Add regex operator and quoting to format filters (#2698)

Closes #2681
Authored by: lukasfink1

diff --git a/README.md b/README.md
index b00cdfdcb2bfbcf816ef589d3570309eb3bfe045..7446cc2c23e23ff39b9d17218a2635369ebfe32b 100644 (file)
--- a/README.md
+++ b/README.md
@@ -1399,7 +1399,7 @@ ## Filtering Formats
  - `asr`: Audio sampling rate in Hertz
  - `fps`: Frame rate
 
-Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields:
+Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains), `~=` (matches regex) and following string meta fields:
 
  - `ext`: File extension
  - `acodec`: Name of the audio codec in use
@@ -1409,7 +1409,7 @@ ## Filtering Formats
  - `format_id`: A short description of the format
  - `language`: Language code
 
-Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain).
+Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). The comparand of a string comparison needs to be quoted with either double or single quotes if it contains spaces or special characters other than `._-`.
 
 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 website. Any other field made available by the extractor can also be used for filtering.
 
@@ -1552,8 +1552,9 @@ # (https/ftps > http/ftp > m3u8_native > m3u8 > http_dash_segments ...)
 
 
 
-# Download the best video with h264 codec, or the best video if there is no such video
-$ yt-dlp -f "(bv*[vcodec^=avc1]+ba) / (bv*+ba/b)"
+# Download the best video with either h264 or h265 codec,
+# or the best video if there is no such video
+$ yt-dlp -f "(bv*[vcodec~='^((he|a)vc|h26[45])']+ba) / (bv*+ba/b)"
 
 # Download the best video with best codec no better than h264,
 # or the best video with worst codec if there is no such video

diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py
index 74684dea3f40c4453b6868370b1a3047194343f2..9892ed328e4609095be6663d288ec54e14fe7155 100644 (file)
--- a/yt_dlp/YoutubeDL.py
+++ b/yt_dlp/YoutubeDL.py
@@ -1842,15 +1842,21 @@ def _build_format_filter(self, filter_spec):
                 '^=': lambda attr, value: attr.startswith(value),
                 '$=': lambda attr, value: attr.endswith(value),
                 '*=': lambda attr, value: value in attr,
+                '~=': lambda attr, value: value.search(attr) is not None
             }
             str_operator_rex = re.compile(r'''(?x)\s*
                 (?P<key>[a-zA-Z0-9._-]+)\s*
-                (?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
-                (?P<value>[a-zA-Z0-9._-]+)\s*
+                (?P<negation>!\s*)?(?P<op>%s)\s*(?P<none_inclusive>\?\s*)?
+                (?P<quote>["'])?
+                (?P<value>(?(quote)(?:(?!(?P=quote))[^\\]|\\.)+|[\w.-]+))
+                (?(quote)(?P=quote))\s*
                 ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
             m = str_operator_rex.fullmatch(filter_spec)
             if m:
-                comparison_value = m.group('value')
+                if m.group('op') == '~=':
+                    comparison_value = re.compile(m.group('value'))
+                else:
+                    comparison_value = re.sub(r'''\\([\\"'])''', r'\1', m.group('value'))
                 str_op = STR_OPERATORS[m.group('op')]
                 if m.group('negation'):
                     op = lambda attr, value: not str_op(attr, value)