]> _ Git - cubist_pdf.git/commitdiff
#7678 @1
authorVincent Vanwaelscappel <vincent@cubedesigners.com>
Mon, 4 Aug 2025 12:57:36 +0000 (14:57 +0200)
committerVincent Vanwaelscappel <vincent@cubedesigners.com>
Mon, 4 Aug 2025 12:57:36 +0000 (14:57 +0200)
resources/tools/docling/convert_page.py

index 78649326b6306d2b3e025e488b9a9d5d5f33e0b1..1e294696a403eeea24d1bbc5adbbb1e15fb4a615 100644 (file)
@@ -20,7 +20,10 @@ converter = DocumentConverter(
     }
 )
 result = converter.convert(sys.argv[1])
+allpages=result.document.export_to_markdown(page_break_placeholder="<!-- page break -->", image_mode=ImageRefMode.EMBEDDED);
+Path(sys.argv[2]+"document.md").write_text(allpages)
 i=0
-for md in result.document.export_to_markdown(page_break_placeholder="<!-- page break -->", image_mode=ImageRefMode.EMBEDDED).split("<!-- page break -->"):
+for md in allpages.split("<!-- page break -->"):
     i+=1
-    Path(sys.argv[2]+"p"+str(i)+".md").write_text(md)
\ No newline at end of file
+    Path(sys.argv[2]+"p"+str(i)+".md").write_text(md)
+