mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-24 12:15:50 +01:00
Format selector mergeall to download and merge all formats
This commit is contained in:
pukkandan
parent
3ffc7c89b0
commit
f8d4ad9ab0
14
README.md
14
README.md
@ -979,8 +979,9 @@ # FORMAT SELECTION
|
||||
You can also use special names to select particular edge case formats:
|
||||
|
||||
- `all`: Select all formats
|
||||
- `b*`, `best*`: Select the best quality format irrespective of whether it contains video or audio.
|
||||
- `w*`, `worst*`: Select the worst quality format irrespective of whether it contains video or audio.
|
||||
- `mergeall`: Select and merge all formats (Must be used with `--audio-multistreams`, `--video-multistreams` or both)
|
||||
- `b*`, `best*`: Select the best quality format irrespective of whether it contains video or audio
|
||||
- `w*`, `worst*`: Select the worst quality format irrespective of whether it contains video or audio
|
||||
- `b`, `best`: Select the best quality format that contains both video and audio. Equivalent to `best*[vcodec!=none][acodec!=none]`
|
||||
- `w`, `worst`: Select the worst quality format that contains both video and audio. Equivalent to `worst*[vcodec!=none][acodec!=none]`
|
||||
- `bv`, `bestvideo`: Select the best quality video-only format. Equivalent to `best*[acodec=none]`
|
||||
@ -1094,10 +1095,17 @@ # For this case, an output template should be used since
|
||||
# by default, bestvideo and bestaudio will have the same file name.
|
||||
$ yt-dlp -f 'bv,ba' -o '%(title)s.f%(format_id)s.%(ext)s'
|
||||
|
||||
# Download and merge the best format that has a video stream,
|
||||
# and all audio-only formats into one file
|
||||
$ yt-dlp -f 'bv*+mergeall[vcodec=none]' --audio-multistreams
|
||||
|
||||
# Download and merge the best format that has a video stream,
|
||||
# and the best 2 audio-only formats into one file
|
||||
$ yt-dlp -f 'bv*+ba+ba.2' --audio-multistreams
|
||||
|
||||
|
||||
# The following examples show the old method (without -S) of format selection
|
||||
# and how to use -S to achieve a similar but better result
|
||||
# and how to use -S to achieve a similar but (generally) better result
|
||||
|
||||
# Download the worst video available (old method)
|
||||
$ yt-dlp -f 'wv*+wa/w'
|
||||
|
||||
@ -1541,83 +1541,6 @@ def _parse_format_selection(tokens, inside_merge=False, inside_choice=False, ins
|
||||
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: # ()
|
||||
selector_function = _build_selector_function(selector.selector)
|
||||
|
||||
elif selector.type == PICKFIRST: # /
|
||||
fs = [_build_selector_function(s) for s in selector.selector]
|
||||
|
||||
def selector_function(ctx):
|
||||
for f in fs:
|
||||
picked_formats = list(f(ctx))
|
||||
if picked_formats:
|
||||
return picked_formats
|
||||
return []
|
||||
|
||||
elif selector.type == SINGLE: # atom
|
||||
format_spec = selector.selector if selector.selector is not None else 'best'
|
||||
|
||||
if format_spec == 'all':
|
||||
def selector_function(ctx):
|
||||
formats = list(ctx['formats'])
|
||||
if formats:
|
||||
for f in formats:
|
||||
yield f
|
||||
|
||||
else:
|
||||
format_fallback = False
|
||||
mobj = re.match(
|
||||
r'(?P<bw>best|worst|b|w)(?P<type>video|audio|v|a)?(?P<mod>\*)?(?:\.(?P<n>[1-9]\d*))?$',
|
||||
format_spec)
|
||||
if mobj is not None:
|
||||
format_idx = int_or_none(mobj.group('n'), default=1)
|
||||
format_idx = format_idx - 1 if mobj.group('bw')[0] == 'w' else -format_idx
|
||||
format_type = (mobj.group('type') or [None])[0]
|
||||
not_format_type = {'v': 'a', 'a': 'v'}.get(format_type)
|
||||
format_modified = mobj.group('mod') is not None
|
||||
|
||||
format_fallback = not format_type and not format_modified # for b, w
|
||||
filter_f = (
|
||||
(lambda f: f.get('%scodec' % format_type) != 'none')
|
||||
if format_type and format_modified # bv*, ba*, wv*, wa*
|
||||
else (lambda f: f.get('%scodec' % not_format_type) == 'none')
|
||||
if format_type # bv, ba, wv, wa
|
||||
else (lambda f: f.get('vcodec') != 'none' and f.get('acodec') != 'none')
|
||||
if not format_modified # b, w
|
||||
else None) # b*, w*
|
||||
else:
|
||||
format_idx = -1
|
||||
filter_f = ((lambda f: f.get('ext') == format_spec)
|
||||
if format_spec in ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav'] # extension
|
||||
else (lambda f: f.get('format_id') == format_spec)) # id
|
||||
|
||||
def selector_function(ctx):
|
||||
formats = list(ctx['formats'])
|
||||
if not formats:
|
||||
return
|
||||
matches = list(filter(filter_f, formats)) if filter_f is not None else formats
|
||||
n = len(matches)
|
||||
if -n <= format_idx < n:
|
||||
yield matches[format_idx]
|
||||
elif format_fallback and ctx['incomplete_formats']:
|
||||
# for extractors with incomplete formats (audio only (soundcloud)
|
||||
# or video only (imgur)) best/worst will fallback to
|
||||
# best/worst {video,audio}-only format
|
||||
n = len(formats)
|
||||
if -n <= format_idx < n:
|
||||
yield formats[format_idx]
|
||||
|
||||
elif selector.type == MERGE: # +
|
||||
def _merge(formats_pair):
|
||||
format_1, format_2 = formats_pair
|
||||
|
||||
@ -1678,6 +1601,91 @@ def _merge(formats_pair):
|
||||
|
||||
return new_dict
|
||||
|
||||
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: # ()
|
||||
selector_function = _build_selector_function(selector.selector)
|
||||
|
||||
elif selector.type == PICKFIRST: # /
|
||||
fs = [_build_selector_function(s) for s in selector.selector]
|
||||
|
||||
def selector_function(ctx):
|
||||
for f in fs:
|
||||
picked_formats = list(f(ctx))
|
||||
if picked_formats:
|
||||
return picked_formats
|
||||
return []
|
||||
|
||||
elif selector.type == SINGLE: # atom
|
||||
format_spec = (selector.selector if selector.selector is not None else 'best').lower()
|
||||
|
||||
# TODO: Add allvideo, allaudio etc by generalizing the code with best/worst selector
|
||||
if format_spec == 'all':
|
||||
def selector_function(ctx):
|
||||
formats = list(ctx['formats'])
|
||||
if formats:
|
||||
for f in formats:
|
||||
yield f
|
||||
elif format_spec == 'mergeall':
|
||||
def selector_function(ctx):
|
||||
formats = list(ctx['formats'])
|
||||
merged_format = formats[0]
|
||||
for f in formats[1:]:
|
||||
merged_format = _merge((merged_format, f))
|
||||
yield merged_format
|
||||
|
||||
else:
|
||||
format_fallback = False
|
||||
mobj = re.match(
|
||||
r'(?P<bw>best|worst|b|w)(?P<type>video|audio|v|a)?(?P<mod>\*)?(?:\.(?P<n>[1-9]\d*))?$',
|
||||
format_spec)
|
||||
if mobj is not None:
|
||||
format_idx = int_or_none(mobj.group('n'), default=1)
|
||||
format_idx = format_idx - 1 if mobj.group('bw')[0] == 'w' else -format_idx
|
||||
format_type = (mobj.group('type') or [None])[0]
|
||||
not_format_type = {'v': 'a', 'a': 'v'}.get(format_type)
|
||||
format_modified = mobj.group('mod') is not None
|
||||
|
||||
format_fallback = not format_type and not format_modified # for b, w
|
||||
filter_f = (
|
||||
(lambda f: f.get('%scodec' % format_type) != 'none')
|
||||
if format_type and format_modified # bv*, ba*, wv*, wa*
|
||||
else (lambda f: f.get('%scodec' % not_format_type) == 'none')
|
||||
if format_type # bv, ba, wv, wa
|
||||
else (lambda f: f.get('vcodec') != 'none' and f.get('acodec') != 'none')
|
||||
if not format_modified # b, w
|
||||
else None) # b*, w*
|
||||
else:
|
||||
format_idx = -1
|
||||
filter_f = ((lambda f: f.get('ext') == format_spec)
|
||||
if format_spec in ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav'] # extension
|
||||
else (lambda f: f.get('format_id') == format_spec)) # id
|
||||
|
||||
def selector_function(ctx):
|
||||
formats = list(ctx['formats'])
|
||||
if not formats:
|
||||
return
|
||||
matches = list(filter(filter_f, formats)) if filter_f is not None else formats
|
||||
n = len(matches)
|
||||
if -n <= format_idx < n:
|
||||
yield matches[format_idx]
|
||||
elif format_fallback and ctx['incomplete_formats']:
|
||||
# for extractors with incomplete formats (audio only (soundcloud)
|
||||
# or video only (imgur)) best/worst will fallback to
|
||||
# best/worst {video,audio}-only format
|
||||
n = len(formats)
|
||||
if -n <= format_idx < n:
|
||||
yield formats[format_idx]
|
||||
|
||||
elif selector.type == MERGE: # +
|
||||
selector_1, selector_2 = map(_build_selector_function, selector.selector)
|
||||
|
||||
def selector_function(ctx):
|
||||
|
||||
Loading…
Reference in New Issue
Block a user