Update mdr_pdf_parser.py
Browse files- mdr_pdf_parser.py +0 -20
mdr_pdf_parser.py
CHANGED
|
@@ -18,26 +18,6 @@
|
|
| 18 |
|
| 19 |
|
| 20 |
|
| 21 |
-
# -*- coding: utf-8 -*-
|
| 22 |
-
# /=====================================================================\ #
|
| 23 |
-
# | MagicDataReadiness - MAGIC PDF Parser | #
|
| 24 |
-
# |---------------------------------------------------------------------| #
|
| 25 |
-
# | Description: | #
|
| 26 |
-
# | Extracts structured content (text, tables, figures, formulas) | #
|
| 27 |
-
# | from PDF documents using layout analysis and OCR. | #
|
| 28 |
-
# | Combines logic from various internal components. | #
|
| 29 |
-
# |---------------------------------------------------------------------| #
|
| 30 |
-
# | Dependencies: | #
|
| 31 |
-
# | - Python 3.11+ | #
|
| 32 |
-
# | - External Libraries (See imports below and installation notes) | #
|
| 33 |
-
# | - Pre-trained CV Models (Downloaded automatically to model dir) | #
|
| 34 |
-
# |---------------------------------------------------------------------| #
|
| 35 |
-
# | Usage: | #
|
| 36 |
-
# | See the __main__ block at the end of the script for an example. | #
|
| 37 |
-
# \=====================================================================/ #
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
# --- External Library Imports ---
|
| 42 |
import os
|
| 43 |
import re
|
|
|
|
| 18 |
|
| 19 |
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
# --- External Library Imports ---
|
| 22 |
import os
|
| 23 |
import re
|