From ff61e403df019076630f65cbbf5433c6a180f6d6 Mon Sep 17 00:00:00 2001
From: Raz Ben Yaish <razb13@gmail.com>
Date: Wed, 13 May 2026 06:27:42 +0000
Subject: [PATCH] fix(Medium RSS): capture username from <link> element

The Medium RSS schema captures fullname and image but the username field
is left empty. Adding a named-capture group for it from the <channel>'s
<link>https://medium.com/@USERNAME</link> element so the schema produces
the same fields the older Medium HTML schema did via medium_username.

Useful for --parse runs against a Medium URL, where the username has to
be discovered from the page content rather than supplied as input.
---
 socid_extractor/schemes.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/socid_extractor/schemes.py b/socid_extractor/schemes.py
index 67ec92a..7a33e01 100644
--- a/socid_extractor/schemes.py
+++ b/socid_extractor/schemes.py
@@ -798,7 +798,7 @@ def _virgool_links(user_row):
     'Medium RSS': {
         'url_hints': ('medium.com',),
         'flags': ['<rss', 'medium.com', 'Stories by'],
-        'regex': r'<title><!\[CDATA\[Stories by (?P<fullname>[^\]]+?) on Medium\]\]></title>[\s\S]*?<image>\s*<url>(?P<image>[^<]+)</url>[\s\S]*?<lastBuildDate>(?P<latest_activity_at>[^<]+)</lastBuildDate>',
+        'regex': r'<title><!\[CDATA\[Stories by (?P<fullname>[^\]]+?) on Medium\]\]></title>[\s\S]*?<link>https://medium\.com/@(?P<username>[^?/<\s]+)[\s\S]*?<image>\s*<url>(?P<image>[^<]+)</url>[\s\S]*?<lastBuildDate>(?P<latest_activity_at>[^<]+)</lastBuildDate>',
         'fields': {},
     },
     'Medium': {