From b603036509421cbf09e0c55a5d4b29e26b2c2d63 Mon Sep 17 00:00:00 2001
From: Agent <agent@localhost>
Date: Tue, 3 Feb 2026 21:44:57 +0000
Subject: [PATCH] Add article fetching to derstandard helper

---
 TOOLS.md        | 13 +++++++++----
 bin/derstandard | 41 ++++++++++++++++++++++++++++++-----------
 2 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/TOOLS.md b/TOOLS.md
index f9d28ca..20af716 100644
--- a/TOOLS.md
+++ b/TOOLS.md
@@ -45,15 +45,20 @@ When user arrives home, HA calls the webhook. Check `memory/arrival-reminders.js
 Helper script: `~/bin/derstandard`
 
 ```bash
-derstandard urls [max]     # Article URLs only (default: 50)
-derstandard titles [max]   # Article titles only
-derstandard items [max]    # Title + URL pairs (tab-separated)
-derstandard raw [max]      # Full RSS XML
+derstandard items [max]     # Title + URL pairs (tab-separated)
+derstandard article <url>   # Full article content for a specific URL
+derstandard urls [max]      # Article URLs only (default: 50)
+derstandard titles [max]    # Article titles only
+derstandard raw [max]       # Full RSS XML
 ```
 
 - Uses internal fivefilters proxy (bypasses web_fetch private IP block)
 - Pre-processes output for minimal token usage
 
+**Workflow for news briefing:**
+1. `derstandard items` → pick interesting titles
+2. `derstandard article <url>` → get full content for selected articles
+
 ## Forgejo Git Access
 
 Helper script: `~/bin/forgejo`
diff --git a/bin/derstandard b/bin/derstandard
index 03fb0a6..0731d2f 100755
--- a/bin/derstandard
+++ b/bin/derstandard
@@ -6,7 +6,6 @@ FIVEFILTERS_URL="https://fivefilters.cloonar.com"
 FIVEFILTERS_IP="10.42.97.5"
 RSS_SOURCE="https://www.derstandard.at/rss"
 
-# Resolve to internal IP (bypasses web_fetch private IP block)
 CURL="curl -sk --resolve fivefilters.cloonar.com:443:${FIVEFILTERS_IP}"
 
 usage() {
@@ -14,10 +13,11 @@ usage() {
 Usage: derstandard <command> [args]
 
 Commands:
-  urls [max]         Extract article URLs (default: 50)
-  titles [max]       Extract article titles
-  items [max]        Title + URL pairs (tab-separated)
-  raw [max]          Raw RSS XML
+  items [max]        Title + URL pairs for selection (default: 50)
+  article <url>      Fetch full article content for a specific URL
+  urls [max]         Article URLs only
+  titles [max]       Article titles only
+  raw [max]          Full RSS XML
 EOF
 }
 
@@ -27,17 +27,36 @@ fetch_feed() {
   $CURL "${FIVEFILTERS_URL}/makefulltextfeed.php?url=${encoded_url}&max=${max}&links=preserve&exc="
 }
 
+fetch_article() {
+  local url="$1"
+  local encoded_url=$(printf '%s' "$url" | sed 's/:/%3A/g; s/\//%2F/g; s/\?/%3F/g; s/&/%26/g; s/=/%3D/g')
+  $CURL "${FIVEFILTERS_URL}/makefulltextfeed.php?url=${encoded_url}&max=1&links=preserve&exc=" | \
+    perl -0777 -ne 'print $1 if /<item>.*?<description>(.*?)<\/description>.*?<\/item>/s' | \
+    sed 's/&lt;/</g; s/&gt;/>/g; s/&quot;/"/g; s/&amp;/\&/g' | \
+    sed 's/<[^>]*>//g' | \
+    tr '\n' ' ' | sed 's/  */ /g'
+}
+
+decode_entities() {
+  sed 's/&amp;amp;/\&/g; s/&amp;/\&/g; s/&lt;/</g; s/&gt;/>/g; s/&quot;/"/g; s/&#39;/'"'"'/g'
+}
+
 case "${1:-}" in
+  items)
+    feed=$(fetch_feed "${2:-50}")
+    titles=$(echo "$feed" | grep -oP '<title>\K[^<]+' | tail -n +2 | decode_entities)
+    urls=$(echo "$feed" | grep -oP '<link>\K[^<]+' | grep "derstandard.at/story")
+    paste <(echo "$titles") <(echo "$urls") 2>/dev/null | head -"${2:-50}"
+    ;;
+  article)
+    [ -z "${2:-}" ] && { echo "Usage: derstandard article <url>"; exit 1; }
+    fetch_article "$2"
+    ;;
   urls)
     fetch_feed "${2:-50}" | grep -oP '<link>\K[^<]+' | grep "derstandard.at/story"
     ;;
   titles)
-    fetch_feed "${2:-50}" | grep -oP '<title><!\[CDATA\[\K[^\]]+' | tail -n +2
-    ;;
-  items)
-    feed=$(fetch_feed "${2:-50}")
-    paste <(echo "$feed" | grep -oP '<title><!\[CDATA\[\K[^\]]+' | tail -n +2) \
-          <(echo "$feed" | grep -oP '<link>\K[^<]+' | grep "derstandard.at/story") 2>/dev/null | head -50
+    fetch_feed "${2:-50}" | grep -oP '<title>\K[^<]+' | tail -n +2 | decode_entities
     ;;
   raw)
     fetch_feed "${2:-50}"