summaryrefslogtreecommitdiff
path: root/scraper/pdf_dump_first_page.sh
diff options
context:
space:
mode:
authorJules Laplace <julescarbon@gmail.com>2018-12-16 15:02:59 +0100
committerJules Laplace <julescarbon@gmail.com>2018-12-16 15:02:59 +0100
commit110f3a34f1f36d0ea999d4aa34bbe66d5f2a01da (patch)
treef21fbeccb6a7e8d3af5d5c537ed5931ecbd62d7e /scraper/pdf_dump_first_page.sh
parent2cb31d4999649a22a0ac659a59a0aa0a0f7a241e (diff)
skip empty, pull citations again
Diffstat (limited to 'scraper/pdf_dump_first_page.sh')
-rw-r--r--scraper/pdf_dump_first_page.sh8
1 files changed, 7 insertions, 1 deletions
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