From 2401bfa815a5cdd5969ad802eb57ec9a24d8c79e Mon Sep 17 00:00:00 2001
From: lost <lost@negativezero.link>
Date: Tue, 9 Nov 2021 00:00:00 +0000
Subject: [PATCH] Improve generic extractor handling of /account/post format.

---
 scripts/extractors/generic.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/scripts/extractors/generic.py b/scripts/extractors/generic.py
index 8786647..c4e6a88 100644
--- a/scripts/extractors/generic.py
+++ b/scripts/extractors/generic.py
@@ -103,6 +103,13 @@ def extract_from_page (page, verbosity, url, args):
 		offset = 7
 	elif path.startswith("/users/"):
 		offset = 8
+	# set 2 as upper bound for how far out we'll go...
+	# for example, expect paths like
+	# /account/username/postid
+	# but don't try too hard with paths like
+	# /year/month/day/postid
+	elif path.count('/') > 3:
+		offset = path.find('/',1) + 1
 	else:
 		offset = 1