diff options
Diffstat (limited to 'scraper/pdf_dump_all.sh')
| -rw-r--r-- | scraper/pdf_dump_all.sh | 20 |
1 files changed, 0 insertions, 20 deletions
diff --git a/scraper/pdf_dump_all.sh b/scraper/pdf_dump_all.sh deleted file mode 100644 index a17c8d44..00000000 --- a/scraper/pdf_dump_all.sh +++ /dev/null @@ -1,20 +0,0 @@ -#!/bin/bash - -for i in datasets/s2/pdf/*/*/*.pdf - do - OUTPUT="${i%.*}.txt" - OUTPUT="${OUTPUT/pdf/txt}" - IMDIR=`dirname ${OUTPUT}` - if [[ ! -e $OUTPUT ]] - then - pdf2txt.py -o "${OUTPUT}" -O "${IMDIR}" "${i}" - if [ -s $OUTPUT ] - then - echo "found $OUTPUT" - else - echo "rm empty $OUTPUT" - rm -f $OUTPUT - fi - fi - done - |
