From 4d0fc39c2a7a2974a3e5402990010dcd3b7bd596 Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Sun, 25 Nov 2018 22:20:29 +0100 Subject: mv --- scraper/pdf_dump_first_page.sh | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 scraper/pdf_dump_first_page.sh (limited to 'scraper') diff --git a/scraper/pdf_dump_first_page.sh b/scraper/pdf_dump_first_page.sh new file mode 100644 index 00000000..2749915d --- /dev/null +++ b/scraper/pdf_dump_first_page.sh @@ -0,0 +1,19 @@ +#!/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 + else + if [ -s $OUTPUT ] + then + echo "found $OUTPUT" + else + echo "rm empty $OUTPUT" + rm -f $OUTPUT + fi + fi + done -- cgit v1.2.3-70-g09d2