The Hindu Newspaper Download Script

#!/bin/bash #ishan dot karve at gmail dot com # #Script to download epaper from Hindu #No more subscription .. pls donate the money to Prime Ministers Welfare Fund #As always /// Its free to use... #Get user to select edition edition_choice=([0]=101 edition_choice=([0]=10 1 [1]=102 [2]=103 [3]=104 [4]=105 ) edition_name=([0]=Chennai edition_name=([0]=Chen nai [1]=Hyderabad [2]=Delhi [3]=Bangalore [4]=Kochi ) echo "Hindu epaper editions are" echo "-----------------------"------------------------------------------------------------------------" -" echo "0. Chennai" echo "1. Hyderabad" echo "2. Delhi" echo "3. Bangalore" echo "4. Kochi" echo "-----------------------"------------------------------------------------------------------------" -" while true; do read -p "Enter edition you wish to selec[0-4]: " ed case $ed in [01234]) echo "Thanks." break;; * ) echo "Please select the correct numeric serial.";; esac done read -p "----- Year ?(eg-2012) : " year read -p "----- Month ?(eg?(eg- 05 for may) : " month read -p "----- Date ?(eg-01,02..) : " date #spider the selected edition using wget to estimate number of pages #define max incremental page limit max_spider=100 echo "Estimating number of pages in ${edition_name[ed]} edition" #start spider for main editon for (( j = 1 ; j <= $max_spider; j++ )) do #prepend zero to single digits pageno=`printf "%03d" $j` echo "Searching for Page $pageno" I_FILE="http://epaper.thehindu.com/pdf/$year/$mo I_FILE="http://epaper.th ehindu.com/pdf/$year/$month/$date/$year$month${da nth/$date/$year$month${dat t e}A_$pageno${edition_choice[ed]}.pdf" debug=`wget --spider $I_FILE 2>&1` #echo $debug if [[ $debug =~ .*link!!!.* ]] then break fi echo "ok.. page $pageno exists" done echo "$pageno pages in the main paper" #clear #decrement counter (( j = j - 1 )) npages_A=$j echo "Estimating number of pages in ${edition_name[ed]} edition supplement"

#start spider for newapaper supplement for (( j = 1 ; j <= $max_spider; j++ )) do #prepend zero to single digits pageno=`printf "%03d" $j` echo "Searching for Page $pageno" I_FILE="http://epaper.thehindu.com/pdf/$year/$month/$date/$year$month${dat e}B_$pageno${edition_choice[ed]}.pdf" debug=`wget --spider $I_FILE 2>&1` # echo $debug if [[ $debug =~ .*link!!!.* ]] then break fi done #clear #decrement counter (( j = j - 1 )) npages_B=$j ty_dir="${HOME}"/Desktop/"hindu_${edition_name[ed]}_${year}_${month}_${date}" #mkdir to store individual pages mkdir $ty_dir echo "Please be patient..Bandwidth intensive operation starts..;-)" echo "Downloading Main Paper .. total $npages_A pages" for (( i = 1 ; i <= npages_A; i++ )) do #prepend zero to single digits pageno=`printf "%03d" $i` echo "Downloading Page $pageno" O_FILE="$ty_dir/A$pageno.pdf" I_FILE="http://epaper.thehindu.com/pdf/$year/$month/$date/$year$month${dat e}A_$pageno${edition_choice[ed]}.pdf" wget -q -O $O_FILE $I_FILE done echo "Downloading Supplement .. total $npages_B pages" for (( i = 1 ; i <= npages_B; i++ )) do #prepend zero to single digits pageno=`printf "%03d" $i` echo "Downloading Page $pageno" O_FILE="$ty_dir/B$pageno.pdf" I_FILE="http://epaper.thehindu.com/pdf/$year/$month/$date/$year$month${dat e}B_$pageno${edition_choice[ed]}.pdf" wget -q -O $O_FILE $I_FILE done echo "Combining all pages into a single pdf document" #combine multiple pdf files gs -dNOPAUSE -sDEVICE=pdfwrite -sOUTPUTFILE=$HOME/Desktop/The_Hindu_${edition_na me[ed]}_${year}_${month}_${date}.pdf -dBATCH $ty_dir/*.pdf #empty directory rm $ty_dir/*.*

#remove directory rmdir $ty_dir