Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import tempfile | |
| import re | |
| import os | |
| import spacy | |
| import pytesseract | |
| import pdf2image | |
| import subprocess | |
| from pdf2image.exceptions import ( | |
| PDFInfoNotInstalledError, | |
| PDFPageCountError, | |
| PDFSyntaxError | |
| ) | |
| import fitz # PyMuPDF | |
| from PIL import Image | |
| import io | |
| import base64 | |
| def clean_text(text): | |
| nlp = spacy.load("en_core_web_sm", disable=["tagger", "parser", "ner", "textcat"]) | |
| text = re.sub(r'\n+', '\n', text) | |
| text = re.sub(r'\s+', ' ', text) | |
| return text.strip() | |
| def image_to_latex(image): | |
| image_path = "/tmp/equation.png" # Modify as needed | |
| image.save(image_path) | |
| result = subprocess.run(["pix2tex", image_path], capture_output=True, text=True) | |
| return result.stdout | |
| def pdf_to_text(file): | |
| doc = fitz.open(file.name) | |
| full_text = '' | |
| for i, page in enumerate(doc): | |
| # Extract text | |
| page_text = page.get_text() | |
| # Extract images and convert to LaTeX | |
| image_list = page.get_images(full=True) | |
| for img in image_list: | |
| xref, name, ext, color_space, width, height, bpc, image_data, image_mask, smask_data = img | |
| # Ensure image_data is a bytes object before opening it | |
| if isinstance(image_data, str): | |
| image_data = image_data.encode() # Convert string to bytes if necessary | |
| image = Image.open(io.BytesIO(image_data)) | |
| latex_code = image_to_latex(image) | |
| page_text += "\n" + latex_code # Add LaTeX code to page text | |
| page_text = clean_text(page_text) | |
| if len(page_text.split()) > 5: | |
| page_number = i + 1 | |
| page_text = "## Metadata: Page Number " + str(page_number) + "\n" + page_text | |
| full_text += page_text + "\n\n" | |
| base_name = os.path.splitext(os.path.basename(file.name))[0] | |
| output_file_name = base_name + ".txt" | |
| with open(output_file_name, 'w') as f: | |
| f.write(full_text) | |
| return f"{output_file_name},{page_number}" | |
| iface = gr.Interface(fn=pdf_to_text, | |
| inputs=gr.inputs.File(label="Your PDF"), | |
| outputs="text", | |
| title="PDF to TXT", | |
| description="Convert your PDF files to clean text") | |
| iface.launch() | |