From 3b74d490e072b58e59b16561d4736601f1c62448 Mon Sep 17 00:00:00 2001
From: Max Teegen <870074+max-te@users.noreply.github.com>
Date: Sun, 13 Jun 2021 16:25:19 +0200
Subject: [PATCH] More string operators for --match-filter

---
 README.md           | 115 ++++++++++++++++++++++++++++++++++++--------
 youtube_dl/utils.py |  10 ++--
 2 files changed, 102 insertions(+), 23 deletions(-)

diff --git a/README.md b/README.md
index 2841ed68f..cfa9e9fb3 100644
--- a/README.md
+++ b/README.md
@@ -128,6 +128,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                          CIDR notation
 
 ## Video Selection:
+<<<<<<< HEAD
     --playlist-start NUMBER              Playlist video to start at (default is
                                          1)
     --playlist-end NUMBER                Playlist video to end at (default is
@@ -160,27 +161,33 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                          than COUNT views
     --max-views COUNT                    Do not download any videos with more
                                          than COUNT views
-    --match-filter FILTER                Generic video filter. Specify any key
-                                         (see the "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
-                                         "comment_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 &
+    --match-filter FILTER                Generic video filter. Specify any key (see
+                                         the "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 "comment_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" .
+                                         For matching strings, the oparators ~= and
+                                         !~= check for string containment and
+                                         exclusion. The operators *= and !*= search
+                                         for a regular expression.
+                                         For example, to only match videos which
+                                         have neither 'sponsored' nor 'Sponsored' in
+                                         the title, use --match-filter "title !*=
+                                         '[Ss]ponsored'".
     --no-playlist                        Download only the video, if the URL
                                          refers to a video and a playlist.
     --yes-playlist                       Download the playlist, if the URL
@@ -192,6 +199,74 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                          downloaded videos in it.
     --include-ads                        Download advertisements as well
                                          (experimental)
+=======
+    --playlist-start NUMBER          Playlist video to start at (default is 1)
+    --playlist-end NUMBER            Playlist video to end at (default is last)
+    --playlist-items ITEM_SPEC       Playlist video items to download. Specify
+                                     indices of the videos in the playlist
+                                     separated by commas like: "--playlist-items
+                                     1,2,5,8" if you want to download videos
+                                     indexed 1, 2, 5, 8 in the playlist. You can
+                                     specify range: "--playlist-items
+                                     1-3,7,10-13", it will download the videos
+                                     at index 1, 2, 3, 7, 10, 11, 12 and 13.
+    --match-title REGEX              Download only matching titles (regex or
+                                     caseless sub-string)
+    --reject-title REGEX             Skip download for matching titles (regex or
+                                     caseless sub-string)
+    --max-downloads NUMBER           Abort after downloading NUMBER files
+    --min-filesize SIZE              Do not download any videos smaller than
+                                     SIZE (e.g. 50k or 44.6m)
+    --max-filesize SIZE              Do not download any videos larger than SIZE
+                                     (e.g. 50k or 44.6m)
+    --date DATE                      Download only videos uploaded in this date
+    --datebefore DATE                Download only videos uploaded on or before
+                                     this date (i.e. inclusive)
+    --dateafter DATE                 Download only videos uploaded on or after
+                                     this date (i.e. inclusive)
+    --min-views COUNT                Do not download any videos with less than
+                                     COUNT views
+    --max-views COUNT                Do not download any videos with more than
+                                     COUNT views
+    --match-filter FILTER            Generic video filter. Specify any key (see
+                                     the "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 "comment_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" .
+                                     For matching strings, the oparators ~= and
+                                     !~= check for string containment and
+                                     exclusion. The operators *= and !*= search
+                                     for a regular expression.
+                                     For example, to only match videos which
+                                     have neither 'sponsored' nor 'Sponsored' in
+                                     the title, use --match-filter "title !*=
+                                     '[Ss]ponsored'"
+    --no-playlist                    Download only the video, if the URL refers
+                                     to a video and a playlist.
+    --yes-playlist                   Download the playlist, if the URL refers to
+                                     a video and a playlist.
+    --age-limit YEARS                Download only videos suitable for the given
+                                     age
+    --download-archive FILE          Download only videos not listed in the
+                                     archive file. Record the IDs of all
+                                     downloaded videos in it.
+    --include-ads                    Download advertisements as well
+                                     (experimental)
+>>>>>>> dd954e809 (More string operators for --match-filter)
 
 ## Download Options:
     -r, --limit-rate RATE                Maximum download rate in bytes per
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index e722eed58..a774b0c9d 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -4369,6 +4369,10 @@ def _match_one(filter_part, dct):
         '>=': operator.ge,
         '=': operator.eq,
         '!=': operator.ne,
+        '~=': operator.contains,
+        '!~=': lambda left, right: not operator.contains(left, right),
+        '*=': lambda left, right: bool(re.search(right, left)),
+        '!*=': lambda left, right: not bool(re.search(right, left)),
     }
     operator_rex = re.compile(r'''(?x)\s*
         (?P<key>[a-z_]+)
@@ -4392,14 +4396,14 @@ 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: