🚧 zdb2ocr: Produce OCR of ZEFYS newspapers (WIP)
parent
3b60b26c53
commit
9303f4b4df
@ -0,0 +1,23 @@
|
|||||||
|
#!/bin/sh
|
||||||
|
zdb=27974534
|
||||||
|
yyyymmdd=19010712
|
||||||
|
|
||||||
|
set -e
|
||||||
|
|
||||||
|
self_dir=`dirname $0`
|
||||||
|
self_dir=`realpath $self_dir`
|
||||||
|
|
||||||
|
|
||||||
|
workspace=$zdb-$yyyymmdd
|
||||||
|
mkdir "$workspace"
|
||||||
|
cd "$workspace"
|
||||||
|
pwd
|
||||||
|
zefys_url="https://content.staatsbibliothek-berlin.de/zefys/SNP$zdb-$yyyymmdd-0-0-0-0.xml"
|
||||||
|
echo "$zefys_url"
|
||||||
|
curl "$zefys_url" > mets.xml
|
||||||
|
|
||||||
|
|
||||||
|
ocrd workspace validate mets.xml | grep -v "<notice>Won't download remote image"
|
||||||
|
|
||||||
|
|
||||||
|
$self_dir/run-docker-hub -I MAX --skip-validation
|
Loading…
Reference in New Issue