#!/bin/bash
#
# Httrack feed downloader.
#

# Configuration
source config || exit 1
MIRRORS="/var/cache/sites/arquivo/conteudo/links.sarava.org/assets"
FEED="https://links.sarava.org/rss?sort=date_desc&count=100"
TMP="/tmp/httracker"
URLS="$TMP/urls.txt"
LEVEL="1"
EXT_LEVEL="1"
FILESIZE=""
USER="arquivo"
GROUP="arquivo"

# Load functions
source lib/httracker/functions || exit 1

# Create folders
mkdir -p $MIRRORS $TMP

# Get URL
# Thanks http://stackoverflow.com/questions/443991/how-to-parse-rss-feeds-xml-in-a-shell-script
curl -s "$FEED" | grep -o '<link>[^<]*' | grep -o "[^>]*$" > $URLS

if [ "$?" != "0" ]; then
  echo "Error downloading feed $FEED, aborting."
  exit 1
fi

# Iterate over all URLs
for link in `cat $URLS | xargs`; do
  httracker_get "$link"
done

# Cleanup
rm -rf $TMP