wget -c "http://lz.book.sohu.com/serialize-id-12171.html" -O index.raw
iconv -f GBK -t UTF-8 index.raw > index.raw.utf
mv -f index.raw.utf index.raw
# find lines containing chapter links
sed -n '/<ul class="clear">/,/<\/ul>/p' index.raw | grep 'chapter.*html' > links.raw
# find links
awk -F 'href="' '{print $2}' links.raw | cut -d'"' -f1 | sed 's@^@http://lz.book.sohu.com/@' > chapterlinks.raw
# find chapter titles
awk -F '">' '{print $2}' links.raw | cut -d'<' -f1 | sed 's@$@.txt@' > chaptertitles.raw
# put links and titles together
paste chapterlinks.raw chaptertitles.raw > chapter_to_dl.raw
awk -f /Users/eickgadias/Unix/lib/awklib/download.awk chapter_to_dl.raw
for mftxt in $(ls *.txt)
do
    iconv -f GBK -t UTF-8 "$mftxt" > "$mftxt".utf
    mv -f "$mftxt".utf "$mftxt"
done
for mftxt in $(ls *.txt)
do
    sed -n '/<div .* id="txtBg">/,/<\/div>/p' "$mftxt" | grep '<p>' | sed 's/<[^>]*>//g;s/\&nbsp;\&nbsp;\&nbsp;\&nbsp;/\n/g' > "$mftxt".part
    mv -f "$mftxt".part "$mftxt"
done
for mfchpt in $(cat chaptertitles.raw)
do
    echo "$mfchpt" | sed 's/\.txt$//' >> book.txt
    echo >> book.txt
    cat "$mfchpt" >> book.txt
    echo >> book.txt
done