Created
March 6, 2016 00:04
-
-
Save oskopek/86a71ccb55266a150521 to your computer and use it in GitHub Desktop.
A simple webscraping bash script for the 2016 Elections in Slovakia
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
| file=vysledky.html | |
| out=vysledky.tmp | |
| res=vysledky | |
| while true; do | |
| : > $out | |
| echo -e '<html><head>\n | |
| <meta charset="UTF-8">\n | |
| </head>\n<body>' >> $out | |
| echo `date` | |
| curl -s http://www.vysledkyvolieb.sk/parlamentne-volby/2016/priebezne-vysledky > $file | |
| echo `date` `cat $file | grep -o '[0-9].*% hlasov'` `echo "<br><br>"` >> $out | |
| echo -e "\nPredbezne vysledky:<br><br><ol>" >> $out | |
| #cat $file | grep -E '/strana/' | sed -E 's/<[^>]*>//g' | sed -E 's/<\/a>//g' >> $out | |
| #cat $file | grep -E '(strana)|([0-9]*,[0-9]*)' | sed -E 'N;s/\n([0-9]*,[0-9]*)/ \1/g' | sed -E 's/<[^>]*>//g' | sed -E 's/<\/a>//g' | tail -n 49 | head -n -3 | sed -E 's/$/<\/li><br>/g' | sed -E 's/^/<li>/g' >> $out | |
| cat $file | grep -E '(href=\"/parlamentne-volby/strana/)|([0-9]+,[0-9]+)' | tail -n 46 | sed -E 'N;s/\n([0-9]*,[0-9]*)/ \1/g' | sed -E 's/<[^>]*>//g' | sed -E 's/<\/a>//g' | sed -E 's/$/<\/li><br>/g' | sed -E 's/^/<li>/g' >> $out | |
| echo '</ol></body></html>' >> $out | |
| cp $out $res | |
| sleep 10s | |
| done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment