diff options
Diffstat (limited to 'scraper/pdf_dump_first_page.sh')
| -rw-r--r-- | scraper/pdf_dump_first_page.sh | 17 |
1 files changed, 0 insertions, 17 deletions
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 |
