summaryrefslogtreecommitdiff
path: root/scraper/pdf_dump_all.sh
diff options
context:
space:
mode:
authorjules@lens <julescarbon@gmail.com>2019-02-20 16:21:53 +0100
committerjules@lens <julescarbon@gmail.com>2019-02-20 16:21:53 +0100
commite0038fbc4b891fe4393acfad8d9755fa1834278e (patch)
treec35aa2d2b0a76c10e57904ed1f41f5a7dcdd4870 /scraper/pdf_dump_all.sh
parent225b7936cd1b80effa4bf77b1ffc3c92a8f17526 (diff)
parent9b97ddf7e1bc1febc4066cd5e083cee688d77027 (diff)
mergez
Diffstat (limited to 'scraper/pdf_dump_all.sh')
-rw-r--r--scraper/pdf_dump_all.sh20
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
-