From 110f3a34f1f36d0ea999d4aa34bbe66d5f2a01da Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Sun, 16 Dec 2018 15:02:59 +0100 Subject: skip empty, pull citations again --- scraper/pdf_dump_first_page.sh | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'scraper/pdf_dump_first_page.sh') diff --git a/scraper/pdf_dump_first_page.sh b/scraper/pdf_dump_first_page.sh index 2749915d..6277d40c 100644 --- a/scraper/pdf_dump_first_page.sh +++ b/scraper/pdf_dump_first_page.sh @@ -6,7 +6,13 @@ for i in datasets/s2/pdf/*/*/*.pdf if [[ ! -e $OUTPUT ]] then pdf2txt.py -p 1 $i > $OUTPUT - echo $OUTPUT + if [ -s $OUTPUT ] + then + echo "found $OUTPUT" + else + echo "rm empty $OUTPUT" + rm -f $OUTPUT + fi else if [ -s $OUTPUT ] then -- cgit v1.2.3-70-g09d2