Fetch Alexa 'Top 1,000,000' site list and munge into a list of domains only.

fetch_alexa.sh

#!/bin/bash
ALEXA_STATIC_1M="http://s3.amazonaws.com/alexa-static/top-1m.csv.zip"

echo 'Attempting to fetch Alexa Top 1M archive...'
curl -o top-1m.csv.zip -s $ALEXA_STATIC_1M
if [ $? -ne 0 ]; then
  echo 'FAILED: Count not fetch file from remote server.'
  exit -1
fi

echo 'Attempting to extract archive...'
unzip top-1m.csv.zip
if [ $? -ne 0 ]; then
  echo 'FAILED: Could not extract CSV file from archive.'
  exit -1
fi

echo 'Attempting to prepare list of domains...'
cut -d ',' -f 2 top-1m.csv > top-1m.txt
if [ $? -ne 0 ]; then
  echo 'FAILED: Could not extract domains from list.'
  exit -1
fi