#45 Allow date/time formatting in output template

Closes #43
This commit is contained in:
pukkandan 2021-02-03 02:45:00 +05:30 committed by GitHub
parent 9c3fe2ef80
commit e29663c644
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 63 additions and 23 deletions

View File

@ -751,7 +751,9 @@ # OUTPUT TEMPLATE
**tl;dr:** [navigate me to examples](#output-template-examples).
The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dlc -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Allowed names along with sequence type are:
The basic usage of `-o` is not to set any template arguments when downloading a single file, like in `youtube-dlc -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Additionally, date/time fields can be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it inside the parantheses seperated from the field name using a `>`. For example, `%(duration>%H-%M-%S)s`.
The available fields are:
- `id` (string): Video identifier
- `title` (string): Video title
@ -870,14 +872,17 @@ #### Output template examples
# Download YouTube playlist videos in separate directory indexed by video order in a playlist
$ youtube-dlc -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
# Download YouTube playlist videos in seperate directories according to their uploaded year
$ youtube-dlc -o '%(upload_date>%Y)s/%(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
# Download all playlists of YouTube channel/user keeping each playlist in separate directory:
$ youtube-dlc -o '%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/user/TheLinuxFoundation/playlists
# Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home
$ youtube-dlc -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
$ youtube-dlc -u user -p password -P '~/MyVideos' -o '%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
# Download entire series season keeping each series and each season in separate directory under C:/MyVideos
$ youtube-dlc -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" https://videomore.ru/kino_v_detalayah/5_sezon/367617
$ youtube-dlc -P "C:/MyVideos" -o "%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" https://videomore.ru/kino_v_detalayah/5_sezon/367617
# Stream the video being downloaded to stdout
$ youtube-dlc -o - BaW_jenozKc

View File

@ -61,6 +61,7 @@
ExistingVideoReached,
expand_path,
ExtractorError,
float_or_none,
format_bytes,
format_field,
formatSeconds,
@ -91,6 +92,7 @@
sanitized_Request,
std_headers,
str_or_none,
strftime_or_none,
subtitles_filename,
to_high_limit_path,
UnavailableVideoError,
@ -735,6 +737,11 @@ def prepare_filename(self, info_dict, warn=False):
try:
template_dict = dict(info_dict)
template_dict['duration_string'] = ( # %(duration>%H-%M-%S)s is wrong if duration > 24hrs
formatSeconds(info_dict['duration'], '-')
if info_dict.get('duration', None) is not None
else None)
template_dict['epoch'] = int(time.time())
autonumber_size = self.params.get('autonumber_size')
if autonumber_size is None:
@ -755,7 +762,8 @@ def prepare_filename(self, info_dict, warn=False):
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: self.params.get('outtmpl_na_placeholder', 'NA'), template_dict)
na = self.params.get('outtmpl_na_placeholder', 'NA')
template_dict = collections.defaultdict(lambda: na, template_dict)
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
@ -773,27 +781,45 @@ def prepare_filename(self, info_dict, warn=False):
r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
outtmpl)
# 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)
(?P<type>[diouxXeEfFgGcrs%]) # conversion type
'''
numeric_fields = list(self._NUMERIC_FIELDS)
# Format date
FORMAT_DATE_RE = FORMAT_RE.format(r'(?P<key>(?P<field>\w+)>(?P<format>.+?))')
for mobj in re.finditer(FORMAT_DATE_RE, outtmpl):
conv_type, field, frmt, key = mobj.group('type', 'field', 'format', 'key')
if key in template_dict:
continue
value = strftime_or_none(template_dict.get(field), frmt, na)
if conv_type in 'crs': # string
value = sanitize(field, value)
else: # number
numeric_fields.append(key)
value = float_or_none(value, default=None)
if value is not None:
template_dict[key] = value
# Missing numeric fields used together with integer presentation types
# in format specification will break the argument substitution since
# string NA placeholder 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:
for numeric_field in 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),
FORMAT_RE.format(re.escape(numeric_field)),
r'%({0})s'.format(numeric_field), outtmpl)
# expand_path translates '%%' into '%' and '$$' into '$'
@ -996,10 +1022,6 @@ def add_default_extra_info(self, ie_result, ie, url):
self.add_extra_info(ie_result, {
'extractor': ie.IE_NAME,
'webpage_url': url,
'duration_string': (
formatSeconds(ie_result['duration'], '-')
if ie_result.get('duration', None) is not None
else None),
'webpage_url_basename': url_basename(url),
'extractor_key': ie.ie_key(),
})

View File

@ -50,6 +50,7 @@
compat_html_entities_html5,
compat_http_client,
compat_integer_types,
compat_numeric_types,
compat_kwargs,
compat_os_name,
compat_parse_qs,
@ -3673,6 +3674,18 @@ def url_or_none(url):
return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
def strftime_or_none(timestamp, date_format, default=None):
datetime_object = None
try:
if isinstance(timestamp, compat_numeric_types): # unix timestamp
datetime_object = datetime.datetime.utcfromtimestamp(timestamp)
elif isinstance(timestamp, compat_str): # assume YYYYMMDD
datetime_object = datetime.datetime.strptime(timestamp, '%Y%m%d')
return datetime_object.strftime(date_format)
except (ValueError, TypeError, AttributeError):
return default
def parse_duration(s):
if not isinstance(s, compat_basestring):
return None