aboutsummaryrefslogtreecommitdiffstats
path: root/yt_dlp
diff options
context:
space:
mode:
Diffstat (limited to 'yt_dlp')
-rw-r--r--yt_dlp/options.py26
-rw-r--r--yt_dlp/utils.py19
2 files changed, 23 insertions, 22 deletions
diff --git a/yt_dlp/options.py b/yt_dlp/options.py
index 85dadc7d9..fba231382 100644
--- a/yt_dlp/options.py
+++ b/yt_dlp/options.py
@@ -375,22 +375,16 @@ def parseOpts(overrideArguments=None):
'--match-filter',
metavar='FILTER', dest='match_filter', default=None,
help=(
- 'Generic video filter. '
- 'Specify any key (see "OUTPUT TEMPLATE" for a list of available keys) to '
- 'match if the key is present, '
- '!key to check if the key is not present, '
- 'key>NUMBER (like "view_count > 12", also works with '
- '>=, <, <=, !=, =) to compare against a number, '
- 'key = \'LITERAL\' (like "uploader = \'Mike Smith\'", also works with !=) '
- 'to match against a string literal '
- 'and & to require multiple matches. '
- 'Values which are not known are excluded unless you '
- 'put a question mark (?) after the operator. '
- 'For example, to only match videos that have been liked more than '
- '100 times and disliked less than 50 times (or the dislike '
- 'functionality is not available at the given service), but who '
- 'also have a description, use --match-filter '
- '"like_count > 100 & dislike_count <? 50 & description"'))
+ 'Generic video filter. Any field (see "OUTPUT TEMPLATE") can be compared with a '
+ 'number or a string using the operators defined in "Filtering formats". '
+ 'You can also simply specify a field to match if the field is present '
+ 'and "!field" to check if the field is not present. '
+ 'Multiple filters can be checked using "&". '
+ 'For example, to only match videos that are not live, '
+ 'has a like count more than 100, a dislike count less than 50 '
+ '(or the dislike field is not available), and also has a description '
+ 'that contains "python", use --match-filter "!is_live & '
+ 'like_count>100 & dislike_count<?50 & description*=\'python\'"'))
selection.add_option(
'--no-match-filter',
metavar='FILTER', dest='match_filter', action='store_const', const=None,
diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py
index f24e00b02..d06b18e00 100644
--- a/yt_dlp/utils.py
+++ b/yt_dlp/utils.py
@@ -4663,17 +4663,20 @@ def render_table(header_row, data, delim=False, extraGap=0, hideEmpty=False):
def _match_one(filter_part, dct):
+ # TODO: Generalize code with YoutubeDL._build_format_filter
COMPARISON_OPERATORS = {
'<': operator.lt,
'<=': operator.le,
'>': operator.gt,
'>=': operator.ge,
'=': operator.eq,
- '!=': operator.ne,
+ '*=': operator.contains,
+ '^=': lambda attr, value: attr.startswith(value),
+ '$=': lambda attr, value: attr.endswith(value),
}
operator_rex = re.compile(r'''(?x)\s*
(?P<key>[a-z_]+)
- \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
+ \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
(?:
(?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)|
(?P<quote>["\'])(?P<quotedstrval>(?:\\.|(?!(?P=quote)|\\).)+?)(?P=quote)|
@@ -4683,7 +4686,11 @@ def _match_one(filter_part, dct):
''' % '|'.join(map(re.escape, COMPARISON_OPERATORS.keys())))
m = operator_rex.search(filter_part)
if m:
- op = COMPARISON_OPERATORS[m.group('op')]
+ unnegated_op = COMPARISON_OPERATORS[m.group('op')]
+ if m.group('negation'):
+ op = lambda attr, value: not unnegated_op(attr, value)
+ else:
+ op = unnegated_op
actual_value = dct.get(m.group('key'))
if (m.group('quotedstrval') is not None
or m.group('strval') is not None
@@ -4693,14 +4700,14 @@ def _match_one(filter_part, dct):
# https://github.com/ytdl-org/youtube-dl/issues/11082).
or actual_value is not None and m.group('intval') is not None
and isinstance(actual_value, compat_str)):
- if m.group('op') not in ('=', '!='):
- raise ValueError(
- 'Operator %s does not support string values!' % m.group('op'))
comparison_value = m.group('quotedstrval') or m.group('strval') or m.group('intval')
quote = m.group('quote')
if quote is not None:
comparison_value = comparison_value.replace(r'\%s' % quote, quote)
else:
+ if m.group('op') in ('*=', '^=', '$='):
+ raise ValueError(
+ 'Operator %s only supports string values!' % m.group('op'))
try:
comparison_value = int(m.group('intval'))
except ValueError: