From 7885a180e1b3ddc37ef2192c74a897b911e48a14 Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Wed, 20 Feb 2019 16:05:25 +0100 Subject: adding countries to citation feed / geocode step --- scraper/pdf_dump_first_page.sh | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 scraper/pdf_dump_first_page.sh (limited to 'scraper/pdf_dump_first_page.sh') diff --git a/scraper/pdf_dump_first_page.sh b/scraper/pdf_dump_first_page.sh deleted file mode 100644 index 20e5182d..00000000 --- a/scraper/pdf_dump_first_page.sh +++ /dev/null @@ -1,17 +0,0 @@ -#!/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 -- cgit v1.2.3-70-g09d2