summaryrefslogtreecommitdiff
path: root/scraper/pdf_dump_first_page.sh
diff options
context:
space:
mode:
authoradamhrv <adam@ahprojects.com>2018-12-15 19:57:49 +0100
committeradamhrv <adam@ahprojects.com>2018-12-15 19:57:49 +0100
commit82b2c0b5d6d7baccbe4d574d96e18fe2078047d7 (patch)
treea8784b7ec2bc5a0451c252f66a6b786f3a2504f5 /scraper/pdf_dump_first_page.sh
parent8e978af21c2b29f678a09701afb3ec7d65d0a6ab (diff)
parentc5b02ffab8d388e8a2925e51736b902a48a95e71 (diff)
Merge branch 'master' of github.com:adamhrv/megapixels_dev
Diffstat (limited to 'scraper/pdf_dump_first_page.sh')
-rw-r--r--scraper/pdf_dump_first_page.sh19
1 files changed, 19 insertions, 0 deletions
diff --git a/scraper/pdf_dump_first_page.sh b/scraper/pdf_dump_first_page.sh
new file mode 100644
index 00000000..2749915d
--- /dev/null
+++ b/scraper/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