Add article fetching to derstandard helper

This commit is contained in:
Agent 2026-02-03 21:44:57 +00:00
parent b7c5344a66
commit b603036509
2 changed files with 39 additions and 15 deletions

View file

@ -45,15 +45,20 @@ When user arrives home, HA calls the webhook. Check `memory/arrival-reminders.js
Helper script: `~/bin/derstandard`
```bash
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 items [max] # Title + URL pairs (tab-separated)
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`

View file

@ -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}"