diff --git a/.gitattributes b/.gitattributes
index 028854857bec63c21eab69e57480c6833001f759..891e72772941b5e7894128c9e99522c17c507040 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -135,3 +135,4 @@ data/AB/1968/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1969/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1970/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1971/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1972/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/8ab3b6e7fe354bdd86bb7165cfd4c663_python.cwl b/.renku/workflow/8ab3b6e7fe354bdd86bb7165cfd4c663_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..307c6119cfa223bded5586236968c97ccf876875
--- /dev/null
+++ b/.renku/workflow/8ab3b6e7fe354bdd86bb7165cfd4c663_python.cwl
@@ -0,0 +1,51 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_origxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1972/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1972/02_extractedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_3)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1972
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1972/02_extractedxml.tar.gz b/data/AB/1972/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..0942484c7de29e31eb54042cda57945653e4c8db
--- /dev/null
+++ b/data/AB/1972/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b875f234b384a4fc3ce819208fb27584450e548f0222df77336c3ce2c29be6
+size 437180559