Created
February 19, 2013 23:31
-
-
Save arturoherrero/4991254 to your computer and use it in GitHub Desktop.
Download issuu documents. Credits: http://www.kurtsik.org/blog/?p=1068
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 | |
| # Script para descargar los documentos de issuu.com como imagenes JPG | |
| # y convertirlos a PDF. | |
| # kurtsik-2011 | |
| # | |
| TMP_DIR="/tmp/issud/" | |
| TMP_FILE="issuufile" | |
| KONT=1 | |
| I_MAGICK=0 | |
| TITLE="" | |
| if [ -z "$1" ]; then | |
| echo "Script para descargar documentos de ISSUU" | |
| echo "Usage: `basename $0` URL" | |
| echo "" | |
| exit 1 | |
| fi | |
| if [ -z `which convert` ]; then | |
| echo "" | |
| echo "No esta disponible el comando convert." | |
| echo "El script puede continuar su ejecucion" | |
| echo "pero no se creara el PDF." | |
| read -p "Continuar? (s/n)" RESPUESTA | |
| if [ "$RESPUESTA" = "s" ]; then | |
| I_MAGICK=1 | |
| else | |
| exit 1 | |
| fi | |
| fi | |
| [ -e $TMP_DIR ] || mkdir $TMP_DIR | |
| wget -q --output-document=$TMP_DIR$TMP_FILE $1 | |
| DOCID=`grep -m 1 documentId $TMP_DIR$TMP_FILE | sed -e 's/.*documentId=//g' | sed -e 's/">//g' | sed -e 's/ //g'` | |
| TITLE=`grep "<title>" $TMP_DIR$TMP_FILE | sed -e 's/.*<title>//g' | sed -e 's/<\/title>//g' | sed -e 's/ //g'` | |
| while [ 1 ]; do | |
| let "FILENAME=$KONT+10000" | |
| sleep 5 | |
| wget -t 18 --wait=7 --random-wait --output-document=$TMP_DIR$FILENAME.jpg http://image.issuu.com/$DOCID/jpg/page_$KONT.jpg | |
| if [ ! `file -b --mime-type $TMP_DIR$FILENAME.jpg` = "image/jpeg" ]; then | |
| rm -f $TMP_DIR$FILENAME.jpg | |
| let "KONT=$KONT-1" | |
| break | |
| fi | |
| let "KONT=$KONT+1" | |
| done | |
| if [ "$KONT" = 0 ]; then | |
| echo "No he podido descargar ningun fichero de imagen." | |
| echo "Verifica la URL que has introducido." | |
| exit 1 | |
| fi | |
| echo "" | |
| echo "Resumen:" | |
| echo " Descargados $KONT ficheros de imagen." | |
| if [ $I_MAGICK ]; then | |
| convert $TMP_DIR*.jpg $TITLE.pdf | |
| echo " Creado el fichero: $TITLE.pdf" | |
| rm -rf $TMP_DIR | |
| else | |
| rm -f $TMP_DIR$TMP_FILE | |
| mv $TMP_DIR ./$TITLE | |
| echo " Creado el directorio $TITLE con los ficheros de imagen" | |
| fi | |
| echo " Done" | |
| exit 0 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment