scraper/pdf_dump_first_page.sh


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17

#!/bin/bash

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