Created
March 26, 2014 15:27
-
-
Save AyoubOuarrak/9785986 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 | |
url="http://cercauniversita.cineca.it/php5/docenti/vis_docenti.php" | |
for area in 01 02 03 04 05 06 07 08 09 10 11 12 13 14 | |
do | |
echo "[ downloading area$area ]" | |
wget -q --post-data "area=$area&\ | |
cognome=&\ | |
conferma=2&\ | |
facolta=00&\ | |
facolta_st=00&\ | |
macro=0000&nome=&\ | |
pagina=%5CA&\ | |
qualifica=**&\ | |
radiogroup=P&\ | |
settore=0000&\ | |
settorec=0000&\ | |
situazione_al=0&\ | |
testuale=1&\ | |
universita=00" $url | |
mv vis_docenti.php area$area.xls | |
echo "[ converting area$area.xls to area$area.csv ]" | |
localc --headless --convert-to ods area$area.xls | |
localc --headless --convert-to csv area$area.ods | |
echo "[ converting area$area.csv from cp1251 to utf8 ]" | |
touch utf8$area.csv | |
iconv -f cp1251 -t utf8 area$area.csv > utf8$area.csv | |
done | |
echo "[ copy data to the DB ]" | |
psql -c "drop table organico_crudo;" | |
psql -c "create table organico_crudo (\ | |
fascia varchar,\ | |
cognome_nome varchar,\ | |
ateneo varchar,\ | |
facolta varchar,\ | |
ssd varchar,\ | |
sc varchar,\ | |
dipartimento varchar\ | |
);" | |
for area in 01 02 03 04 05 06 07 08 09 10 11 12 13 14 | |
do | |
psql -c "\COPY organico_crudo FROM 'utf8$area.csv' DELIMITERS ',' CSV HEADER;" | |
done | |
echo "[ cleaning ]" | |
rm area*.csv | |
rm area*.ods | |
rm area*.xls | |
rm utf8*.csv | |
echo "done" | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment