| # scripts/extract_from_pdf.py | |
| import pdfplumber | |
| import os | |
| def extract_text_from_pdf(pdf_path, output_path): | |
| # Open the file for writing in append mode to ensure each page's content is saved immediately | |
| os.makedirs(os.path.dirname(output_path), exist_ok=True) | |
| with open(output_path, 'w', encoding='utf-8') as f: | |
| with pdfplumber.open(pdf_path) as pdf: | |
| for page_num, page in enumerate(pdf.pages, start=1): | |
| # Define bounding boxes for each column | |
| right_column = (page.width * 0.7, 0, page.width, page.height) | |
| # Extract text from the right column | |
| right_text = page.within_bbox(right_column).extract_text(x_tolerance=3, y_tolerance=3, layout=True) | |
| # Debug output to check extracted text | |
| print(f"\n--- Page {page_num} ---") | |
| print("Right column (proverbs):") | |
| print(right_text if right_text else "No text found in right column") | |
| # Write each line from the right column directly to the file | |
| if right_text: | |
| right_lines = right_text.split('\n') | |
| for line in right_lines: | |
| # Check and print each line before writing to verify it has content | |
| line = line.strip() | |
| if line: | |
| print(f"Writing line to file: {line}") | |
| f.write(line + '\n') | |
| print(f"Data successfully saved to {output_path}") | |
| if __name__ == "__main__": | |
| # Path to your PDF file | |
| pdf_path = r"C:\Users\moham\iraqi_arabic_llm_project\iraqi_proverbs.pdf" | |
| # Output path for the extracted proverbs | |
| output_path = "../data/raw_data/iraqi_data.txt" | |
| extract_text_from_pdf(pdf_path, output_path) | |