blogger-index.sh

#!/usr/bin/env bash
#
# Download an index of posts from a blogger blog
#
# Example usage: ./blogger-index techblog.netflix.com
#
# Dependencies: xml2json, jq

set -e

url="$1"

if [ -z "$url" ]; then
  echo "Usage: ./blogger-index <url>"
  exit 1
fi

urls="$(curl -s http://$url/sitemap.xml | xml2json | sed -e "s/\\$//g" | jq -r ".sitemapindex .sitemap | map(.loc) | map(.t) | .[]")"

for url in $urls; do
  curl -s "$url" | xml2json | sed -e "s/\\$//g" | jq -r ".urlset .url | map(.loc) | map(.t) | .[]" >> index.txt
done