getAlexaCountryData.sh

#!/bin/bash

DATE=`date +%Y%m%d`

ALEXA_URL=http://www.alexa.com/topsites/countries%3B
COUNTRY_CODE=$1
OUTPUT_FILE=ALEXA_${COUNTRY_CODE}-${DATE}.txt

echo "Downloading Alexa top site data for $COUNTRY_CODE"

touch $OUTPUT_FILE

i=0
for i in {0..5}
do

curl "${ALEXA_URL}${i}/${COUNTRY_CODE}" | grep "<a href=\"/siteinfo/.*\"" | sed -r 's/.*>(.*)<.*/\1/' >> $OUTPUT_FILE
# curl "http://www.alexa.com/topsites/countries%3B0/HU" | grep "<a href=\"/siteinfo/.*\"" | sed 's/>(.*)</\"\0\"/' >> $OUTPUT_FILE
i=$i+1
done

wc -l $OUTPUT_FILE