Used pypdf to create extract_specification_document_tables in parsing.py. Should allow easier indexing of the various file types in future. Will need to adapt for files other than .MCA and look at formalising into a local database.

2026-05-22 01:11:24 +01:00
parent 51c6af9782
commit 14b17a22d7
3 changed files with 124 additions and 3 deletions
@@ -7,7 +7,10 @@ authors = [
 ]
 requires-python = ">=3.14"
 dependencies = [
-    "requests (>=2.34.2,<3.0.0)"
+    "requests (>=2.34.2,<3.0.0)",
+    "pypdf (>=6.12.0,<7.0.0)",
+    "pandas (>=3.0.3,<4.0.0)",
+    "pandas-stubs (>=3.0.0.260204,<4.0.0.0)"
 ]