Download yourself a Bible

downloadbible.sh

#!/bin/bash
bib=$1
bas=$2
bookfile=`tempfile`
versefile=`tempfile`
[ -z "$bib" ] && bib="acf"
[ -z "$bas" ] && bas="http://www.bibliaonline.com.br/"
mkdir -p "/tmp/$bib"
echo "cd \"/tmp/$bib\"" > $bookfile
echo "DOWNLOAD BOOK INDEX"
curl "$bas$bib" | grep ".*book=.*$bas$bib" >> $bookfile
sed -i "s/^.* href='/wget /" $bookfile
sed -i "s/'.*$//" $bookfile
cd "/tmp/$bib"
echo "REMOVE OLD FILES"
rm /tmp/$bib/*
echo "DOWNLOAD CHAPTER INDEX"
bash $bookfile
grep -E ">[0-9]{1,3}<" * > $versefile
sed -i "s/^.*href='/wget /" $versefile
sed -i "s/'.*$//" $versefile
# echo "SHOW VERSE LINKS"
# cat $versefile
echo "REMOVE CHAPTER INDEX FILES"
rm /tmp/$bib/*
echo "DOWNLOAD CHAPTERS"
bash $versefile
echo "REMOVE TEMPORARY FILES"
rm $bookfile $versefile
echo "PRUNE CHAPTERS"
for file in *
do tempfile=`tempfile`
  book=`grep '<body' $file | sed "s/^.*book='//" | sed "s/'.*$//"`
  chapter=`printf "%03d" \`grep '<body' $file | sed "s/^.*chapter='//" | sed "s/'.*$//"\``
  cat $file | awk 'BEGIN {x = 0}
    {
      if ($0 ~ "<article>") {x = 1}
      if (x == 1) {print $0}
      if ($0 ~ "</article>") {x = 0}
    }' > $tempfile
  mkdir -p /tmp/$bib/$book/
  cp $tempfile /tmp/$bib/$book/$chapter.chap.html
  rm $tempfile
done
echo "MERGE BOOKS"
for directory in */
do pandoc $directory*.chap.html --from=html --to=html -o $directory/complete.html
done
echo "ORDERING BOOKS"
nm=1
for bb in gn ex lv nm dt js jz rt 1sm 2sm 1rs 2rs 1cr 2cr ed ne et jó sl pv ec ct is jr lm ez dn os jl am ob jn mq na hc sf ag zc ml mt mc lc jo atos rm 1co 2co gl ef fp cl 1ts 2ts 1tm 2tm tt fm hb tg 1pe 2pe 1jo 2jo 3jo jd ap
do cp $bb/complete.html "`printf "%02d-$bb.html" $nm`"
  nm=$(( $nm + 1 ))
done
echo "FINAL MERGE"
pandoc -s *.html --from=html --to=html > final.html