[urlshortener] update

docs/supportedsites.md

@@ -1276,13 +1276,13 @@ Consider all sites to be NSFW unless otherwise known.
 <tr>
     <td>Bitly</td>
     <td>https://bit.ly/</td>
-    <td></td>
+    <td>Links</td>
     <td></td>
 </tr>
 <tr>
     <td>Twitter t.co</td>
     <td>https://t.co/</td>
-    <td></td>
+    <td>Links</td>
     <td></td>
 </tr>
 

gallery_dl/extractor/urlshortener.py

@@ -4,57 +4,66 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.
 
-"""Extractor for general-purpose URL shorteners"""
+"""Extractors for general-purpose URL shorteners"""
 
 from .common import BaseExtractor, Message
 from .. import exception
 
 
 class UrlshortenerExtractor(BaseExtractor):
-    """Extractor for general-purpose URL shorteners"""
+    """Base class for URL shortener extractors"""
     basecategory = "urlshortener"
+
+
+INSTANCES = {
+    "bitly": {
+        "root": "https://bit.ly",
+        "pattern": r"bit\.ly",
+    },
+    "tco": {
+        # t.co sends 'http-equiv="refresh"' (200) when using browser UA
+        "headers": {"User-Agent": None},
+        "root": "https://t.co",
+        "pattern": r"t\.co",
+    },
+}
+
+BASE_PATTERN = UrlshortenerExtractor.update(INSTANCES)
+
+
+class UrlshortenerLinkExtractor(UrlshortenerExtractor):
+    """Extractor for general-purpose URL shorteners"""
+    subcategory = "link"
+    pattern = BASE_PATTERN + r"/([^/?&#]+)"
     test = (
         ("https://bit.ly/3cWIUgq", {
             "count": 1,
-            "pattern": "^https://gumroad.com/l/storm_b1"
+            "pattern": "^https://gumroad.com/l/storm_b1",
         }),
         ("https://t.co/bCgBY8Iv5n", {
             "count": 1,
-            "pattern": ("^https://twitter.com/elonmusk/status/"
+            "pattern": "^https://twitter.com/elonmusk/status/"
-                        "1421395561324896257/photo/1")
+                       "1421395561324896257/photo/1",
+        }),
+        ("https://t.co/abcdefghij", {
+            "exception": exception.NotFoundError,
         }),
     )
 
     def __init__(self, match):
-        BaseExtractor.__init__(self, match)
+        UrlshortenerExtractor.__init__(self, match)
-        self.headers = INSTANCES[self.category].get("headers")
         self.id = match.group(match.lastindex)
 
-    def request(self, url, **kwargs):
+        try:
-        kwargs["headers"] = self.headers
+            self.headers = INSTANCES[self.category]["headers"]
-        return BaseExtractor.request(self, url, **kwargs)
+        except Exception:
+            self.headers = None
 
     def items(self):
         response = self.request(
-            "{}/{}".format(self.root, self.id), method="HEAD",
+            "{}/{}".format(self.root, self.id), headers=self.headers,
-            allow_redirects=False, notfound="URL")
+            method="HEAD", allow_redirects=False, notfound="URL")
-        if "location" not in response.headers:
+        try:
+            yield Message.Queue, response.headers["location"], {}
+        except KeyError:
             raise exception.StopExtraction("Unable to resolve short URL")
-        yield Message.Queue, response.headers["location"], {}
-
-
-INSTANCES = {
-    "bitly": {
-        "root": "https://bit.ly",
-        "pattern": r"bit\.ly",
-    },
-    "tco": {
-        # t.co sends 'http-equiv="refresh"' (200) when using browser UA
-        "headers": {"User-Agent": None},
-        "root": "https://t.co",
-        "pattern": r"t\.co",
-    },
-}
-
-UrlshortenerExtractor.pattern = \
-    UrlshortenerExtractor.update(INSTANCES) + r"/([^/?#&]+)"