site notes pdf to json 🟩

backend/documents_parser/pdf.py

@@ -1,5 +1,12 @@
 from typing import List
 
+import pymupdf
+
 
 def pdf_to_text_list(pdf_bytes: bytes) -> List[str]:
-    raise NotImplementedError
+    tokens: List[str] = []
+    with pymupdf.open(stream=pdf_bytes, filetype="pdf") as doc:
+        for page in doc:
+            for line in page.get_text().split("\n"):
+                tokens.append(line)
+    return tokens