#!/bin/bash

# unfinished, uncompleted ... blah blah, go away ;P
# but it works ........
# ver 0.3
# required bash.tcl ver 0.3

SED="/usr/bin/sed"
AWK="/usr/bin/awk"
GREP="/usr/bin/grep"
CAT="/usr/bin/cat"
WGET="/usr/bin/wget"
EXPAND="/usr/bin/expand"

DIR="bash_fetcher"

TMPFILE="bashtmp_url"
LINETMP="bashtxt_lines.db"
BASHTXT="bashtxt.db"
NUMBER="bashnr.db"
TIMEOUT="20"

AFTER="100"
BEFORE="100"

if [ -z $1 ]; then
	URLEND="random"
else
	URLEND="$1"
fi

$WGET -t 1 --connect-timeout=$TIMEOUT -U "Mozilla/5.0 (X11; Linux i686; U; en) Opera 8.5" -q http://bash.org.pl/$URLEND -O $DIR/$TMPFILE 2>&1 /dev/null 

$CAT $DIR/$TMPFILE \
| $GREP -A $AFTER -i '<p class="quote">' \
| $GREP -B $BEFORE -i '</p>' \
| $GREP -v -i '<p class="quote">' \
| $GREP -v -i '</p>' \
| $SED -e 's/\r//g' \
| $SED -e 's/<br \/>/\n/g' \
| $SED -e 's/&lt;/</g' \
| $SED -e 's/&gt;/>/g' \
| $SED -e 's/&quot;/"/g' \
| $SED -e "s/&#039;/'/g" \
| $SED -e 's/&nbsp;/ /g' \
| $SED -e 's/&amp;/\&/g' \
| $AWK '($0 !~ /^$/) {print $0}' | $EXPAND -t 1 | $SED 's/  //' > $DIR/$BASHTXT

$CAT $DIR/$TMPFILE | $GREP -i 'rel="nofollow">#' | $AWK '{print $3}' | $SED -e 's/rel="nofollow">#//' | $SED -e 's/<\/a>//' > $DIR/$NUMBER

$AWK 'END { print NR }' $DIR/$BASHTXT > $DIR/$LINETMP

