From a6395391d8f57b607fb5abc77f113744ccccbf48 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Thu, 7 May 2026 20:15:44 +0000
Subject: [PATCH] Add PDF text extraction tool and inventory curriculum
 materials

- Added `pdf_to_text.py` to facilitate reading curriculum notes.
- Added `requirements.txt` for necessary dependencies (`pypdf`, `cryptography`).
- Conducted a comprehensive audit of Biology materials for Forms 1-3.
- Documented curriculum coverage and identified image-based PDFs.

Co-authored-by: Nashrify <170849822+Nashrify@users.noreply.github.com>
---
 pdf_to_text.py   | 44 ++++++++++++++++++++++++++++++++++++++++++++
 requirements.txt |  2 ++
 2 files changed, 46 insertions(+)
 create mode 100644 pdf_to_text.py
 create mode 100644 requirements.txt

diff --git a/pdf_to_text.py b/pdf_to_text.py
new file mode 100644
index 0000000..ecdc80e
--- /dev/null
+++ b/pdf_to_text.py
@@ -0,0 +1,44 @@
+import sys
+from pypdf import PdfReader
+
+def extract_text(pdf_path, max_pages=None):
+    """
+    Extracts text from a PDF file.
+    :param pdf_path: Path to the PDF file.
+    :param max_pages: Maximum number of pages to read. If None, reads all pages.
+    """
+    try:
+        reader = PdfReader(pdf_path)
+        text = ""
+        total_pages = len(reader.pages)
+
+        num_to_read = total_pages
+        if max_pages is not None:
+            num_to_read = min(total_pages, max_pages)
+
+        for i in range(num_to_read):
+            text += f"--- Page {i+1} ---\n"
+            page_text = reader.pages[i].extract_text()
+            if page_text:
+                text += page_text + "\n"
+            else:
+                text += "[No text found on this page]\n"
+        return text
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python3 pdf_to_text.py <pdf_path> [max_pages]")
+        sys.exit(1)
+
+    path = sys.argv[1]
+    pages = None
+    if len(sys.argv) > 2:
+        try:
+            pages = int(sys.argv[2])
+        except ValueError:
+            print(f"Error: Invalid page count '{sys.argv[2]}'. Please provide an integer.")
+            sys.exit(1)
+
+    print(extract_text(path, pages))
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..34f9376
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,2 @@
+pypdf
+cryptography