get_all_phenixbb.sh

get_all_phenixbb.sh

#!/usr/bin/env bash

if [[ ! -d phenixbb ]]
then
    mkdir phenixbb
fi

cd phenixbb

curl -s https://phenix-online.org/pipermail/phenixbb/ |\
    grep -o "2[0-9]\+-[A-Z][a-z]\+\.txt\.gz" |\
    while read input_url
    do
        output_txt=$(basename ${input_url} .gz |\
            sed -e 's/January/01/' \
                -e 's/February/02/' \
                -e 's/March/03/' \
                -e 's/April/04/' \
                -e 's/May/05/' \
                -e 's/June/06/' \
                -e 's/July/07/' \
                -e 's/August/08/' \
                -e 's/September/09/' \
                -e 's/October/10/' \
                -e 's/November/11/' \
                -e 's/December/12/')

        curl -s https://phenix-online.org/pipermail/phenixbb/${input_url} |\
            gunzip > ${output_txt}
    done

find . -name '????-??.txt' | sort -t- -n -k1,2 | xargs cat > phenixbb.txt
find . -name '????-??.txt' -delete
cd ..