From 410b7c88aaaccb2ceaf778015cb5a696b561e03c Mon Sep 17 00:00:00 2001 From: "jules@lens" Date: Fri, 8 Feb 2019 23:23:45 +0100 Subject: pdf_dump_all.sh --- scraper/pdf_dump_all.sh | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 scraper/pdf_dump_all.sh diff --git a/scraper/pdf_dump_all.sh b/scraper/pdf_dump_all.sh new file mode 100644 index 00000000..a17c8d44 --- /dev/null +++ b/scraper/pdf_dump_all.sh @@ -0,0 +1,20 @@ +#!/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 + -- cgit v1.2.3-70-g09d2