diff options
Diffstat (limited to 'scraper/pdf_dump_first_page.sh')
| -rw-r--r-- | scraper/pdf_dump_first_page.sh | 8 |
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 |