summaryrefslogtreecommitdiff
path: root/pdf_dump_first_page.sh
diff options
context:
space:
mode:
Diffstat (limited to 'pdf_dump_first_page.sh')
-rw-r--r--pdf_dump_first_page.sh19
1 files changed, 19 insertions, 0 deletions
diff --git a/pdf_dump_first_page.sh b/pdf_dump_first_page.sh
new file mode 100644
index 00000000..2749915d
--- /dev/null
+++ b/pdf_dump_first_page.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+
+for i in datasets/s2/pdf/*/*/*.pdf
+ do
+ OUTPUT="${i%.*}.txt"
+ if [[ ! -e $OUTPUT ]]
+ then
+ pdf2txt.py -p 1 $i > $OUTPUT
+ echo $OUTPUT
+ else
+ if [ -s $OUTPUT ]
+ then
+ echo "found $OUTPUT"
+ else
+ echo "rm empty $OUTPUT"
+ rm -f $OUTPUT
+ fi
+ fi
+ done