real init

.github/workflows/push.yaml

@@ -0,0 +1,16 @@
+name: CI
+
+on:
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Run a one-line script
+        env: 
+          BOT_TOKEN: ${{ secrets.BOT_TOKEN }}
+        run: bash crawl_news.sh

crawl_news.sh

@@ -0,0 +1,42 @@
+#!/bin/bash
+
+OLD_FEED=/tmp/test.txt
+CURRENT_FEED=$(mktemp -p /tmp crawl_feed.XXX)
+BOT_TOKEN=${BOT_TOKEN:=""}
+CHANNEL_ID=${CHANNEL_ID:="@dcss_news"}
+URL="https://api.telegram.org/bot${BOT_TOKEN}/sendMessage"
+
+SHORT_COMMITS=$(mktemp -p /tmp crawl.XXXX)
+
+wget https://github.com/crawl/crawl/commits/master.atom -O /tmp/master.atom
+
+xml sel -N x=http://www.w3.org/2005/Atom -t -m "//x:entry" -v "x:content"  -v "x:link/@href" -n -o "----" -n /tmp/master.atom | sed -e 's/&amp;\|&#38;/\&/g' -e 's/&lt;\|&#60;/</g' -e 's/&gt;\|&#62;/>/g' -e 's/&quot;\|&#34;/"/g' -e "s/&apos;\|&#39;/'/g" -e 's/&nbsp;|&#160;/ /g' | grep -v '^$' | sed 's/^[ \t]*//' > $CURRENT_FEED
+
+push_news() {
+    DATA=$(echo "$1" | grep -v "^\s*$")
+    IFS=$'\n' read -rd '' HEADER LINK <<<"$DATA"
+
+    if [[ $(echo "$DATA" | wc -l ) == 2 ]]
+    then
+        # TODO: normalize the string(converting html entities)
+        echo "<a href='${LINK}'>${HEADER}</a>" >> $SHORT_COMMITS
+    else
+        curl -s -X POST "$URL" -d chat_id=$ID -d text="$1"
+    fi
+}
+
+export -f push_news
+export SHORT_COMMITS
+
+# 's/^[[:space:]]*$/\x0/'
+if [ -f "$OLD_FEED" ]
+then
+    diff $OLD_FEED $CURRENT_FEED --changed-group-format="%>" --unchanged-group-format="" | tac -s $'\n----' |   sed -e 's/----/\x0/' -e 's/<[^>]\+>//g' | xargs -0 -I{} -- bash -c 'push_news "$@"' _ {}
+else
+    sed -e 's/----/\x0/' -e 's/<[^>]\+>//g' $CURRENT_FEED | xargs -0 -I{} -- bash -c 'push_news "$@"' _ {}
+fi
+
+
+while read -r COMMIT; do
+    curl -s -X POST $URL -d chat_id=$ID -d parse_mode="HTML" -d text="$COMMIT"
+done < $SHORT_COMMITS