improved pdfcreator

1- use CLI
2- refactor code

python/pdfcreator/driver.py

@@ -0,0 +1,99 @@
+# driver.py
+from pypdf import PageObject
+from pdfaggregator import *
+from pypdf import PdfReader, PdfWriter
+import argparse
+
+
+PDF_INPUTS = [
+    {"file": "pdfcreator/input.pdf", "sections": ["5", "@20-30"]},
+    # {"file": "pdfcreator/input2.pdf",
+    # "sections": ["3.1"]}
+]
+
+OUTPUT_PDF = "pdfcreator/extracted_sections.pdf"
+
+# crop ratios
+HEADER_CROP = 0.1
+FOOTER_CROP = 0.03
+
+
+def main(pdf_inputs, output_pdf):
+
+    content_writer = PdfWriter()
+    toc_entries = []
+    current_page = 0
+
+    for pdf_info in pdf_inputs:  # or change
+        REFERENCE_BOX = None
+        reader = PdfReader(pdf_info["file"])
+        outline_tree = build_outline_tree(reader)
+        total_pages = len(reader.pages)
+
+        for entry in pdf_info["sections"]:
+            page_indices = parse_page_range(entry)
+
+            if page_indices:
+                # Explicit page range
+                current_page, REFERENCE_BOX, toc_entry = extract_page_range(
+                    entry, reader, content_writer, current_page, REFERENCE_BOX,
+                    HEADER_CROP, FOOTER_CROP
+                )
+            else:
+                # Section prefix
+                current_page, REFERENCE_BOX, toc_entry = extract_section_prefix(
+                    entry, reader, content_writer, current_page, REFERENCE_BOX,
+                    outline_tree, HEADER_CROP, FOOTER_CROP
+                )
+
+        if toc_entry:
+            toc_entries.append(toc_entry)
+
+    # Create TOC PDF
+    toc_pdf = create_toc_pdf(toc_entries)
+    toc_page_count = len(toc_pdf.pages)
+
+    final_writer = PdfWriter()
+    # add TOC pages
+    for page in toc_pdf.pages:
+        final_writer.add_page(page)
+    # add content pages
+    for page in content_writer.pages:
+        final_writer.add_page(page)
+
+    # Add bookmarks
+    bookmark_stack = {}
+    for entry in toc_entries:
+        parent = bookmark_stack.get(entry["level"] - 1)
+        bm = final_writer.add_outline_item(
+            title=entry["title"],
+            page_number=(entry["page"] - 1) + toc_page_count,
+            parent=parent
+        )
+        bookmark_stack[entry["level"]] = bm
+
+    with open(output_pdf, "wb") as f:
+        final_writer.write(f)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Extract sections and page ranges from PDFs and aggregate into a new PDF with TOC and bookmarks."
+    )
+
+    parser.add_argument(
+        "-o", "--output",
+        required=True,
+        help="Output PDF file"
+    )
+
+    parser.add_argument(
+        "-i", "--inputs",
+        nargs="+",
+        help="Inputs in the form file.pdf:section1,section2 or file.pdf:@1-10"
+    )
+
+    args = parser.parse_args()
+    pdf_inputs = parse_inputs(args)
+
+    main(pdf_inputs, args.output)