pdf_dump_first_page.sh


1
2
3
4
5
6
7
8
9
10
11

#!/bin/bash

for i in datasets/s2/pdf/*/*/*.pdf
  do
    OUTPUT="${i%.*}.txt"
    if [ ! -e $OUTPUT ]
    then
      pdf2txt.py -p 1 $i > $OUTPUT
      echo $OUTPUT
    fi
  done