[YoutubeDL] Add negation support for string comparisons in format selection expressions (closes #18600, closes #18805)

This commit is contained in:
Sergey M․ 2019-01-20 13:48:09 +07:00
parent 379306ef55
commit 2cc779f497
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
3 changed files with 54 additions and 4 deletions

View File

@ -667,13 +667,14 @@ # FORMAT SELECTION
- `asr`: Audio sampling rate in Hertz - `asr`: Audio sampling rate in Hertz
- `fps`: Frame rate - `fps`: Frame rate
Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields: Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields:
- `ext`: File extension - `ext`: File extension
- `acodec`: Name of the audio codec in use - `acodec`: Name of the audio codec in use
- `vcodec`: Name of the video codec in use - `vcodec`: Name of the video codec in use
- `container`: Name of the container format - `container`: Name of the container format
- `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`) - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`)
- `format_id`: A short description of the format - `format_id`: A short description of the format
Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain).
Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster. Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.

View File

@ -239,6 +239,52 @@ def test_format_selection_video(self):
downloaded = ydl.downloaded_info_dicts[0] downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot') self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
def test_format_selection_string_ops(self):
formats = [
{'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
]
info_dict = _make_result(formats)
# equals (=)
ydl = YDL({'format': '[format_id=abc-cba]'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'abc-cba')
# does not equal (!=)
ydl = YDL({'format': '[format_id!=abc-cba]'})
self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
# starts with (^=)
ydl = YDL({'format': '[format_id^=abc]'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'abc-cba')
# does not start with (!^=)
ydl = YDL({'format': '[format_id!^=abc-cba]'})
self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
# ends with ($=)
ydl = YDL({'format': '[format_id$=cba]'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'abc-cba')
# does not end with (!$=)
ydl = YDL({'format': '[format_id!$=abc-cba]'})
self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
# contains (*=)
ydl = YDL({'format': '[format_id*=-]'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'abc-cba')
# does not contain (!*=)
ydl = YDL({'format': '[format_id!*=-]'})
self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
def test_youtube_format_selection(self): def test_youtube_format_selection(self):
order = [ order = [
'38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13', '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',

View File

@ -1063,21 +1063,24 @@ def _build_format_filter(self, filter_spec):
if not m: if not m:
STR_OPERATORS = { STR_OPERATORS = {
'=': operator.eq, '=': operator.eq,
'!=': operator.ne,
'^=': lambda attr, value: attr.startswith(value), '^=': lambda attr, value: attr.startswith(value),
'$=': lambda attr, value: attr.endswith(value), '$=': lambda attr, value: attr.endswith(value),
'*=': lambda attr, value: value in attr, '*=': lambda attr, value: value in attr,
} }
str_operator_rex = re.compile(r'''(?x) str_operator_rex = re.compile(r'''(?x)
\s*(?P<key>ext|acodec|vcodec|container|protocol|format_id) \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)? \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?
\s*(?P<value>[a-zA-Z0-9._-]+) \s*(?P<value>[a-zA-Z0-9._-]+)
\s*$ \s*$
''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
m = str_operator_rex.search(filter_spec) m = str_operator_rex.search(filter_spec)
if m: if m:
comparison_value = m.group('value') comparison_value = m.group('value')
op = STR_OPERATORS[m.group('op')] str_op = STR_OPERATORS[m.group('op')]
if m.group('negation'):
op = lambda attr, value: not str_op
else:
op = str_op
if not m: if not m:
raise ValueError('Invalid filter specification %r' % filter_spec) raise ValueError('Invalid filter specification %r' % filter_spec)