## --> more createbibletext
for x in `ls *.html`
do
Y="`echo $x | awk -F. '{print $1}'`"
html2text -ascii $x | col -b | \
grep -v "King_James_Version_of_the_Bible" | \
grep -v "For questions about the Hyper-text King James Version of the Bible, please see" | \
grep -v "the FAQ. Any questions that are not covered in the FAQ should be directed to" | \
grep -v "webmaster@cforc.com." | \
grep -v "Computers_For_Christ" | sed -e '/^$/d' > TXT/$Y.txt
done
## using loop to create plain text version from HTML ##
## loop lists all files with html extension, then parses file name from extension,
## then takes and uses html2text to convert file, however file had non-printable
## characters embedded, so used col -b to filter them out... but the files
## also had several lines of information not essential to the project... since
## the KJV is not copyrighted, however the HTML code is... then removed the blank lines
## and redirected the output to a file in a different directory with a txt extension.