summaryrefslogtreecommitdiff
path: root/scraper/pdf_dump_all.sh
diff options
context:
space:
mode:
authorJules Laplace <julescarbon@gmail.com>2019-02-20 16:05:25 +0100
committerJules Laplace <julescarbon@gmail.com>2019-02-20 16:05:25 +0100
commit7885a180e1b3ddc37ef2192c74a897b911e48a14 (patch)
treebac496d50008c035668d7e6c0143b7ecabd3193d /scraper/pdf_dump_all.sh
parent8f0d09f4c5bfb8b09757c3dbdb6d29061f0405d4 (diff)
adding countries to citation feed / geocode step
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
-