summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--scraper/pdf_dump_all.sh20
1 files changed, 20 insertions, 0 deletions
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
+