Option to determine extractors ahead of time

Sometimes I just want to know whether youtube-dl can be expected to handle a given URL.  This option accomplishes that quickly.  Previously, I would run youtube-dl with --simulate or --skip-download, but these would take 5+ seconds on my system before returning.  The --determine-extractors option of this PR, however, only takes 1.3 to 2.6 seconds.  You can use it, for example, to handle arbitrary URLs intelligently:  If --determine-extractor indicates success, run youtube-dl (or mpv or whatever).  Otherwise, run $BROWSER.

Thank you.

youtube_dl/__init__.py

@@ -9,6 +9,7 @@ import codecs
 import io
 import os
 import random
+import re
 import sys
 
 
@@ -123,6 +124,23 @@ def _real_main(argv=None):
         table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
         write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
         sys.exit(0)
+    if opts.determine_extractors:
+        status = 1
+        for url in all_urls:
+            if re.match(r'^[^\s/]+\.[^\s/]+/', url):  # generic.py
+                write_string('The url doesn\'t specify the protocol, trying with http\n', out=sys.stderr)
+                url = 'http://' + url
+            for ie in list_extractors(opts.age_limit):
+                if not ie._WORKING or ie.IE_NAME == 'generic':
+                    continue
+                try:
+                    if re.match(getattr(ie, '_VALID_URL'), url):
+                        write_string(ie.IE_NAME + ' ' + url + '\n', out=sys.stdout)
+                        status = 0
+                        break
+                except AttributeError:
+                    pass
+        sys.exit(status)
 
     # Conflicting, missing and erroneous options
     if opts.usenetrc and (opts.username is not None or opts.password is not None):

youtube_dl/options.py

@@ -161,6 +161,10 @@ def parseOpts(overrideArguments=None):
         '--extractor-descriptions',
         action='store_true', dest='list_extractor_descriptions', default=False,
         help='Output descriptions of all supported extractors')
+    general.add_option(
+        '--determine-extractors',
+        action='store_true', dest='determine_extractors', default=False,
+        help='List the extractor that would be used for each URL. Exit status indicates at least one successful match.')
     general.add_option(
         '--force-generic-extractor',
         action='store_true', dest='force_generic_extractor', default=False,