[InfoExtractor] Support groups in _search_regex(), etc

dirkf · Jul 18, 2023 · ffcea47 · ffcea47
1 parent 6e04c30
commit ffcea47
Showing 1 changed file with 5 additions and 4 deletions.
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -1005,6 +1005,8 @@ def _search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=True, f
             if group is None:
                 # return the first matching group
                 return next(g for g in mobj.groups() if g is not None)
+            elif isinstance(group, (list, tuple)):
+                return tuple(mobj.group(g) for g in group)
             else:
                 return mobj.group(group)
         elif default is not NO_DEFAULT:
@@ -1020,10 +1022,9 @@ def _html_search_regex(self, pattern, string, name, default=NO_DEFAULT, fatal=Tr
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
         res = self._search_regex(pattern, string, name, default, fatal, flags, group)
-        if res:
-            return clean_html(res).strip()
-        else:
-            return res
+        if isinstance(res, tuple):
+            return tuple(map(clean_html, res))
+        return clean_html(res)
 
     def _get_netrc_login_info(self, netrc_machine=None):
         username = None