pdf-diff2.py

import fitz  # PyMuPDF
import difflib

def extract_text_from_pdf(file_path):
    doc = fitz.open(file_path)
    pages_text = []
    for page_num in range(len(doc)):
        page = doc.load_page(page_num)
        text = page.get_text()
        pages_text.append(text)
    return pages_text

def highlight_differences(pdf1_path, pdf2_path, output_path):
    doc1 = fitz.open(pdf1_path)
    pdf1_pages = extract_text_from_pdf(pdf1_path)
    pdf2_pages = extract_text_from_pdf(pdf2_path)

    # Keep track of highlighted instances to avoid duplicates
    highlighted_instances = set()

    for page_num, (text1, text2) in enumerate(zip(pdf1_pages, pdf2_pages)):
        if text1 != text2:
            # Use difflib to find differences line by line
            diff = list(difflib.ndiff(text1.splitlines(), text2.splitlines()))
            page = doc1.load_page(page_num)

            # Track lines that have been removed, added, or changed
            removed_lines = set()
            added_lines = set()
            changed_lines = []

            # Collect removed and added lines
            for line in diff:
                if line.startswith("- "):
                    removed_lines.add(line[2:].strip())
                elif line.startswith("+ "):
                    added_lines.add(line[2:].strip())

            # Detect changed lines
            sm = difflib.SequenceMatcher(None, text1.splitlines(), text2.splitlines())
            for tag, i1, i2, j1, j2 in sm.get_opcodes():
                if tag == 'replace':
                    for i in range(i1, i2):
                        changed_lines.append((text1.splitlines()[i].strip(), text2.splitlines()[j1].strip()))

            for line in diff:
                text_to_highlight = line[2:].strip()
                color = None
                note_content = ""

                # Check for replaced lines
                if line.startswith("- ") and (i + 1 < len(diff) and diff[i + 1].startswith("+ ")):
                    new_line = diff[i + 1][2:].strip()
                    color = (0, 0, 1)  # Blue for replaced lines
                    note_content = f"Replaced: '{text_to_highlight}' with '{new_line}'"
                
                # Check for added lines
                elif line.startswith("+ "):
                    color = (0, 1, 0)  # Green for added lines
                    note_content = f"Added line: '{text_to_highlight}'"
                
                # Check for removed lines
                elif line.startswith("- "):
                    color = (1, 0, 0)  # Red for removed lines
                    note_content = f"Removed line: '{text_to_highlight}'"

                # Highlight only if a color has been set
                if color is not None:
                    print(f"Searching for: '{text_to_highlight}' on page {page_num + 1}")
                    text_instances = page.search_for(text_to_highlight)

                    for inst in text_instances:
                        if inst not in highlighted_instances:  # Check if already highlighted
                            annot = page.add_highlight_annot(inst)
                            annot.set_colors(stroke=color)  # Set the highlight color
                            annot.update()
                            if note_content:  # Add note if present
                                annot.set_info(title="Note", content=note_content)
                            highlighted_instances.add(inst)  # Mark this instance as highlighted
                    else:
                        print(f"No match found for: '{text_to_highlight}' on page {page_num + 1}")

            print(f"Differences highlighted on page {page_num + 1}.")

    # Save the annotated PDF
    doc1.save(output_path)
    print(f"Annotated PDF saved as '{output_path}'.")

# Specify paths
pdf1_path = "1.pdf"
pdf2_path = "4.pdf"
output_path = "output_annotated.pdf"

# Call the function to highlight differences
highlight_differences(pdf1_path, pdf2_path, output_path)