(ie.ie_key())
|
||||
if not ie.working():
|
||||
self.report_warning('The program functionality for this site has been marked as broken, '
|
||||
'and will probably not work.')
|
||||
|
||||
try:
|
||||
ie_result = ie.extract(url)
|
||||
if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
|
||||
break
|
||||
if isinstance(ie_result, list):
|
||||
# Backwards compatibility: old IE result format
|
||||
ie_result = {
|
||||
'_type': 'compat_list',
|
||||
'entries': ie_result,
|
||||
}
|
||||
self.add_default_extra_info(ie_result, ie, url)
|
||||
if process:
|
||||
return self.process_ie_result(ie_result, download, extra_info)
|
||||
else:
|
||||
return ie_result
|
||||
except GeoRestrictedError as e:
|
||||
msg = e.msg
|
||||
if e.countries:
|
||||
msg += '\nThis video is available in %s.' % ', '.join(
|
||||
map(ISO3166Utils.short2full, e.countries))
|
||||
msg += '\nYou might want to use a VPN or a proxy server (with --proxy) to workaround.'
|
||||
self.report_error(msg)
|
||||
break
|
||||
except ExtractorError as e: # An error we somewhat expected
|
||||
self.report_error(compat_str(e), e.format_traceback())
|
||||
break
|
||||
except MaxDownloadsReached:
|
||||
raise
|
||||
except Exception as e:
|
||||
if self.params.get('ignoreerrors', False):
|
||||
self.report_error(error_to_compat_str(e), tb=encode_compat_str(traceback.format_exc()))
|
||||
break
|
||||
else:
|
||||
raise
|
||||
else:
|
||||
self.report_error('no suitable InfoExtractor for URL %s' % url)
|
||||
|
||||
def add_default_extra_info(self, ie_result, ie, url):
|
||||
self.add_extra_info(ie_result, {
|
||||
'extractor': ie.IE_NAME,
|
||||
'webpage_url': url,
|
||||
'webpage_url_basename': url_basename(url),
|
||||
'extractor_key': ie.ie_key(),
|
||||
})
|
||||
|
||||
def process_ie_result(self, ie_result, download=True, extra_info={}):
|
||||
"""
|
||||
Take the result of the ie(may be modified) and resolve all unresolved
|
||||
references (URLs, playlist items).
|
||||
|
||||
It will also download the videos if 'download'.
|
||||
Returns the resolved ie_result.
|
||||
"""
|
||||
result_type = ie_result.get('_type', 'video')
|
||||
|
||||
if result_type in ('url', 'url_transparent'):
|
||||
ie_result['url'] = sanitize_url(ie_result['url'])
|
||||
extract_flat = self.params.get('extract_flat', False)
|
||||
if ((extract_flat == 'in_playlist' and 'playlist' in extra_info)
|
||||
or extract_flat is True):
|
||||
self.__forced_printings(
|
||||
ie_result, self.prepare_filename(ie_result),
|
||||
incomplete=True)
|
||||
return ie_result
|
||||
|
||||
if result_type == 'video':
|
||||
self.add_extra_info(ie_result, extra_info)
|
||||
return self.process_video_result(ie_result, download=download)
|
||||
elif result_type == 'url':
|
||||
# We have to add extra_info to the results because it may be
|
||||
# contained in a playlist
|
||||
return self.extract_info(ie_result['url'],
|
||||
download,
|
||||
ie_key=ie_result.get('ie_key'),
|
||||
extra_info=extra_info)
|
||||
elif result_type == 'url_transparent':
|
||||
# Use the information from the embedding page
|
||||
info = self.extract_info(
|
||||
ie_result['url'], ie_key=ie_result.get('ie_key'),
|
||||
extra_info=extra_info, download=False, process=False)
|
||||
|
||||
# extract_info may return None when ignoreerrors is enabled and
|
||||
# extraction failed with an error, don't crash and return early
|
||||
# in this case
|
||||
if not info:
|
||||
return info
|
||||
|
||||
force_properties = dict(
|
||||
(k, v) for k, v in ie_result.items() if v is not None)
|
||||
for f in ('_type', 'url', 'id', 'extractor', 'extractor_key', 'ie_key'):
|
||||
if f in force_properties:
|
||||
del force_properties[f]
|
||||
new_result = info.copy()
|
||||
new_result.update(force_properties)
|
||||
|
||||
# Extracted info may not be a video result (i.e.
|
||||
# info.get('_type', 'video') != video) but rather an url or
|
||||
# url_transparent. In such cases outer metadata (from ie_result)
|
||||
# should be propagated to inner one (info). For this to happen
|
||||
# _type of info should be overridden with url_transparent. This
|
||||
# fixes issue from https://github.com/ytdl-org/youtube-dl/pull/11163.
|
||||
if new_result.get('_type') == 'url':
|
||||
new_result['_type'] = 'url_transparent'
|
||||
|
||||
return self.process_ie_result(
|
||||
new_result, download=download, extra_info=extra_info)
|
||||
elif result_type in ('playlist', 'multi_video'):
|
||||
# We process each entry in the playlist
|
||||
playlist = ie_result.get('title') or ie_result.get('id')
|
||||
self.to_screen('[download] Downloading playlist: %s' % playlist)
|
||||
|
||||
playlist_results = []
|
||||
|
||||
playliststart = self.params.get('playliststart', 1) - 1
|
||||
playlistend = self.params.get('playlistend')
|
||||
# For backwards compatibility, interpret -1 as whole list
|
||||
if playlistend == -1:
|
||||
playlistend = None
|
||||
|
||||
playlistitems_str = self.params.get('playlist_items')
|
||||
playlistitems = None
|
||||
if playlistitems_str is not None:
|
||||
def iter_playlistitems(format):
|
||||
for string_segment in format.split(','):
|
||||
if '-' in string_segment:
|
||||
start, end = string_segment.split('-')
|
||||
for item in range(int(start), int(end) + 1):
|
||||
yield int(item)
|
||||
else:
|
||||
yield int(string_segment)
|
||||
playlistitems = orderedSet(iter_playlistitems(playlistitems_str))
|
||||
|
||||
ie_entries = ie_result['entries']
|
||||
|
||||
def make_playlistitems_entries(list_ie_entries):
|
||||
num_entries = len(list_ie_entries)
|
||||
return [
|
||||
list_ie_entries[i - 1] for i in playlistitems
|
||||
if -num_entries <= i - 1 < num_entries]
|
||||
|
||||
def report_download(num_entries):
|
||||
self.to_screen(
|
||||
'[%s] playlist %s: Downloading %d videos' %
|
||||
(ie_result['extractor'], playlist, num_entries))
|
||||
|
||||
if isinstance(ie_entries, list):
|
||||
n_all_entries = len(ie_entries)
|
||||
if playlistitems:
|
||||
entries = make_playlistitems_entries(ie_entries)
|
||||
else:
|
||||
entries = ie_entries[playliststart:playlistend]
|
||||
n_entries = len(entries)
|
||||
self.to_screen(
|
||||
'[%s] playlist %s: Collected %d video ids (downloading %d of them)' %
|
||||
(ie_result['extractor'], playlist, n_all_entries, n_entries))
|
||||
elif isinstance(ie_entries, PagedList):
|
||||
if playlistitems:
|
||||
entries = []
|
||||
for item in playlistitems:
|
||||
entries.extend(ie_entries.getslice(
|
||||
item - 1, item
|
||||
))
|
||||
else:
|
||||
entries = ie_entries.getslice(
|
||||
playliststart, playlistend)
|
||||
n_entries = len(entries)
|
||||
report_download(n_entries)
|
||||
else: # iterable
|
||||
if playlistitems:
|
||||
entries = make_playlistitems_entries(list(itertools.islice(
|
||||
ie_entries, 0, max(playlistitems))))
|
||||
else:
|
||||
entries = list(itertools.islice(
|
||||
ie_entries, playliststart, playlistend))
|
||||
n_entries = len(entries)
|
||||
report_download(n_entries)
|
||||
|
||||
if self.params.get('playlistreverse', False):
|
||||
entries = entries[::-1]
|
||||
|
||||
if self.params.get('playlistrandom', False):
|
||||
random.shuffle(entries)
|
||||
|
||||
x_forwarded_for = ie_result.get('__x_forwarded_for_ip')
|
||||
|
||||
for i, entry in enumerate(entries, 1):
|
||||
self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
|
||||
# This __x_forwarded_for_ip thing is a bit ugly but requires
|
||||
# minimal changes
|
||||
if x_forwarded_for:
|
||||
entry['__x_forwarded_for_ip'] = x_forwarded_for
|
||||
extra = {
|
||||
'n_entries': n_entries,
|
||||
'playlist': playlist,
|
||||
'playlist_id': ie_result.get('id'),
|
||||
'playlist_title': ie_result.get('title'),
|
||||
'playlist_uploader': ie_result.get('uploader'),
|
||||
'playlist_uploader_id': ie_result.get('uploader_id'),
|
||||
'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
|
||||
'extractor': ie_result['extractor'],
|
||||
'webpage_url': ie_result['webpage_url'],
|
||||
'webpage_url_basename': url_basename(ie_result['webpage_url']),
|
||||
'extractor_key': ie_result['extractor_key'],
|
||||
}
|
||||
|
||||
reason = self._match_entry(entry, incomplete=True)
|
||||
if reason is not None:
|
||||
self.to_screen('[download] ' + reason)
|
||||
continue
|
||||
|
||||
entry_result = self.process_ie_result(entry,
|
||||
download=download,
|
||||
extra_info=extra)
|
||||
playlist_results.append(entry_result)
|
||||
ie_result['entries'] = playlist_results
|
||||
self.to_screen('[download] Finished downloading playlist: %s' % playlist)
|
||||
return ie_result
|
||||
elif result_type == 'compat_list':
|
||||
self.report_warning(
|
||||
'Extractor %s returned a compat_list result. '
|
||||
'It needs to be updated.' % ie_result.get('extractor'))
|
||||
|
||||
def _fixup(r):
|
||||
self.add_extra_info(
|
||||
r,
|
||||
{
|
||||
'extractor': ie_result['extractor'],
|
||||
'webpage_url': ie_result['webpage_url'],
|
||||
'webpage_url_basename': url_basename(ie_result['webpage_url']),
|
||||
'extractor_key': ie_result['extractor_key'],
|
||||
}
|
||||
)
|
||||
return r
|
||||
ie_result['entries'] = [
|
||||
self.process_ie_result(_fixup(r), download, extra_info)
|
||||
for r in ie_result['entries']
|
||||
]
|
||||
return ie_result
|
||||
else:
|
||||
raise Exception('Invalid result type: %s' % result_type)
|
||||
|
||||
def _build_format_filter(self, filter_spec):
|
||||
" Returns a function to filter the formats according to the filter_spec "
|
||||
|
||||
OPERATORS = {
|
||||
'<': operator.lt,
|
||||
'<=': operator.le,
|
||||
'>': operator.gt,
|
||||
'>=': operator.ge,
|
||||
'=': operator.eq,
|
||||
'!=': operator.ne,
|
||||
}
|
||||
operator_rex = re.compile(r'''(?x)\s*
|
||||
(?P<key>width|height|tbr|abr|vbr|asr|filesize|filesize_approx|fps)
|
||||
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
|
||||
(?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
|
||||
$
|
||||
''' % '|'.join(map(re.escape, OPERATORS.keys())))
|
||||
m = operator_rex.search(filter_spec)
|
||||
if m:
|
||||
try:
|
||||
comparison_value = int(m.group('value'))
|
||||
except ValueError:
|
||||
comparison_value = parse_filesize(m.group('value'))
|
||||
if comparison_value is None:
|
||||
comparison_value = parse_filesize(m.group('value') + 'B')
|
||||
if comparison_value is None:
|
||||
raise ValueError(
|
||||
'Invalid value %r in format specification %r' % (
|
||||
m.group('value'), filter_spec))
|
||||
op = OPERATORS[m.group('op')]
|
||||
|
||||
if not m:
|
||||
STR_OPERATORS = {
|
||||
'=': operator.eq,
|
||||
'^=': lambda attr, value: attr.startswith(value),
|
||||
'$=': lambda attr, value: attr.endswith(value),
|
||||
'*=': lambda attr, value: value in attr,
|
||||
}
|
||||
str_operator_rex = re.compile(r'''(?x)
|
||||
\s*(?P<key>ext|acodec|vcodec|container|protocol|format_id)
|
||||
\s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?
|
||||
\s*(?P<value>[a-zA-Z0-9._-]+)
|
||||
\s*$
|
||||
''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
|
||||
m = str_operator_rex.search(filter_spec)
|
||||
if m:
|
||||
comparison_value = m.group('value')
|
||||
str_op = STR_OPERATORS[m.group('op')]
|
||||
if m.group('negation'):
|
||||
op = lambda attr, value: not str_op(attr, value)
|
||||
else:
|
||||
op = str_op
|
||||
|
||||
if not m:
|
||||
raise ValueError('Invalid filter specification %r' % filter_spec)
|
||||
|
||||
def _filter(f):
|
||||
actual_value = f.get(m.group('key'))
|
||||
if actual_value is None:
|
||||
return m.group('none_inclusive')
|
||||
return op(actual_value, comparison_value)
|
||||
return _filter
|
||||
|
||||
def _default_format_spec(self, info_dict, download=True):
|
||||
|
||||
def can_merge():
|
||||
merger = FFmpegMergerPP(self)
|
||||
return merger.available and merger.can_merge()
|
||||
|
||||
def prefer_best():
|
||||
if self.params.get('simulate', False):
|
||||
return False
|
||||
if not download:
|
||||
return False
|
||||
if self.params.get('outtmpl', DEFAULT_OUTTMPL) == '-':
|
||||
return True
|
||||
if info_dict.get('is_live'):
|
||||
return True
|
||||
if not can_merge():
|
||||
return True
|
||||
return False
|
||||
|
||||
req_format_list = ['bestvideo+bestaudio', 'best']
|
||||
if prefer_best():
|
||||
req_format_list.reverse()
|
||||
return '/'.join(req_format_list)
|
||||
|
||||
def build_format_selector(self, format_spec):
|
||||
def syntax_error(note, start):
|
||||
message = (
|
||||
'Invalid format specification: '
|
||||
'{0}\n\t{1}\n\t{2}^'.format(note, format_spec, ' ' * start[1]))
|
||||
return SyntaxError(message)
|
||||
|
||||
PICKFIRST = 'PICKFIRST'
|
||||
MERGE = 'MERGE'
|
||||
SINGLE = 'SINGLE'
|
||||
GROUP = 'GROUP'
|
||||
FormatSelector = collections.namedtuple('FormatSelector', ['type', 'selector', 'filters'])
|
||||
|
||||
def _parse_filter(tokens):
|
||||
filter_parts = []
|
||||
for type, string, start, _, _ in tokens:
|
||||
if type == tokenize.OP and string == ']':
|
||||
return ''.join(filter_parts)
|
||||
else:
|
||||
filter_parts.append(string)
|
||||
|
||||
def _remove_unused_ops(tokens):
|
||||
# Remove operators that we don't use and join them with the surrounding strings
|
||||
# for example: '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 == '[':
|
||||
if last_string:
|
||||
yield tokenize.NAME, last_string, last_start, last_end, last_line
|
||||
last_string = None
|
||||
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 == ']':
|
||||
break
|
||||
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
|
||||
elif type in [tokenize.NAME, tokenize.NUMBER, tokenize.OP]:
|
||||
if not last_string:
|
||||
last_string = string
|
||||
last_start = start
|
||||
last_end = end
|
||||
else:
|
||||
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:
|
||||
# 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, [])
|
||||
elif type == tokenize.OP:
|
||||
if string == ')':
|
||||
if not inside_group:
|
||||
# ')' will be handled by the parentheses group
|
||||
tokens.restore_last_token()
|
||||
break
|
||||
elif inside_merge and string in ['/', ',']:
|
||||
tokens.restore_last_token()
|
||||
break
|
||||
elif inside_choice and string == ',':
|
||||
tokens.restore_last_token()
|
||||
break
|
||||
elif string == ',':
|
||||
if not current_selector:
|
||||
raise syntax_error('"," must follow a format selector', start)
|
||||
selectors.append(current_selector)
|
||||
current_selector = None
|
||||
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 == '[':
|
||||
if not current_selector:
|
||||
current_selector = FormatSelector(SINGLE, 'best', [])
|
||||
format_filter = _parse_filter(tokens)
|
||||
current_selector.filters.append(format_filter)
|
||||
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 == '+':
|
||||
video_selector = current_selector
|
||||
audio_selector = _parse_format_selection(tokens, inside_merge=True)
|
||||
if not video_selector or not audio_selector:
|
||||
raise syntax_error('"+" must be between two format selectors', start)
|
||||
current_selector = FormatSelector(MERGE, (video_selector, audio_selector), [])
|
||||
else:
|
||||
raise syntax_error('Operator not recognized: "{0}"'.format(string), start)
|
||||
elif type == tokenize.ENDMARKER:
|
||||
break
|
||||
if current_selector:
|
||||
selectors.append(current_selector)
|
||||
return selectors
|
||||
|
||||
def _build_selector_function(selector):
|
||||
if isinstance(selector, list):
|
||||
fs = [_build_selector_function(s) for s in selector]
|
||||
|
||||
def selector_function(ctx):
|
||||
for f in fs:
|
||||
for format in f(ctx):
|
||||
yield format
|
||||
return selector_function
|
||||
elif selector.type == GROUP:
|
||||