Update modify_pdf.py

modify_pdf.py

@@ -1,44 +1,44 @@
-import pdfplumber
-from reportlab.pdfgen import canvas
-from reportlab.lib.pagesizes import letter
-from PyPDF2 import PdfWriter, PdfReader
+import fitz  # PyMuPDF
 
 def modify_pdf(input_pdf, output_pdf, scale_text=1.2, line_thickness=1.2):
     """
-    Modify text size and thickness in a PDF, preserving vector data and layers.
+    Modify text size and thickness in a PDF while preserving vector data and layers.
+
     Args:
         input_pdf (str): Path to the input PDF file.
         output_pdf (str): Path to save the modified PDF.
         scale_text (float): Factor to scale text size.
         line_thickness (float): Factor to adjust text thickness.
     """
-    # Step 1: Extract text and vector elements
-    with pdfplumber.open(input_pdf) as pdf:
-        pages = pdf.pages
-        c = canvas.Canvas(output_pdf, pagesize=letter)
-        for page_number, page in enumerate(pages):
-            # Extract all text elements
-            text_objects = page.extract_words()
-            for text_obj in text_objects:
-                # Scale text size
-                x, y, width, height = text_obj["x0"], text_obj["top"], text_obj["x1"], text_obj["bottom"]
-                new_size = height * scale_text
-                c.setFont("Helvetica", new_size)
-                c.drawString(x, y, text_obj["text"])
-            
-            # Optionally handle vector data (if available)
-            # PDF vector paths modification can be added if pdfplumber provides access
-            
-        c.save()
-    
-    # Step 2: Merge with original PDF for vector layer preservation
-    original = PdfReader(input_pdf)
-    modified = PdfReader(output_pdf)
-    writer = PdfWriter()
-    for page in original.pages:
-        writer.add_page(page)
-    for page in modified.pages:
-        writer.add_page(page)
-    with open(output_pdf, "wb") as f:
-        writer.write(f)
-    print(f"Saved modified PDF to {output_pdf}")
+    doc = fitz.open(input_pdf)
+    for page in doc:
+        # Process text objects
+        try:
+            for text_instance in page.search_for(" "):  # Use a space as placeholder to find text blocks
+                # Extract text properties
+                text = page.get_text("text", clip=text_instance)
+                bbox = text_instance
+                font_size = bbox[3] - bbox[1]  # Approximation of text height
+
+                # Replace text with scaled size
+                page.delete_text(text_instance)
+                page.insert_text(
+                    (bbox[0], bbox[1]),
+                    text,
+                    fontsize=font_size * scale_text,
+                    overlay=True
+                )
+        except Exception as e:
+            print(f"Error modifying text size on page {page.number + 1}: {e}")
+
+        # Process vector paths for thickness
+        try:
+            for shape in page.get_drawings():
+                for path in shape["items"]:
+                    if "line_width" in path:
+                        path["line_width"] *= line_thickness
+        except Exception as e:
+            print(f"Error modifying text thickness on page {page.number + 1}: {e}")
+
+    doc.save(output_pdf)
+    print(f"Modified PDF saved to {output_pdf}")