Get all those t.co links before they're gone forever

tco.sh

#!/bin/sh
# go to the base directory of your twitter archive, ie something like twitter-YYYY-MM-DD-deadbeefcafe42069
# run this for loop:


for i in `grep -oh "https://t.co/[[:alnum:]]*" data/*.js | sort | uniq` 
do
echo $i $(curl -Is ${i} | grep location | sed -e 's/location./, /') | sed -e 's/ ,/,/' | tee -a tco.csv
done

# this will take ... a while. It will save them to a csv file called tco.csv.