Simple bash-script for searching raw HTML sources
Simple bash-script for searching raw HTML sources
Uses Unix's Commons: awk, grep, head, tail

Will run for cygWin (winOS) as well, but make sure
you've got the path right to your archive (arcDir)



#!/bin/bash


# Local archive folder
# --> Edit here for your own local path
arcDir="/pathto/archives/8chan/qresearch/.zfs/snapshot/grab-n-snap-20190713-0227/qresearch/res"
# For CygWin, path could be for example:
# arcDir="/cygdrive/D/archive/pol/res"

# SearchTerm provided by user -- make sure it's there and not too short
srcTerm="${1}"
if [ "${srcTerm}" == "" ]; then
echo "Script searches for expressions in a HTML-archive"
echo "No search term given -- script will exit. Next time"
echo "try e.g.: ./searchArchive \"puzzle ever\""
exit
else
if [ $(echo -n "${srcTerm}" | wc | awk '{print $3}') -eq 1 ]; then
echo "# Search term is 1 character long -- that's not smart..."
echo "# Script refuses to search for \"${srcTerm}\""
exit
elif [ $(echo -n "${srcTerm}" | wc | awk '{print $3}') -le 3 ]; then
echo "# Warning! Length of search term is /dev/null | wc -l


if [ ${nf} -eq 0 ]; then
echo "# Error! No HTML-files found in \"${arcDir}\""
echo "# Please check if archivePath (\"arcDir=...\") is set correct."
exit
fi
echo "# Searching for \"${srcTerm}\" in \"${arcDir}\" (${nf} files)"

# TempFile and store all HTML-files in there
tmp="tmp.log"
ls ${arcDir}/*.html > ${tmp}

# Make some substitutions in searchTerm, like escaping spaces & "."
srcstr=

echo "${srcTerm}" | sed 's/\ /\\\ /g' | sed 's/\./\\\./g'



# Read tempFile line by line
while read ifile; do
# Count number of occurrences in current source file
n=

cat "${ifile}" | grep -iob "${srcstr}" | wc -l


# If count is > 0, list occurrences
if [ ${n} -gt 0 ]; then
echo ">${n} occurrences in \"${ifile}\":"
j=0
for off in

cat "${ifile}" | grep -iob "${srcstr}" | awk -F":" '{print $1+1}' | tr '\n' ' '

; do
j=

expr $j + 1


echo -n " (${j}) "
tail -c+${off} "${ifile}" | head -c640
echo ""
done
fi
done