From 0504f6cc878aa01a6e72cc4af791881d01774231 Mon Sep 17 00:00:00 2001 From: Michal Date: Tue, 25 Aug 2026 13:21:29 +0100 Subject: [PATCH] rules: dreamwidth journals that use entry-content The community rule matches only div.usercontent; journal styles vary and diziet's (which arrives via Planet Debian) uses div.entry-content, so those posts fell through to Readability. The upstream file's own comment notes it needs converting to a wildcard. Found by the stale-rule diagnostic after a full re-import. Co-Authored-By: Claude Opus 5 (1M context) Claude-Session: https://claude.ai/code/session_011sSJdftQx5bW5HZHgUKF3i --- site_config/custom/.dreamwidth.org.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 site_config/custom/.dreamwidth.org.txt diff --git a/site_config/custom/.dreamwidth.org.txt b/site_config/custom/.dreamwidth.org.txt new file mode 100644 index 0000000..0ab1da9 --- /dev/null +++ b/site_config/custom/.dreamwidth.org.txt @@ -0,0 +1,13 @@ +# The community rule only matches div.usercontent. Dreamwidth journal styles +# vary, and diziet's (which reaches us via Planet Debian) renders the post into +# div.entry-content instead, so extraction fell through to Readability. +body: //div[contains(concat(' ', normalize-space(@class), ' '), ' usercontent ')] +body: //div[contains(concat(' ', normalize-space(@class), ' '), ' entry-content ')] + +title: //div[contains(@id, 'entrysubj')] + +strip_id_or_class: currents +strip_id_or_class: comment +strip_id_or_class: module-content + +test_url: https://diziet.dreamwidth.org/21442.html