Improve --sub-langs (see desc)

* Treat `--sub-langs` entries as regex
* `all` can be used to refer to all the subtitles
* the language code can be prefixed with `-` to exclude it
* Deprecates `--all-subs`
Closes #253

README.md

@@ -594,15 +594,17 @@ ## Subtitle Options:
                                      (Alias: --write-automatic-subs)
     --no-write-auto-subs             Do not write auto-generated subtitles
                                      (default) (Alias: --no-write-automatic-subs)
-    --all-subs                       Download all the available subtitles of the
-                                     video
     --list-subs                      List all available subtitles for the video
     --sub-format FORMAT              Subtitle format, accepts formats
                                      preference, for example: "srt" or
                                      "ass/srt/best"
-    --sub-langs LANGS                Languages of the subtitles to download
-                                     (optional) separated by commas, use --list-
-                                     subs for available language tags
+    --sub-langs LANGS                Languages of the subtitles to download (can
+                                     be regex) or "all" separated by commas.
+                                     (Eg: --sub-langs en.*,ja) You can prefix
+                                     the language code with a "-" to exempt it
+                                     from the requested languages. (Eg: --sub-
+                                     langs all,-live_chat) Use --list-subs for a
+                                     list of available language tags
 
 ## Authentication Options:
     -u, --username USERNAME          Login with this account ID
@@ -1257,6 +1259,7 @@ # DEPRECATED OPTIONS
     -t, --title                      -o "%(title)s-%(id)s.%(ext)s"
     -l, --literal                    -o accepts literal names
     --all-formats                    -f all
+    --all-subs                       --sub-langs all --write-subs
     --autonumber-size NUMBER         Use string formatting. Eg: %(autonumber)03d
     --metadata-from-title FORMAT     --parse-metadata "%(title)s:FORMAT"
     --prefer-avconv                  avconv is no longer officially supported (Alias: --no-prefer-ffmpeg)

test/test_YoutubeDL.py

@@ -601,6 +601,26 @@ def get_info(params={}):
         self.assertTrue(subs)
         self.assertEqual(set(subs.keys()), set(['es', 'fr']))
 
+        result = get_info({'writesubtitles': True, 'subtitleslangs': ['all', '-en']})
+        subs = result['requested_subtitles']
+        self.assertTrue(subs)
+        self.assertEqual(set(subs.keys()), set(['es', 'fr']))
+
+        result = get_info({'writesubtitles': True, 'subtitleslangs': ['en', 'fr', '-en']})
+        subs = result['requested_subtitles']
+        self.assertTrue(subs)
+        self.assertEqual(set(subs.keys()), set(['fr']))
+
+        result = get_info({'writesubtitles': True, 'subtitleslangs': ['-en', 'en']})
+        subs = result['requested_subtitles']
+        self.assertTrue(subs)
+        self.assertEqual(set(subs.keys()), set(['en']))
+
+        result = get_info({'writesubtitles': True, 'subtitleslangs': ['e.+']})
+        subs = result['requested_subtitles']
+        self.assertTrue(subs)
+        self.assertEqual(set(subs.keys()), set(['es', 'en']))
+
         result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
         subs = result['requested_subtitles']
         self.assertTrue(subs)

yt_dlp/YoutubeDL.py

@@ -244,11 +244,15 @@ class YoutubeDL(object):
     writedesktoplink:  Write a Linux internet shortcut file (.desktop)
     writesubtitles:    Write the video subtitles to a file
     writeautomaticsub: Write the automatically generated subtitles to a file
-    allsubtitles:      Downloads all the subtitles of the video
+    allsubtitles:      Deprecated - Use subtitlelangs = ['all']
+                       Downloads all the subtitles of the video
                        (requires writesubtitles or writeautomaticsub)
     listsubtitles:     Lists all available subtitles for the video
     subtitlesformat:   The format code for subtitles
-    subtitleslangs:    List of languages of the subtitles to download
+    subtitleslangs:    List of languages of the subtitles to download (can be regex).
+                       The list may contain "all" to refer to all the available
+                       subtitles. The language can be prefixed with a "-" to
+                       exclude it from the requested languages. Eg: ['all', '-live_chat']
     keepvideo:         Keep the video file after post-processing
     daterange:         A DateRange object, download only if the upload_date is in the range.
     skip_download:     Skip the actual download of the video file
@@ -2038,15 +2042,28 @@ def process_subtitles(self, video_id, normal_subtitles, automatic_captions):
                 available_subs):
             return None
 
+        all_sub_langs = available_subs.keys()
         if self.params.get('allsubtitles', False):
-            requested_langs = available_subs.keys()
+            requested_langs = all_sub_langs
+        elif self.params.get('subtitleslangs', False):
+            requested_langs = set()
+            for lang in self.params.get('subtitleslangs'):
+                if lang == 'all':
+                    requested_langs.update(all_sub_langs)
+                    continue
+                discard = lang[0] == '-'
+                if discard:
+                    lang = lang[1:]
+                current_langs = filter(re.compile(lang + '$').match, all_sub_langs)
+                if discard:
+                    for lang in current_langs:
+                        requested_langs.discard(lang)
+                else:
+                    requested_langs.update(current_langs)
+        elif 'en' in available_subs:
+            requested_langs = ['en']
         else:
-            if self.params.get('subtitleslangs', False):
-                requested_langs = self.params.get('subtitleslangs')
-            elif 'en' in available_subs:
-                requested_langs = ['en']
-            else:
-                requested_langs = [list(available_subs.keys())[0]]
+            requested_langs = [list(all_sub_langs)[0]]
 
         formats_query = self.params.get('subtitlesformat', 'best')
         formats_preference = formats_query.split('/') if formats_query else []

yt_dlp/options.py

@@ -548,7 +548,7 @@ def _dict_from_multiple_values_options_callback(
     subtitles.add_option(
         '--all-subs',
         action='store_true', dest='allsubtitles', default=False,
-        help='Download all the available subtitles of the video')
+        help=optparse.SUPPRESS_HELP)
     subtitles.add_option(
         '--list-subs',
         action='store_true', dest='listsubtitles', default=False,
@@ -561,7 +561,10 @@ def _dict_from_multiple_values_options_callback(
         '--sub-langs', '--srt-langs',
         action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
         default=[], callback=_comma_separated_values_options_callback,
-        help='Languages of the subtitles to download (optional) separated by commas, use --list-subs for available language tags')
+        help=(
+            'Languages of the subtitles to download (can be regex) or "all" separated by commas. (Eg: --sub-langs en.*,ja) '
+            'You can prefix the language code with a "-" to exempt it from the requested languages. (Eg: --sub-langs all,-live_chat) '
+            'Use --list-subs for a list of available language tags'))
 
     downloader = optparse.OptionGroup(parser, 'Download Options')
     downloader.add_option(