add OpenLibraryWorks

2 files changed, 37 insertions, 0 deletions

diff --git a/python/notes/version_4.md b/python/notes/version_4.md
index 7b45083..a78f9e1 100644
--- a/python/notes/version_4.md
+++ b/python/notes/version_4.md
@@ -73,3 +73,18 @@ Example:
 
 * https://openlibrary.org/works/OL488811W/The_debt?edition=debtwhatamerica000robi
 
+```
+{
+  "biblio": {
+    "container_name": "BLACK AFRICA: The Economic and Cultural Basis for a Federated State",
+    "unstructured": "For details on African Renaissance see Cheikh Anta Diop, BLACK AFRICA: The Economic and Cultural Basis for a Federated State, New Expanded Edition. Trenton, NJ: Africa World Press, 1987.",
+    "year": 1987
+  },
+  "index": 28,
+  "key": "8_CR29",
+  "ref_source": "crossref",
+  "release_year": 2009,
+  "release_ident": "2igycuiobvhxrcmmrzz6anufuq",
+  "work_ident": "aaacj23jqbdxvajwj5kc6jpejq"
+}
+```
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index a82c535..faf76fd 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -685,3 +685,25 @@ class BrefZipFuzzy(Refcat):
 
     def output(self):
         return luigi.LocalTarget(path=self.path(ext="json.zst"), format=Zstd)
+
+
+class OpenLibraryWorks(Refcat):
+    """
+    Extract just the works.
+    """
+    def requires(self):
+        return OpenLibraryDump()
+
+    def run(self):
+        output = shellout("""
+                          zstdcat -T0 {input} |
+                          parallel -j {n} --block 10M --pipe "jq -rc 'select(.type == \\"work\\")'" |
+                          zstd -T0 -c > {output}
+                          """,
+                          n=self.n,
+                          tmpdir=self.tmpdir,
+                          input=self.input().path)
+        luigi.LocalTarget(output).move(self.output().path)
+
+    def output(self):
+        return luigi.LocalTarget(path=self.path(ext="json.zst"), format=Zstd)