Add option to list in json extractors matching URL or all extractors

yt_dlp/__init__.py

@@ -13,6 +13,7 @@ import optparse
 import os
 import re
 import traceback
+import json
 
 from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS, CookieLoadError
 from .downloader.external import get_external_downloader
@@ -119,6 +120,45 @@ def print_extractor_information(opts, urls):
         out = 'Supported TV Providers:\n{}\n'.format(render_table(
             ['mso', 'mso name'],
             [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]))
+    elif opts.list_extractors_json:
+        from .extractor.generic import GenericIE
+        dicts = []
+        e_index = 0
+        urls = dict.fromkeys(urls, False)
+        if len(urls):
+            for ie in gen_extractors():
+                if ie == GenericIE:
+                    matched_urls = [url for url, matched in urls.items() if not matched]
+                else:
+                    matched_urls = tuple(filter(ie.suitable, urls.keys()))
+                    urls.update(dict.fromkeys(matched_urls, True))
+                # show only extractor with matched URL
+                if len(matched_urls):
+                    data = {'index': e_index,
+                            'name': ie.IE_NAME,
+                            'desc': ie.IE_DESC if ie.IE_DESC else '',
+                            'working': ie.working(),
+                            'enabled': ie.is_enabled(),
+                            'return_type': ie.return_type(),
+                            'regex_url': ie.list_regex_url(),
+                            'matched_urls': matched_urls,
+                    }
+                    e_index += 1
+                    dicts.append(data)
+        else:
+            # show all extractors
+            for ie in gen_extractors():
+                data = {'index': e_index,
+                        'name': ie.IE_NAME,
+                        'desc': ie.IE_DESC if ie.IE_DESC else '',
+                        'working': ie.working(),
+                        'enabled': ie.is_enabled(),
+                        'return_type': ie.return_type(),
+                        'regex_url': ie.list_regex_url(),
+                        }
+                dicts.append(data)
+                e_index += 1
+        out = json.dumps(dicts, indent=4)
     else:
         return False
     write_string(out, out=sys.stdout)

yt_dlp/extractor/common.py

@@ -14,6 +14,7 @@ import netrc
 import os
 import random
 import re
+import string
 import subprocess
 import sys
 import time
@@ -610,6 +611,23 @@ class InfoExtractor:
         # so that lazy_extractors works correctly
         return cls._match_valid_url(url) is not None
 
+
+    @classmethod
+    def list_regex_url(cls):
+        return cls._VALID_URL if type(cls._VALID_URL) in [list, tuple] \
+            else (cls._VALID_URL.translate({ord(c): None for c in string.whitespace}),) if type(cls._VALID_URL) is str \
+            else []
+
+    @classmethod
+    def return_type(cls):
+        if '_RETURN_TYPE' not in cls.__dict__:
+            return ''
+        return cls._RETURN_TYPE
+
+    @classmethod
+    def is_enabled(cls):
+        return cls._ENABLED
+
     @classmethod
     def _match_id(cls, url):
         return cls._match_valid_url(url).group('id')

yt_dlp/options.py

@@ -362,6 +362,10 @@ def create_parser():
         '--list-extractors',
         action='store_true', dest='list_extractors', default=False,
         help='List all supported extractors and exit')
+    general.add_option(
+        '--list-extractors-json',
+        action='store_true', dest='list_extractors_json', default=False,
+        help='List all supported extractors parameters in JSON format and exit')
     general.add_option(
         '--extractor-descriptions',
         action='store_true', dest='list_extractor_descriptions', default=False,