import sys
+import os
from pathlib import Path
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
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
+j=0
for md in allpages.split("<!-- page break -->"):
i+=1
- Path(sys.argv[2]+"p"+str(i)+".md").write_text(md)
+ j+=1
+ while os.stats(Path(sys.argv[2] + "/../texts/ph{j}.html")).st_size < 21:
+ Path(sys.argv[2]+"p"+str(j)+".md").write_text("")
+ j+=1
+ Path(sys.argv[2]+"p"+str(j)+".md").write_text(md)