Last active
April 22, 2016 10:47
-
-
Save brain90/8194120 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
# Mengunduh semua lema dari kamus kateglo | |
# Author: Brain90 | |
set -vx | |
url='http://www.kateglo.com/?&mod=dictionary&' | |
# Halaman maksimum untuk tiap entri | |
declare -A entri | |
entri[a]=66 entri[b]=160 entri[c]=31 entri[d]=47 entri[e]=24 entri[f]=11 | |
entri[g]=46 entri[h]=30 entri[i]=28 entri[j]=29 entri[k]=151 entri[l]=52 | |
entri[m]=265 entri[n]=20 entri[o]=14 entri[p]=170 entri[q]=1 entri[r]=43 | |
entri[s]=119 entri[t]=110 entri[u]=19 entri[v]=7 entri[w]=10 entri[x]=1 | |
entri[y]=2 entri[z]=4 | |
# Looping entri dari a-z | |
for i in "${!entri[@]}" | |
do | |
# Sedot semua lema dari halaman satu s.d halaman maksimum | |
halaman_maksimum=${entri[$i]} | |
for ((c=1; c<=$halaman_maksimum; c++)) | |
do | |
wget --no-proxy -q $url'idx='$i'&p='$c -O - | grep -o 'phrase=[^""]\+' | sed -e 's/phrase=//g' >> lema.txt | |
done | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment